Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 144 appraisals
The American journal of pathology
An Integrated Machine Learning and Genomic Framework for Precise Detection of Gastric Cancer
This study presents a novel integrative approach for the analysis of high-dimensional gene expression data, leveraging the complementary strengths of unsupervised clustering and supervised classification. Using K-means clustering, the data set is stratified into three distinct clusters, revealing intrinsic biological patterns and relationships. The resulting cluster assignments are subsequently used as pseudolabels to train machine learning models, including support vector machines, random forest, and a stacking ensemble classifier. To validate and enhance the robustness of clustering, complementary methods, such as hierarchical clustering and density-based spatial clustering of applications with noise (DBSCAN), are used, with results visualized through principal component analysis-driven dimensionality reduction. The high predictive accuracy achieved by the classifiers underlines the separability and reliability of the identified clusters. Furthermore, feature importance analysis highlighted key genetic determinants within each cluster, offering actionable insights into potential biomarkers and critical genomic features. This framework bridges the gap between exploratory unsupervised learning and predictive supervised modeling, providing a scalable and interpretable method for analyzing complex genomic data sets. Its applicability extends to biomarker discovery, patient stratification, and other precision medicine applications, emphasizing its utility in advancing genomic research and clinical practice.
3 Aug 2026
Read appraisal →Clinical & translational oncology : official publication of the Federation of Spanish Oncology Societies and of the National Cancer Institute of Mexico
Research progress of machine learning applications in gastric cancer diagnosis and therapy
Gastric cancer (GC), a malignant neoplasm originating from the gastric mucosal epithelium, represents one of the most prevalent cancers worldwide. Early detection is critical for improving treatment outcomes and patient prognosis. Recent advances in artificial intelligence (AI), particularly in machine learning, have introduced powerful computational and analytical capabilities that are increasingly being applied in GC research. Machine learning algorithms have shown considerable promise in enhancing the accuracy of GC diagnosis and optimizing therapeutic strategies. This review provides a concise overview of progress in machine learning applications within oncology, examines their current role and clinical utility in GC diagnosis and treatment, and highlights the transformative potential of machine learning in advancing GC management and patient care.
2 Aug 2026
Read appraisal →Scientific reports
Safety design guidelines for clinician-AI interaction in computer-aided diagnosis systems using system-theoretic framework with explainability validation
Ensuring the safety of Artificial Intelligence-enabled Computer-Aided Diagnosis systems is critical because diagnostic errors can have serious consequences for patient care. However, existing regulatory and risk management frameworks often do not sufficiently address the complex socio-technical interactions between clinicians and Artificial Intelligent systems, leaving key human-centered safety challenges underexplored. This paper presents a systematic and human-centered approach to deriving safety design guidelines for clinician-Artificial Intelligence interaction in Computer-Aided Diagnosis systems using System-Theoretic Process Analysis. Through this analysis, we identify critical hazards associated with clinician-Artificial Intelligence collaboration, including automation bias on system recommendations, and misinterpretation of explanations. Based on the identified unsafe control actions, we formulate a set of actionable and traceable safety design guidelines that promote transparency, coherent explanations, and calibrated trust in Artificial Intelligence-assisted decision-making. To bridge safety analysis and system design, the proposed guidelines are operationalized within a Computer-Aided Diagnosis interaction framework. The framework includes a safety-oriented Graphical User Interface that integrates multiple explanation methods and interactive mechanisms to promote clinician engagement. Furthermore, we introduce a safety-oriented evaluation approach that uses consistency across multiple explanation methods as a quantitative indicator of potentially unreliable or ambiguous explanations. By linking System-Theoretic Process Analysis, interaction design, and explainability evaluation, this work provides a unified and reusable framework for improving the safety and reliability of Artificial Intelligence-driven Computer-Aided Diagnosis systems.
31 July 2026
Read appraisal →Human vaccines & immunotherapeutics
Artificial intelligence in immune checkpoint inhibitor research: A bibliometric analysis of the landscape
This bibliometric analysis examines the transformative role of artificial intelligence (AI) in immune checkpoint inhibitor (ICI) research. Using VOSviewer, CiteSpace, and Bibliometrix, we analyzed 1,938 publications from the Web of Science Core Collection (2015-2026), revealing a dramatic rise in AI-related ICI studies, led by China and the USA. Key findings demonstrate AI's integration in predicting treatment response, optimizing dosing strategies, and managing immune-related adverse events. Through keyword co-occurrence and citation analyses, we identify critical AI applications including digital pathology and tumor microenvironment characterization. This comprehensive overview provides valuable insights into research trends and emerging frontiers for AI-driven innovations in cancer immunotherapy.
30 July 2026
Read appraisal →Journal of chemical information and modeling
Functionally Guided Graph Learning for Robust Cross-Patient Cell-Type Annotation in Single-Cell RNA Sequencing
Cross-patient cell-type annotation in single-cell RNA sequencing (scRNA-seq) remains challenging due to pronounced interpatient heterogeneity and distribution shifts across patient-specific cellular contexts. Conventional annotation approaches often rely on proximity-driven graph construction or expression similarity, which may introduce spurious cell-cell connections and lead to unstable knowledge transfer across patients. To address this limitation, we propose PathoGraph, a functionally guided graph learning framework for robust cross-patient cell-type annotation. The proposed method integrates KEGG-7-based biosemantic graph structure learning with cross-patient representation adaptation. Specifically, pathway-derived functional semantic profiles are incorporated to refine patient-specific cell graphs, encouraging biologically coherent neighborhoods and suppressing noise introduced by purely expression-based similarity. Based on the refined graphs, a cross-patient representation adaptation mechanism further aligns embeddings between labeled reference patients and unlabeled query patients to facilitate reliable annotation transfer. Experiments on three cross-patient scRNA-seq data sets, including leukemia, breast invasive carcinoma, and colorectal cancer data sets, demonstrate that PathoGraph achieves stable annotation performance across 32 directed reference-to-query transfer tasks. Across all tasks, PathoGraph obtained an average ACC of 84.28% and an F1-score of 84.08%, showing competitive and stable performance compared with representative marker-based, correlation-based, and model-based annotation methods. Ablation studies further show that removing the biosemantic graph learning module reduces the average accuracy to 83.48%, highlighting the importance of functional-guided graph refinement. In addition, post hoc functional relevance analyses in immune-cell and cancer-associated contexts suggest that the learned cell-cell graphs capture biologically relevant neighborhood structures beyond expression-driven proximity. The source code and processed data are publicly available at: https://github.com/LiYuechao1998/PathoGraph.
29 July 2026
Read appraisal →Cell reports methods
Data modeling the interplay between single-cell shape, single-cell protein expression, and tissue state.
While cell shape fundamentally governs tissue function, the underlying links between single-cell shape and protein expression have been difficult to resolve due to limitations in imaging multiplexing and population averaging. Here, we use multiplexed imaging and machine learning to investigate the coupling of cell shape and protein expression in heterogeneous human tissues. Our analysis establishes a universal, bi-directional link between a cell's shape and its protein expression across cell types, diseases, and disease states, amplified for cell state markers. Machine learning interpretability shows that shape features can potentially generate hypotheses of protein functions. Screening all protein-cell type pairs identified a subpopulation of large, p53-positive tumor cells across two cancers. Shape properties further enhanced graph neural network disease state prediction. Our results open the door to unraveling the intricate connections between protein expression, cell shape, tissue organization, and tissue state in a physiological context.
23 July 2026
Read appraisal →BMJ open
Endoscopic biopsy strategies for gastric ulcers: an updated systematic review
OBJECTIVE: To systematically summarise recent evidence on endoscopic biopsy for gastric ulcer. DESIGN: Systematic review of clinical studies. DATA SOURCES: PubMed, Embase, Cochrane Library, Web of Science, CNKI and CiNii Research were searched for studies published from 2015 to May 2025. ELIGIBILITY CRITERIA: Original studies involving adults with endoscopically diagnosed gastric ulcers or ulcerative gastric lesions directly informing biopsy strategy were eligible if they evaluated biopsy timing, number, site or related diagnostic outcomes. DATA EXTRACTION AND SYNTHESIS: Two reviewers independently screened studies, extracted data and assessed risk of bias using the Newcastle-Ottawa Scale. Owing to substantial clinical and methodological heterogeneity, findings were synthesised narratively. RESULTS: Seven studies were included and grouped into four domains: biopsy timing, biopsy number, biopsy site and safety. Available data suggested that most malignancies may be identifiable at the initial endoscopy examination although repeat biopsy during ulcer healing or scarring might still detect some missed cancers. Evidence on the biopsy site remained limited and inconsistent, and findings from healed-phase ulcers further suggested that the anatomical site alone may be insufficient to guide biopsy strategy. Available studies also indicated that four well-targeted biopsies may be adequate for some depressed or polypoid lesions whereas more extensive sampling might be needed for infiltrative or otherwise suspicious lesions. Limited safety data did not show a clear increase in adverse events with broader biopsy strategies or the biopsy of stabilised bleeding ulcers. CONCLUSIONS: Contemporary evidence on endoscopic biopsy for gastric ulcers remains limited, heterogeneous and largely observational. Available data suggest that biopsy at initial endoscopy and adequate, lesion-targeted sampling may improve diagnostic yield, while follow-up and intensive sampling should be individualised according to endoscopic appearance, histological findings and clinical suspicion. PROSPERO REGISTRATION NUMBER: CRD420251157851.
21 July 2026
Read appraisal →Metabolomics : Official journal of the Metabolomic Society
Clinical lipidomics in bacterial sepsis: a systematic review of serum and plasma evaluations
BACKGROUND: Lipid metabolism plays a central role in host-pathogen interactions and immune regulation during bacterial sepsis, with its dysregulation contributing to organ failure and mortality. Blood-based lipidomics has emerged as a promising approach for identifying diagnostic and prognostic biomarkers in sepsis. However, discrepancies in lipid profiles between serum and plasma remain a major challenge for clinical translation. This systematic review synthesizes lipidomic evidence from serum and plasma in bacterial sepsis patients to identify reproducible lipid biomarkers, evaluate methodological heterogeneity and assess associations with clinical outcomes. METHODS: A systematic search of five databases (Scopus, Pubmed, Ovid MEDLINE, Web of Science and Google Scholar) identified nine eligible studies published between 2016 and 2025 that applied untargeted or targeted lipidomics on human serum and plasma samples from adult bacterial sepsis patients (PROSPERO: CRD420251086177). RESULTS: Across both matrices, reproducible candidate lipid biomarkers included triacylglycerols (TAG), phosphatidylcholines (PC), lysophosphatidylcholines (LPC), sphingomyelins (SM) and ceramides. Synthesized findings revealed characteristically distinct directional trajectories: consistent elevation of TAG, bidirectional shifts of PC, depletion of LPC, bidirectional shifts of SM and elevation of SM. Preliminary trend within the literature indicates that serum-based studies more frequently captured prognostic alterations, whereas plasma-based studies often focused on diagnostic discrimination. Substantial heterogeneity was observed in sample handling, lipid extraction protocols and analytical platforms. CONCLUSIONS: Overall, both matrices offer valuable clinical insights, though these apparent differences in diagnostic or prognostic utility may reflect primary study designs rather than intrinsic matrix superiorities. Methodological heterogeneity limits reproducibility, highlighting the need for standardized workflows to enable translation of sepsis lipid biomarkers.
9 July 2026
Read appraisal →IEEE transactions on pattern analysis and machine intelligence
A Survey on Interpretability in Visual Recognition
Visual recognition models have achieved unprecedented success in various tasks. While researchers aim to understand the underlying mechanisms of these models, the growing demand for deployment in safety-critical areas like autonomous driving and medical diagnostics has accelerated the development of eXplainable AI (XAI). Distinct from generic XAI, visual recognition XAI is positioned at the intersection of vision and language, which represent the two most fundamental human modalities and form the cornerstones of multimodal intelligence. This paper provides a systematic survey of XAI in visual recognition by establishing a multi-dimensional taxonomy from a human-centered perspective based on intent, object, presentation, and methodology. Beyond categorization, we summarize critical evaluation desiderata and metrics, conducting an extensive qualitative assessment across different categories and demonstrating quantitative benchmarks within specific dimensions. Furthermore, we explore the interpretability of Multimodal Large Language Models and practical applications, identifying emerging trends and opportunities. By synthesizing these diverse perspectives, this survey provides an insightful roadmap to inspire future research on the interpretability of visual recognition models.
1 July 2026
Read appraisal →ACS sensors
Artificial Raman Expert: Autonomous Spectroscopic Reasoning Driven by Localized Large Language Models
Analytical sciences increasingly require autonomous systems capable of real-time heuristic reasoning and dynamic parameter adaptation. However, current automated laboratory platforms remain largely restricted to rigid synthesis workflows. Here, we introduce the Artificial Raman Expert (ARE), an autonomous AI-driven analytical framework powered by localized, open-source large language models (LLMs) to ensure strict data privacy and reproducibility. By integrating a structured knowledge base (A-Knowhow), ARE internalizes the tacit decision-making logic of seasoned spectroscopists. To ensure safe and scalable deployment, ARE's cognitive and optical reasoning was first validated within a risk-free virtual reality (VR) sandbox before being successfully translated to a physical Raman spectrometer. Across highly complex physicochemical scenarios, ARE demonstrated advanced cognitive capabilities: evaluating the spatial heterogeneity of pharmaceutical samples, performing spectral unmixing to isolate trace narcotics from severe forensic matrix interferences within just 3 analytical cycles, heuristically halting analyses after 8-10 iterations-despite human prompts mandating >30 positions-thereby reducing analytical time and resource consumption by ∼70%. Additionally, ARE conducted constraint-aware parameter tuning, dynamically capping laser exposure at 60 s to optimize signal-to-noise ratios while strictly preventing biological cell phototoxicity. By actively optimizing analytical resources and adapting to noisy data, ARE demonstrates the feasibility of context-aware autonomous spectroscopy. This work provides a foundational proof-of-concept for encoding tacit analytical expertise into AI-driven instrumentation, with potential for broader application across diverse analytical domains.
28 June 2026
Read appraisal →Genome biology
MLMarker: a machine learning framework for tissue inference and biomarker discovery
MLMarker is a machine learning tool that computes continuous tissue similarity scores for proteomics data, addressing the challenge of interpreting complex or sparse datasets. Trained on 34 healthy tissues, its Random Forest model generates probabilistic predictions with SHAP-based protein-level explanations. A penalty factor corrects for missing proteins, improving robustness for low-coverage samples. Across three public datasets, MLMarker revealed brain-like signatures in cerebral melanoma metastases, achieved high accuracy in a pan-cancer cohort, and identified brain and pituitary origins in biofluids. MLMarker provides an interpretable framework for tissue inference and hypothesis generation, available as a Python package and Streamlit app.
26 June 2026
Read appraisal →Cancer causes & control : CCC
HPV in breast cancer: prevalence and comparison with healthy tissue-a systematic review and meta-analysis
INTRODUCTION: Breast cancer (BC) is the most common cancer among women worldwide, with over 2.3 million new cases annually. Recent studies suggest that Human Papillomavirus (HPV), a known oncogenic virus, may be involved in BC development. This study investigates HPV prevalence in BC samples and its potential role in tumorigenesis. METHODS: Random-effects meta-analyses were conducted to estimate raw proportions and odds ratio (OR), with 95% confidence intervals (CIs). Heterogeneity was assessed using I2. Statistical significance was set at p < 0.05. Analyses were performed in R 4.5.0 RESULTS: Our meta-analysis encompassed 82 studies and evaluated 7,683 breast cancer (BC) tissue samples to assess the presence of HPV. The overall prevalence of HPV in BC specimens was estimated at 23% (95%CI: 19%-28%). When stratified by continent, Oceania exhibited the highest regional prevalence at 38%. Comparative analysis between BC tissues and healthy controls revealed a significantly increased likelihood of HPV detection in the cancer group (OR 5.06; P < 0.001). This association remained statistically robust in both case-control (OR 6.34; P < 0.001) and cross-sectional designs (OR 2.83; P < 0.001). Among continents, South America demonstrated the most pronounced association (OR 11.66; P = 0.005). Subgroup analysis based on economic classification indicated that countries with low-income settings had the highest HPV prevalence (34%; 95%CI: 9%-73%). Evaluation by BC subtype revealed that luminal B had the highest HPV-positive rate (44%; 95%CI: 27%-61%). CONCLUSION: This meta-analysis reveals a global presence of HPV in BC and suggests a possible link. Further well-designed studies are needed to confirm its role in tumorigenesis.
26 June 2026
Read appraisal →Acta dermato-venereologica
Recurrent Cutaneous Eosinophilic Vasculitis: A Systematic Review of Clinicopathologic Features and Treatment Outcomes
Recurrent cutaneous eosinophilic vasculitis is a rare, predominantly cutaneous vasculitis described mainly in isolated reports. We aimed to systematically synthesize published evidence on its clinico-pathological features, treatment and outcomes. We reviewed case reports and case series of recurrent cutaneous eosinophilic vasculitis and related entities identified in PubMed, Scopus and reference lists (last searched 16 February 2026), using structured report and case-level extraction, duplicate handling, Joanna Briggs Institute critical appraisal and descriptive synthesis. Twenty reports comprising 24 unique cases were included. Most patients presented with relapsing pruritic purpura of the lower extremities. Peripheral eosinophilia was frequent, antineutrophil cytoplasmic antibodies were negative in all reported cases and histopathology consistently showed eosinophil-rich vasculitis, usually with fibrinoid and/or necrotizing change. Systemic corticosteroids often induced improvement, but relapse during tapering or after withdrawal was common. The evidence was limited by small, heterogeneous reports and incomplete follow-up. Overall, the findings support a recognizable cutaneous-predominant, relapse-prone pattern, highlight the importance of assessing extracutaneous involvement in differential diagnosis and support provisional refinement of the previously proposed diagnostic framework.
26 June 2026
Read appraisal →Croatian medical journal
Artificial intelligence in pathology: a framework for preserving brain capital in the diagnostic apex
AIM: To present a five-criterion calibration framework for evaluating artificial intelligence (AI) tools in pathology centered on preserving "brain capital" - the finite cognitive resources available to clinicians - and stabilizing the "diagnostic apex," the point where histological evidence meets clinical judgment. METHODS: Using cognitive load theory (CLT) and implementation science, we developed the Pathology AI Diagnostic Balance - a conceptual model mapping the physician-specimen interaction within working memory and IT infrastructure constraints - and examined it in the context of peer-reviewed case studies of implemented pathology AI tools. RESULTS: The framework identifies five criteria: Contextual Literacy (integration of clinical history), Responsibility (preservation of signing authority), Evidence Gap Analysis (closure of diagnostic uncertainty), Verification (feasibility of quality control), and Opportunity Cost (return on cognitive investment). Successful tools, such as Ki-67 quantification and breast cancer screening, reduce cognitive burden by automating routine tasks or enabling rapid verification. Conversely, tools requiring an exhaustive re-review or producing opaque recommendations deplete cognitive bandwidth, causing decision fatigue and diagnostic errors. CONCLUSION: Pathologists are positioned to exercise evaluative authority over tools that increase extraneous cognitive load. Clinical expertise represents pathologists' most distinctive contribution to AI development: defining which failure modes matter clinically, what context an AI must integrate, and whether a tool serves patient care. By prioritizing cognitive sustainability over purely technical metrics, the profession can ensure AI functions as a genuine enhancement of diagnostic capability rather than an additional burden on diagnostic workflows.
15 June 2026
Read appraisal →Croatian medical journal
Artificial intelligence enables scale, consistency, and rigor in forensic identity inference.
Advances in forensic genomics, which include massively parallel sequencing, dense single nucleotide polymorphism testing, and forensic genetic genealogy (FGG), have greatly expanded the range of cases in which DNA evidence can generate investigative leads. As a result, the primary limitations in modern forensic DNA analysis are no longer analytical sensitivity or marker availability, but the ability to reason consistently, transparently, and at scale over increasingly complex genetic, genealogical, and contextual information. Current forensic workflows remain predominantly human-centered, relying on manual reasoning that is difficult to standardize, reproduce, document, or scale across growing case inventories. The potential of artificial intelligence (AI) is described as an enabling layer for forensic identity inference, defined here as computational decision-support systems that structure, prioritize, and document reasoning over genetic associations, genealogical structures, and investigative context during identity hypothesis development. While formal statistical inference quantifies evidentiary weight, identity inference governs how evidence is explored, combined, and acted upon during investigations. AI-assisted systems can augment, but not replace, expert judgment by supporting scalable prioritization, relational reasoning, and systematic documentation of analytical decisions, while reducing bias. Properly designed AI-enabled systems offer a path to sustainably scaling FGG while supporting scientific rigor, accountability, and public trust.
15 June 2026
Read appraisal →Journal of global health
Plasma proteomic signatures predict incident benign prostatic hyperplasia: a prospective cohort study of 20 996 men
BACKGROUND: Benign prostatic hyperplasia (BPH) is a prevalent disease in elderly men. However, the plasma proteomic signatures for incident BPH are absent, hindering early prediction and risk stratification. We aimed to identify plasma proteins associated with incident BPH and the implicated biological pathways. METHODS: This prospective cohort was constructed based on the UK Biobank, enrolling 20 996 BPH-free males at baseline. We used the Olink Explore platform to determine the abundances of 2920 plasma proteins. We used Cox regression models to evaluate associations and the Extreme Gradient Boosting model to perform feature selection and predictive modelling. We performed pathway enrichment and Mendelian randomisation analyses to elucidate the molecular pathways involved and assess causality. RESULTS: During the median follow-up period of 13.38 years, 2405 incident BPH cases were recorded. Cox regression identified 92 plasma proteins significantly associated with BPH risk (false discovery rate <0.05). Extreme Gradient Boosting model prioritised a three-protein signature: TSPAN1 (hazard ratio (HR) = 1.24) and KLK3 (HR = 1.34) as risk factors, and EDA2R (HR = 0.83) as a protective factor. This three-protein panel achieved an AUC of 0.71 (95% confidence interval = 0.69-0.73) for predicting BPH onset. Enrichment analysis revealed the associated proteins were mainly involved in immune-inflammatory pathways and stromal remodelling. As revealed by Mendelian randomisation, TSPAN1 and KLK3 were causally associated with incident BPH. CONCLUSIONS: We identified a three-protein panel (TSPAN1, KLK3, EDA2R) which can predict incident BPH. The findings highlight potential targets for non-invasive risk assessment and therapy.
15 June 2026
Read appraisal →Journal of ovarian research
Deep learning-based prediction of gene expression from histopathology identifies NR5A1 as a candidate biomarker and druggable target in high-grade serous ovarian carcinoma
BACKGROUND: High-grade serous ovarian cancer (HGSOC) is the most lethal ovarian cancer subtype, responsible for ~ 70% of ovarian cancer-related deaths and marked by late-stage diagnosis and frequent platinum resistance. Although transcriptomic profiling enables molecular stratification and prediction of therapeutic response; routine clinical use of this approach is limited by cost and logistical constraints. Computational pathology analysis offers a scalable alternative by inferring transcriptional states directly from routine hematoxylin and eosin (H&E) whole-slide images (WSIs). METHODS: Paired H&E WSIs and RNA-sequencing data from the TCGA-OV cohort, including 1,371 diagnostic H&E WSIs retrieved for preprocessing and quality control, were used to develop a self-supervised virtual-transcriptomics framework based on Momentum Contrast v2 (MoCo v2) and multi-output Random Forest regression. Model performance was assessed using patient-level five-fold cross-validation. Candidate genes were evaluated by reverse transcription quantitative polymerase chain reaction (RT-qPCR) in an independent cohort of 10 HGSOC tumors, including 4 platinum responders and 6 non-responders. RESULTS: The model predicted expression of approximately 6,400 protein-coding genes, achieving a genome-wide mean Pearson correlation of r = 0.36, with more than 300 genes showing stronger image-expression coupling (r > 0.44). RT-qPCR analysis of 18 candidate genes revealed substantial inter-patient heterogeneity. NR5A1 exhibited the highest expression variability (coefficient of variation [CV] = 1.486) and significantly higher expression in platinum-responsive tumors than in non-responders (mean 2⁻ΔCt = 0.263 vs. 0.013; p < 0.05). Exploratory in silico docking and molecular dynamics (MD) analyses suggested structurally stable binding interactions between Steroidogenic Factor-1 (SF-1/NR5A1) and the natural plant compound cubebin. CONCLUSION: This study demonstrates that histological architecture contains measurable transcriptomic information that can support scalable biomarker prioritization from routine diagnostic histology in HGSOC. NR5A1 represents a hypothesis-generating candidate biomarker and structurally tractable target for future experimental studies. Future validation in larger, multi-center cohorts will be essential to confirm model robustness, biological relevance, and potential clinical utility.
14 June 2026
Read appraisal →Placenta
Recent advances in multimodal approaches for investigating placental development and related diseases
The placenta is a vital organ that supports fetal growth and pregnancy maintenance. Its dysfunction is associated with severe complications, including preeclampsia, fetal growth restriction, and placenta accreta spectrum disorders. Traditional approaches to placental research have provided valuable insights but are limited in capturing the complexity of this dynamic organ. In recent years, multimodal approaches-integrating advanced imaging, single-cell and spatial omics, and artificial intelligence (AI)-have enabled comprehensive analyses of placental development and disease. These strategies offer improved diagnostic accuracy, deeper molecular understanding, and real-time assessment of placental function. This review summarizes recent advances in multimodal placental research, highlighting key technologies such as ultrasound and MRI, single-cell transcriptomics, spatial profiling, and AI-based prediction models. Particular emphasis is placed on contributions from Chinese research teams, who have developed novel platforms, atlases, and clinically relevant tools. We also discuss ongoing challenges, including data standardization, interpretability of AI models, and ethical considerations. Looking ahead, the integration of multimodal data with AI and wearable technologies holds promise for precision obstetrics and individualized pregnancy care. Together, these innovations are advancing both scientific understanding and clinical management of placenta-related disorders.
12 June 2026
Read appraisal →Developmental cell
A machine learning-based megakaryocyte identification system uncovers resident organs, markers, and functional diversity
The organ- and stage-specific diversity of megakaryocytes (MKs) has prompted a reassessment of their distribution and functions. By integrating single-cell transcriptomic data across multiple organs and developmental stages, we identified previously unreported MK and platelet markers, including Tnik, a key regulator of MK function and platelet production. Using these markers alongside established ones, we developed a machine learning-based MK identification system (MKIDS) that enables MK detection in the brain, heart, and placenta in mice and humans. Functional studies demonstrated that brain-resident MKs are essential for neural development, underscoring organ-specific roles of MKs in regulating tissue development and function. Transcriptomic integration of MKs across organs and stages, with functional validation, revealed a developmental shift in platelet production-from a mitochondria-low to a mitochondria-enriched subpopulation. Our findings offer a transformative perspective on the MK system, highlighting its cellular diversity, functional complexity, and developmental dynamics.
12 June 2026
Read appraisal →European respiratory review : an official journal of the European Respiratory Society
Artificial intelligence-enabled histological analysis in pre-clinical respiratory disease models: a scoping review
Histological analysis is a cornerstone of pre-clinical respiratory disease research. It enables assessment of pathology, therapeutic effects, and mechanisms. However, conventional approaches rely on manual scoring, which is subjective, time-consuming, and difficult to scale. Artificial intelligence (AI), particularly deep learning, offers potential to automate histology workflows. To date, its use in pre-clinical respiratory models has not been synthesised.We conducted a scoping review following the Joanna Briggs Institute guidelines. We searched MEDLINE and Embase (inception - January 2025) for pre-clinical studies using AI to analyse histology in respiratory disease models. Screening, full-text review, and data extraction were performed in duplicate.Of 6271 studies screened, 29 met inclusion criteria. Most used murine models (76%) and investigated lung cancer (28%), pulmonary fibrosis (24%), or tuberculosis (17%). Haematoxylin and eosin was the most common stain (48%), with others targeting collagen or immune markers. AI tasks included image classification (n=20), segmentation (n=10), and object detection (n=4), predominantly using convolutional neural networks (69%). Pre-processing methods (e.g. stain normalisation) were common, but annotation and training practices were inconsistently reported. AI model performance was generally high (accuracy ≥90%; seven studies); however, validation metrics varied, and external validation was absent. Most studies used "black box" models, with minimal application of explainability techniques. Reproducibility measures, such as sharing datasets or code were rarely reported.AI tools are poised to transform histological analysis in pre-clinical respiratory research. The field will be able to further harness AI to automate pre-clinical respiratory histological analysis by addressing gaps that we have identified in validation, transparency, and standardisation.
12 June 2026
Read appraisal →Journal of clinical oncology : official journal of the American Society of Clinical Oncology
Neoadjuvant Taxane Plus Trastuzumab and Pertuzumab With or Without Carboplatin in Human Epidermal Growth Factor Receptor 2-Positive Breast Cancer: The Randomized Noninferiority Phase III neoCARHP Trial
PURPOSE: The neoCARHP aimed to investigate the efficacy and safety of investigator-selected taxane (docetaxel, paclitaxel, or nab-paclitaxel) plus trastuzumab and pertuzumab, with carboplatin (TCbHP) or without carboplatin (THP), in stage II and III human epidermal growth factor receptor 2 (HER2)-positive breast cancer. METHODS: The neoCARHP was a multicenter, randomized, phase III, noninferiority study. Eligible patients were women age 18 years or older with previously untreated, stage II and III, HER2-positive invasive breast cancer. Patients were randomly assigned (1:1) to receive six 3-week cycles of TCbHP or THP. The primary end point was pathologic complete response (pCR) rate in the breast and axilla (ypT0/is ypN0) in the modified intention-to-treat (mITT) population (all randomly assigned patients receiving at least one dose of study treatment). Safety was evaluated in all patients who received any study treatment. RESULTS: Between April 30, 2021, and August 27, 2024, 774 patients were randomly assigned and 766 were included in the mITT population (382 in THP and 384 in TCbHP). pCR was achieved in 245 (64.1% [95% CI, 59.1 to 69.0]) patients in the THP group and 253 (65.9% [60.9-70.6]) in the TCbHP group (absolute difference, -1.8% [95% CI, -8.5 to 5.0]; odds ratio, 0.93 [95% CI, 0.69 to 1.25]; Pnoninferiority = .0089). The THP group had fewer grade 3 and 4 adverse events (20.7% v 34.6%) and serious adverse events (1.3% v 4.7%) than the TCbHP group. The most common grade 3 and 4 adverse events with THP were neutropenia (6.8% v 16.4% with TCbHP), leukopenia (5.5% v 14.8%), and diarrhea (2.6% v 4.2%). No treatment-associated deaths occurred. CONCLUSION: THP provided noninferior pCR rates and improved tolerability compared with TCbHP. Omitting carboplatin may be applicable in HER2-positive breast cancer.
12 June 2026
Read appraisal →Journal of clinical oncology : official journal of the American Society of Clinical Oncology
Durvalumab in Combination With Neoadjuvant Chemotherapy in Early Triple-Negative Breast Cancer: Long-Term Analysis From the GeparNuevo Trial
The phase II GeparNuevo trial investigated whether adding durvalumab to neoadjuvant chemotherapy (NACT) only in patients with early triple-negative breast cancer cT1b-cT4a-d would improve pathologic complete response (pCR) rate and patient survival. Hundred and seventy-four patients were randomly assigned to receive durvalumab or placebo concurrently with nab-paclitaxel once per week and followed by dose-dense epirubicin and cyclophosphamide. With 86.4 months of median follow-up compared with the previously reported 43.7 months, durvalumab showed sustained significant improvements in long-term outcomes as defined by STEEP compared with placebo regarding not only invasive disease-free survival (iDFS; hazard ratio [HR], 0.56 [95% CI, 0.32 to 0.99]; stratified log-rank P = .0431), but also distant disease-free survival (DDFS; HR, 0.41 [95% CI, 0.21 to 0.80]; P = .0069) and overall survival (OS; HR, 0.33 [95% CI, 0.14 to 0.79]; P = .0085). All analyses were stratified by stromal tumor-infiltrating lymphocytes (sTILs) at baseline (low [≤10%], intermediate [11%-59%], high [≥60%]). In exploratory subgroup analysis, patients with nodal involvement at baseline demonstrated a greater iDFS benefit (HR, 0.33 [95% CI, 0.144 to 0.771]; P = .01; Pinteraction = 0.045). sTILs in residual disease (RD) could be assessed in 39/71 patients without pCR. Post hoc analyses by sTILs high (>10%) versus low (≤10%) in RD showed estimated 7-year iDFS rates of 92.3% (95% CI, 56.6 to 98.9) and 51.4% (95% CI, 29.2 to 69.7), respectively. Hence, adding durvalumab to dose-dense NACT without adjuvant continuation of checkpoint inhibition improved long-term survival outcomes, irrespective of the extent of pathologic response. This underscores the necessity to re-evaluate the adjuvant continuation of checkpoint inhibition.
11 June 2026
Read appraisal →Biochemical and biophysical research communications
Efferocytosis-related biomarkers and immune infiltration in pancreatic ductal adenocarcinoma based on single-cell sequencing and machine learning: a comprehensive bioinformatics analysis and experimental validation
BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is a highly invasive and lethal malignancy, with its complex tumor microenvironment (TME) severely limiting therapeutic efficacy. Efferocytosis, a key process by which macrophages clear apoptotic cells, has been demonstrated to influence tumor initiation and progression by modulating immune responses, promoting M2 polarization, and facilitating immune evasion. Yet, the function and predictive significance of genes linked to efferocytosis in PDAC are still not fully understood. METHODS: This study integrated TCGA-PDAC, GTEx, and GEO datasets with single-cell transcriptomics to screen and analyze expression patterns and functions of efferocytosis-related genes (ERGs) in PDAC. Differential analysis, single-cell clustering, cell communication, and pseudo-time analysis revealed heterogeneity in macrophage efferocytosis. Subsequently, a six-gene prognostic model (CD36, ITGAV, PANX1, PPARG, S100A4, THBS1) was constructed and validated using Cox and LASSO regression. Concurrently, GSEA pathway analysis, immune infiltration assessment, and immunotherapy response prediction were conducted. Key gene functions were validated through molecular docking, RT-qPCR, western blotting, and functional experiments. RESULTS: Single-cell analysis revealed that macrophages exhibit the highest efferocytic activity within the PDAC microenvironment, demonstrating significant subpopulation heterogeneity. Differential analysis identified 23 key intersecting genes, ultimately yielding a risk model comprising six core genes. The model exhibited strong predictive accuracy in both the training and validation groups (notable AUC). Additional examination showed that patients at high risk showed a heightened presence of pathways linked to the reprogramming of energy metabolism and inflammatory reactions, along with heightened genomic instability and immunosuppressive TME traits, suggesting a grim prognosis. Experimental validation confirmed that knockdown of THBS1 significantly inhibited the proliferation, migration, and invasion of PDAC cells. CONCLUSION: The research clarifies the diverse nature of macrophage efferocytosis in PDAC and its crucial function in the restructuring of TME. It establishes and validates a six-gene risk prediction model, clarifying the functional significance of core genes, including THBS1. These findings provide novel molecular tools for PDAC prognosis assessment and identify potential targets for immunotherapy and personalized treatment strategies.
11 June 2026
Read appraisal →Gene
Based on WGCNA and machine learning studies, SMURF2 drives NSCLC malignant transformation, ferroptosis, and macrophage polarization by ubiquitinating SPP1
BACKGROUND: Non-small cell lung cancer (NSCLC) is a common type of lung cancer with poor prognosis and high mortality in advanced stages. Although secreted phosphoprotein 1 (SPP1) is associated with the progression of NSCLC, its specific mechanisms remain to be explored. METHODS: Through integrated bioinformatics analysis combining weighted gene co-expression network analysis (WGCNA), differential expression analysis, gene enrichment analysis with the Kyoto Encyclopedia of Genes and Genomes (KEGG)/Gene Ontology (GO), and machine learning techniques incorporating database predictions, core genes were identified. Experimental validation was conducted using Western blot, co-immunoprecipitation (Co-IP), cycloheximide (CHX) chase assay, Ubiquitin Immunoprecipitation (Ub-IP), colony formation, flow cytometry, transwell assay, reactive oxygen species (ROS) detection, and quantitative real-time PCR (qRT-PCR). The functional impact of SPP1 on tumor growth was further confirmed through mouse models and immunohistochemistry (IHC). RESULTS: Based on WGCNA and machine learning, SPP1 was identified as a core gene. SMURF2 ubiquitinated and degraded SPP1. Rescue experiments confirmed that SMURF2 inhibited proliferation and invasion, and promoted apoptosis in NSCLC cells, which were reversed by SPP1 overexpression. Furthermore, SMURF2 enhanced ferroptosis and modulated macrophage polarization via the same ubiquitination mechanism. Animal studies verified that SMURF2-mediated ubiquitination and degradation of SPP1 suppressed tumor growth. CONCLUSION: This study aims to investigate the role of SMURF2-mediated ubiquitination of SPP1 in inhibiting malignant progression, promoting ferroptosis, and modulating macrophage polarization in NSCLC, thereby providing a theoretical foundation and new insights for understanding and targeting NSCLC.
10 June 2026
Read appraisal →Blood advances
Ropeginterferon alfa-2b for prefibrotic myelofibrosis and lower-risk myelofibrosis requiring cytoreduction
There is currently no consensus on the optimal treatment of early myelofibrosis (MF). Ropeginterferon alfa-2b (ropeg) is a next-generation monopegylated interferon alfa-2b developed specifically to treat myeloproliferative neoplasms. We conducted a phase 2 study in patients with prefibrotic primary MF (pre-PMF) and Dynamic International Prognostic Scoring System low-/intermediate-1-risk fibrotic PMF or secondary MF (SMF) who required cytoreduction. Ongoing treatment with hydroxyurea was substituted with ropeg (week 0, 250 μg; week 2, 350 μg; week 4 onward, 500 μg every 2 weeks). The primary end points were safety and clinicohematologic complete response (CHCR). Seventy-one patients (40 men and 31 women) with a median age of 60 years (range, 31-86) were enrolled and followed up for a median of 119 weeks (range, 10-131). At weeks 24, 48, and 104, CHCR was achieved in 63.8% (pre-PMF, 74%; fibrotic PMF, 20%; fibrotic SMF, 42.9%), 63.5% (pre-PMF, 69.6%; fibrotic PMF, 25%; SMF, 53.9%), and 70% of patients (pre-PMF, 78.4%; fibrotic PMF, 33.3%; SMF, 50%), respectively. Thrombo-hemorrhagic events were not observed after stopping hydroxyurea. At weeks 24, 48, and 104, reduction in JAK2V617F variant allele frequency (VAF) was observed in 53.1%, 70%, and 67.6% of patients, and reduction in CALR mutant VAF was observed in 52.6%, 42.9%, and 40% of patients, respectively. In 50 evaluable cases at week 104, 13 patients (26%) had reduced bone marrow reticulin fibrosis. There were 3 treatment discontinuations (4.2%) due to adverse events. In conclusion, ropeg was safe and induced CHCR associated with significant molecular responses in patients with early MF. This trial was registered at www.clinicaltrials.gov as NCT04988815.
9 June 2026
Read appraisal →Journal of proteome research
AI-Based Digital Pathology-Enabled Spatial-Omics Data Analyses of the Human Kidney
Identification of tissue-region-specific changes in glycosylation is crucial for understanding the pathogenesis of kidney diseases, yet it remains a great challenge. We developed a workflow that combines matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) data with AI-based digital pathology annotations of kidney functional tissue units (FTUs) to profile N-glycan distributions within biopsy tissues. This approach can generate molecular-level data relevant to diverse pathological outcomes, thereby aiding in the elucidation of disease mechanisms. As a proof-of-concept, we demonstrate that this AI-based digital pathology approach to MALDI data segmentation enables the detection and differentiation of N-glycosylation within FTUs of healthy kidney tissue. We then elucidated differences in N-glycosylation between the diseased kidney tissue samples from patients with different diagnoses. Sialic acid N-glycans, which have been linked to various kidney diseases, displayed enrichment in the glomeruli and tubules of tissues from patients diagnosed with diabetic kidney disease (DKD), whereas they were enriched in the tubules and arteries from patients with acute kidney injury (AKI), in comparison to healthy tissue. Furthermore, we found that polylactosamine N-glycans were enriched only in the AKI samples, indicating their potential roles in tubular injury and inflammation. This workflow has the potential to bridge the gap between region-specific glycosylation and its implications on FTUs in diseases, paving the way for targeted molecular imaging studies in the kidney and other tissues.
7 June 2026
Read appraisal →Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy
Benchmarking spectroscopic-chemometric models for human bloodstain time since deposition in tropical outdoor microenvironments
Reliable estimation of the time since deposition (TSD) of bloodstains remains a key challenge in forensic reconstruction, particularly under realistic outdoor conditions. This study benchmarks visible (Vis) reflectance, attenuated total reflectance-Fourier transform infrared (ATR-FTIR) and micro-Raman spectroscopy, each coupled with partial least squares (PLS) regression and artificial neural networks (ANN), for TSD estimation of human bloodstains aged up to 100 days under naturally fluctuating tropical outdoor microenvironments. Blood from multiple donors was deposited on glass slides and aged under two conditions: open-air exposure and enclosed storage in sealed plastic bags. Spectra were acquired from the outer ring of each stain, preprocessed by standard normal variate transformation and partitioned by donor into training and independent test sets. Vis reflectance primarily tracked haemoglobin chromophore changes via Soret and α/β bands, whereas ATR-FTIR highlighted protein secondary structure and hydration through amide I-III and O-H/N-H stretching features. Micro-Raman spectra emphasised porphyrin breathing and CC stretching modes, together with aromatic amino-acid and amide bands that remained informative even at late ageing stages. Across all techniques, PLS models provided robust quantitative performance (R2P up to 0.98, RMSEP typically ∼5-10 days, RPD > 3), with micro-Raman-PLS giving the highest predictive accuracy and enclosed exposure consistently improving model stability relative to open air. ANN models did not provide systematic advantages over PLS and were more sensitive to condition-specific variance. In the context of previous outdoor ATR-FTIR studies, these results show that established Vis-, ATR-FTIR- and Raman-based chemometric models can deliver competitive TSD estimates when calibrated within clearly defined environmental domains, underscoring the importance of donor-independent and environmental-aware validation for forensic interpretation.
7 June 2026
Read appraisal →Journal of theoretical biology
Subtypes estimation in single-cell multi-omics data via S-multi-SNE
Single-cell RNA sequencing (scRNA-seq) has rapidly become an essential method in modern biology, as it allows global characterisation of transcriptomics in individual cells from different tissues, or organisms. scRNA-seq data are collected from a single individual organism and they are composed as mRNA count matrices with rows representing the cells and columns the genes. New technologies further allow multi-omics data to be obtained on the same set of single cells. In this paper, multi-SNE and S-multi-SNE, two multi-view dimensionality reduction approaches, are adapted for visualization and classification of cellular subtypes, two important challenges in the analysis of scRNA-seq data. S-multi-SNE has been adapted for cell subtype estimation of scRNA-seq data. In a series of experiments we illustrate that it is possible to identify cell subtypes by leveraging information from individuals from the same species, from different species, and when data are generated by different sequencing technologies. In the conducted analyses, we show that S-multi-SNE consistently outperformed several other machine learning techniques and, in most comparisons, surpassed existing reference-based single-cell classification algorithms. We further illustrate how two single-cell multi-omics datasets, scATAC-seq and scRNA-seq, can be integrated together through S-multi-SNE for improved cell subtype identification.
7 June 2026
Read appraisal →Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy
Multivariate feature analysis of early-stage laryngeal cancer serum components using surface-enhanced Raman spectroscopy
Laryngeal cancer is a common head-and-neck malignant tumor with geographically variable incidence. Its lack of specific early clinical symptoms often causes missed diagnosis, leading to most cases being identified at intermediate/advanced stages and thus poor treatment efficacy and prognosis. Early, accurate screening for high-risk populations is therefore critical to improving survival. This study systematically investigates the clinical application value of surface-enhanced Raman spectroscopy (SERS) combined with deep learning models for serum screening in early laryngeal cancer. It specifically examines the discriminative performance of one-dimensional convolutional neural network (1D-CNN) models, including CNN-attention with a fused attention mechanism and CNN-baseline without an attention mechanism, and compares these with traditional machine learning models.Serum samples were collected from three groups: Early laryngeal cancer, vocal fold polyps, and healthy controls. SERS was used to obtain serum molecular vibration fingerprint spectra. After spectral preprocessing, five models (CNN-attention, CNN-baseline, SVM, AdaBoost, KNN) were established to discriminate the three groups and compare performance. Leave-one-patient-out cross-validation (LOPO-CV) results indicate that the CNN-attention and CNN-baseline models significantly outperform other models in discrimination efficacy. Specifically, the CNN-attention model achieves a patient-level accuracy of 89.33%, while the CNN-baseline model reaches 88.67%. SVM, KNN, and AdaBoost had inferior performance. This study confirms that serum SERS-based 1D-CNN provides an efficient, accurate method for early laryngeal cancer screening, laying a foundation for clinical translation and offering new technical support for early screening.
7 June 2026
Read appraisal →Medicine
Associations of TyG-related indices with NAFLD-related outcomes: A systematic review and meta-analysis
BACKGROUND: The triglyceride-glucose (TyG) index and related composite indices have been increasingly studied as accessible metabolic markers for fatty liver disease. However, evidence remains difficult to interpret because different TyG-related indices have been evaluated across heterogeneous populations and nonalcoholic fatty liver disease (NAFLD)-related outcomes. We conducted a systematic review and meta-analysis to clarify the pooled associations that could be formally synthesized and to summarize the broader descriptive evidence. METHODS: We systematically searched PubMed, Embase, the Cochrane Library, China National Knowledge Infrastructure, Wanfang Data, VIP Database, and China Biology Medicine Database from inception to December 2025. Observational studies evaluating the TyG index or related composite indices, including TyG-body mass index, TyG-waist circumference, and TyG-waist-to-height ratio, in relation to NAFLD-related outcomes were eligible. Random-effects meta-analyses were performed in R. Only studies with sufficient comparability in exposure operationalization, outcome definition, and effect-size reporting were quantitatively pooled; the remaining studies were retained in the descriptive synthesis. RESULTS: Nineteen studies involving 212,618 participants were included in the systematic review, including 16 cross-sectional studies and 3 cohort studies. Of these, 8 studies contributed to at least 1 quantitative synthesis. In continuous-scale analyses, higher TyG levels were associated with increased odds of NAFLD/steatosis (5 studies; pooled odds ratio [OR], 2.72; 95% confidence interval [CI], 2.08-3.55; I2 = 85.7%). In highest-versus-lowest analyses, the association remained significant (4 studies; pooled OR, 4.36; 95% CI, 3.39-5.61; I2 = 92.8%). TyG-body mass index (2 studies; pooled OR, 1.04; 95% CI, 1.03-1.05; I2 = 0.0%) and TyG-waist circumference (2 studies; pooled OR, 1.01; 95% CI, 1.01-1.01; I2 = 15.1%) were also positively associated with NAFLD/steatosis. TyG-waist-to-height ratio showed a positive association in supportive synthesis, but evidence for liver fibrosis and nonalcoholic steatohepatitis remained limited and was mainly descriptive. CONCLUSION: TyG-related indices were consistently associated with NAFLD/steatosis across the available literature. The basic TyG index had the broadest evidence base, whereas composite indices suggested possible additional value in selected settings. These markers may be useful for metabolic fatty liver risk stratification, but further studies with standardized outcome definitions and clearer exposure parameterization are needed.
31 May 2026
Read appraisal →Journal of neuro-oncology
Intramedullary or invasive characteristics of spinal melanocytomas: a PRISMA compliant systematic review and pooled case analysis
PURPOSE: Primary meningeal melanocytomas (MMs) of the spinal cord are rare lesions. Even rarer are intramedullary and invasive variants. These intramedullary lesions may exhibit more aggressive behavior than their "benign" classification appreciates. The role of adjuvant radiotherapy (aRT) in this context remains uncertain. METHODS: This study is a PRISMA-compliant systematic review with a pooled-case analysis, including two recent institutional cases included as illustrative examples. RESULTS: Sixty-three reports were identified of primary intramedullary or invasive MMs. Among 56 patients with available recurrence data, 8 of 30 patients (26.7%) experienced recurrence after gross-total resection (GTR) and in 8 of 22 (36.4%) after near-total or subtotal resection (NTR/STR), with no significant difference between groups (two-sided Fisher's exact, P = 0.548). No recurrence was observed among three patients who received aRT upfront post GTR, compared with 8 of 27 (29.6%) who did not receive radiation (two-sided Fisher's exact, P = 0.545); however, this subgroup was markedly underpowered and should be interpreted as hypothesis-generating only. Nine patients developed metastatic disease or progression, including one post biopsy. Of the eight who underwent resection at index surgery, 2 (25%) had undergone GTR and 6 (75%) STR. CONCLUSIONS: These findings suggest that the designation of MMs as benign lesions may underestimate the oncologic potential of intramedullary or invasive disease. Consideration of aRT on an individualized basis for patients with intramedullary or invasive disease is reasonable, regardless of extent of resection.
30 May 2026
Read appraisal →Journal of the Egyptian National Cancer Institute
Artificial intelligence in cancer immunotherapy: current trends in predicting response and personalizing treatment
Artificial intelligence (AI) can transform cancer immunotherapy by enabling more accurate prediction of treatment responses, the discovery of specific biomarkers, and the development of personalised treatment plans. Traditional single-marker biomarkers (PD-L1, TMB, MSI) lack consistency across tumour types and cannot be used to assess tumour heterogeneity or the dynamic tumour microenvironment (TME). This review synthesises developments in multimodal AI models that combine genomics, transcriptomics, radiomics, digital pathology (pathomics), circulating biomarkers, and clinical evidence to create composite predictive signatures with significantly better discriminatory value. AUCs over 0.8 have been seen in a few retrospective studies with deep learning and ensemble models on whole-slide images, CT/MRI/PET radiomics, spatial and single-cell omics, and multi-omics fusion models, but prospective and multicentre validation is scarce, and external validation often shows deterioration in performance. AI is also used to enhance the translational pipelines of adoptive cell therapies (e.g., CAR-T) by improving patient selection, manufacturing (e.g., digital twins), and early toxicity prediction (e.g., CRS, ICANS). Nevertheless, clinical implementation remains hindered by data heterogeneity, bias, poor longitudinal validation, limited reproducibility, and a lack of transparency in most models, even though prospective, multicenter validation and explainable AI are crucial for clinician trust and regulatory acceptance. New systems such as federated learning, foundation models, spatial omics, digital twins, and wearable monitoring represent paths to generalizable, privacy-preserving, and actionable systems in clinical practice. To achieve the potential of AI, the generation of data will need to be standardized, reporting must be transparent, interdisciplinary, and regulatory frameworks must be strengthened focusing on the practical use of AI and patient safety. By taking these steps, AI could be shifted to prospective clinical decision support, which uses AI to meaningfully enhance personalization and outcomes in cancer immunotherapy based on a retrospective research tool.
30 May 2026
Read appraisal →American Society of Clinical Oncology educational book. American Society of Clinical Oncology. Annual Meeting
Artificial Intelligence in Oncology: Clinical Applications, Challenges, and Opportunities
Artificial intelligence (AI) is reshaping cancer research and clinical oncology by enabling large-scale analysis of complex biomedical data. Although early AI efforts focused on single-modality tasks such as imaging interpretation or pathology classification, contemporary oncology increasingly requires integrated reasoning across heterogeneous inputs, including imaging, digital pathology, and genomics. Multimodal artificial intelligence (MMAI) models represent a major evolution by fusing these data types into unified predictive systems capable of informing diagnosis, risk stratification, treatment selection, and disease monitoring. This manuscript reviews the state of AI in oncology and highlights emerging foundation models within the field. There will be a focus on histopathology, and how this can be incorporated into risk assessment models. There will also be examples of MMAI utility in radiology and spatial proteomics. Additionally, we will discuss ethical and legal implications of MMAI in modern oncology, and recommendations for responsible application within clinical oncology practice.
30 May 2026
Read appraisal →The New England journal of medicine
Zanidatamab with and without Tislelizumab in HER2-Positive Gastroesophageal Cancer
BACKGROUND: Zanidatamab, a dual human epidermal growth factor receptor 2 (HER2)-targeted bispecific antibody, plus chemotherapy both with and without tislelizumab (anti-programmed death 1), showed encouraging efficacy and safety as first-line therapy in phase 2 studies involving patients with HER2-positive gastroesophageal adenocarcinoma. METHODS: In an open-label, phase 3 trial, we randomly assigned, in a 1:1:1 ratio, patients with previously untreated, centrally confirmed HER2-positive advanced gastroesophageal adenocarcinoma to receive zanidatamab and tislelizumab plus chemotherapy, zanidatamab plus chemotherapy, or trastuzumab plus chemotherapy. The two primary end points were progression-free survival and overall survival. RESULTS: At a median follow-up of 25.9 months, progression-free survival was longer with zanidatamab-tislelizumab-chemotherapy (median among 302 patients, 12.4 months) and zanidatamab-chemotherapy (median among 304 patients, 12.4 months) than with trastuzumab-chemotherapy (median among 308 patients, 8.1 months) (hazard ratio for progression or death with zanidatamab-tislelizumab-chemotherapy, 0.63 [95% confidence interval {CI}, 0.51 to 0.78]; hazard ratio with zanidatamab-chemotherapy, 0.65 [95% CI, 0.52 to 0.81]; P<0.001 for both comparisons). Overall survival was longer with zanidatamab-tislelizumab-chemotherapy than with trastuzumab-chemotherapy (median, 26.4 vs. 19.2 months; hazard ratio for death, 0.72; 95% CI, 0.57 to 0.90; P = 0.004). At this interim analysis, overall survival did not differ significantly between zanidatamab-chemotherapy (median, 24.4 months) and trastuzumab-chemotherapy (hazard ratio, 0.80; 95% CI, 0.64 to 1.01; P = 0.06). The incidence of grade 3 or higher adverse events was 83.3% with zanidatamab-tislelizumab-chemotherapy, 73.8% with zanidatamab-chemotherapy, and 74.5% with trastuzumab-chemotherapy; diarrhea was the most common such event, in 24.8%, 20.0%, and 12.9% of patients, respectively. CONCLUSIONS: Zanidatamab plus chemotherapy, both with and without tislelizumab, led to longer progression-free survival than trastuzumab plus chemotherapy among patients with HER2-positive advanced gastroesophageal adenocarcinoma. At this interim analysis, overall survival was longer with zanidatamab-tislelizumab-chemotherapy than with trastuzumab-chemotherapy; further analyses are planned to assess zanidatamab-chemotherapy. Diarrhea was a common adverse event. (Funded by Jazz Pharmaceuticals and others; HERIZON-GEA-01 ClinicalTrials.gov number, NCT05152147.).
29 May 2026
Read appraisal →Autoimmunity
IgA Vasculitis with necrotizing arteritis: a multicenter retrospective study from the French Vasculitis Study Group and systematic review of the literature
IgA vasculitis (IgAV) primarily affects small vessels, but rare cases with necrotizing arteritis (NA) raise questions about overlap with polyarteritis nodosa (PAN). To characterize IgAV with necrotizing arteritis (IgAV-NA) and compare its phenotype with classical IgAV and PAN. We performed a multicenter retrospective study combined with a systematic literature review (1990-2025). Patients fulfilled EULAR/PRINTO/PRES IgAV criteria, had pathological or imaging evidence of NA in small or medium arteries, and were ANCA-negative. Thirty patients were included (7 from databases, 23 from the literature). NA was confirmed by biopsy (n = 16) or vascular imaging (n = 14). Clinical features, treatments, remission, and mortality were compared with 257 adult IgAV and 196 PAN patients. Median age was 54.5 years. IgAV-NA was characterized by severe manifestations, including gastrointestinal bleeding, perforation, surgical abdomen, neuropathy, pancreatitis, and livedo. Compared with classical IgAV, IgAV-NA showed significantly higher rates of multi-organ involvement and mortality. Compared with PAN, IgAV-NA shared vascular complications but had less fever and neuropathy. Despite arterial involvement, patients did not fulfil PAN criteria. IgAV-NA represents a rare, severe IgAV phenotype with life-threatening complications rather than an IgAV-PAN overlap. Severe or atypical IgAV presentations should prompt vascular imaging and intensified immunosuppression.
28 May 2026
Read appraisal →Journal of the American College of Cardiology
Combining Genomics With Lipid and Inflammatory Biomarkers to Predict Coronary Artery Disease Risk: UK Biobank Study
BACKGROUND: Coronary artery disease (CAD) polygenic risk score (PRS), low-density-lipoprotein cholesterol (LDL-C), lipoprotein(a) (Lp(a)), and high-sensitivity C-reactive protein (hsCRP) are biomarkers that predict CAD. It is unclear whether integrating genomics with lipid and inflammatory biomarkers could complement traditional risk scores in identifying people at risk of CAD. OBJECTIVES: This study assesses the predictive value of CAD PRS, LDL-C, Lp(a), and hsCRP for incident CAD across different age and sex groups. METHODS: Participants (n = 215,695) from the UK Biobank aged 40 to 69 years with baseline CAD PRS, LDL-C, Lp(a), and hsCRP values were followed for 12 years to assess the incidence of CAD. We evaluated a multivariable-adjusted Cox model that included all 4 biomarkers, net reclassification index, C-statistics, and population attributable risk across different age and sex groups. RESULTS: Over a 12-year follow-up, 4,721 men and 2,425 women developed CAD. The HRs for incident CAD associated with each biomarker elevation were 1.79 (95% CI: 1.70-1.89) for CAD PRS, 1.60 (95% CI: 1.48-1.66) for LDL-C, 1.20 (95% CI: 1.12-1.29) for Lp(a), and 1.64 (95% CI: 1.57-1.72) for hsCRP. CAD PRS demonstrated a stronger association in men (HR per SD: 1.49; 95% CI: 1.45-1.54) than women (HR per SD: 1.37; 95% CI: 1.31-1.44; P-interaction ≤ 0.001). All biomarkers conferred greater HRs at younger ages (P < 0.0001). Individuals with all biomarkers elevated had a 4.65-fold increased risk of CAD compared with those with no elevated biomarkers. A combined 4-biomarker model had a higher C-statistic of 0.753 compared with the pooled cohort equations (C-statistic of 0.740). The C-statistic of the combined 4-biomarker model was also higher in younger individuals in both sexes and yielded a 32.0% continuous net reclassification index when compared with the pooled cohort equations. CONCLUSIONS: CAD PRS, LDL-C, hsCRP, and Lp(a) show independent age- and sex-specific associations with CAD. Measuring all 4 biomarkers may improve midlife CAD risk prediction for both male and female patients.
28 May 2026
Read appraisal →The journal of maternal-fetal & neonatal medicine : the official journal of the European Association of Perinatal Medicine, the Federation of Asia and Oceania Perinatal Societies, the International Society of Perinatal Obstetricians
Integrated cell-free DNA and omics genetic scores for early detection of gestational diabetes: evidence from a nationwide multicenter study
BACKGROUND: Gestational diabetes mellitus (GDM) affects 15.6% of pregnancies globally, with Vietnam exhibiting one of the highest prevalences at 21%. Current diagnostic approaches at 24-28 weeks limit early intervention opportunities. We developed a multi-modal machine learning framework integrating cell-free DNA (cfDNA) structural features and genetic information for early GDM prediction at 10-12 weeks of gestation in Vietnamese women. METHODS: We analyzed blood samples from 1,086 pregnant women (435 GDM cases, 651 controls) collected at 9-12 weeks. Two parallel analytical pathways were employed: cfDNA profiling extracting cfDNA-specific features (fragment length, end motifs, GC content, nucleosome patterns), and whole-genome imputation generating predictions for ∼19,000 omics traits. Component scores were developed using TabPFN classifier and integrated via logistic regression into a unified master score. RESULTS: Genome-wide analysis identified five omics traits with significant GDM associations: HSD11B1, NEK7, COMMD10, KLRC4, and OCEL1. Component score optimization revealed distinct patterns-cfDNA scores peaked at 200 features (AUC = 71.53), while genetics-based scores improved with up to 2,000 omics traits (AUC = 77.21). The final master score, integrating three components (gbSC2000, gbSCBH, cfSC200), achieved AUCs of 86.82-87.19 across validation cohorts with 70% sensitivity and 89% specificity. Addition-deletion analysis confirmed that both cfDNA and genetic components provided essential, non-redundant contributions. CONCLUSIONS: This multi-modal framework demonstrates superior performance compared to single-biomarker approaches, enabling risk stratification from very low (4% GDM prevalence) to very high risk (90% prevalence). At the cutoff 0.4, the model identifies 78% of future GDM cases at 10-12 weeks while maintaining an 18% false-positive rate, potentially enabling early interventions to prevent GDM development and associated complications.
27 May 2026
Read appraisal →Analytical chemistry
Human-to-Rat Validation of PMI Biomarkers: A Bidirectional Cross-Species Metabolomics Study Reveals Asymmetric Translation
Accurately estimating the post-mortem interval (PMI, also known as time since death) remains a major challenge in forensic science due to substantial biological and environmental variability in human cases. While animal models provide controlled conditions for identifying PMI-related metabolic changes, their translational value for human forensics is unclear. This study bridges controlled rat metabolomics with real-world human autopsy samples using LC-MS-based metabolomics and machine learning. We analyzed femoral blood from 435 medico-legal autopsies (PMI 1-10 days) and employed two complementary modeling strategies. An untargeted Lasso model using all 3450 detected features achieved R2 = 0.51 and identified 51 consistently selected PMI-informative molecular features. To assess cross-species robustness, we reanalysed rat samples using the same analytical platform. Eighteen of the 51 human-derived features were detected in rats, showing clear PMI-dependent trends and strong correlations with PMI. Two metabolites achieved level 2 annotation and matched known PMI biomarkers from previous animal studies, demonstrating meaningful human-to-rat biochemical overlap. In contrast, a targeted Lasso model based on biomarkers identified in rats performed poorly in humans (R2 = 0.10), underscoring limited direct rat-to-human translation. Overall, human-derived biomarkers validated robustly in the controlled rat model proved far more reliable. These findings highlight both the potential and limitations of cross-species PMI biomarker discovery and emphasize the need for improved metadata, especially temperature history, to advance PMI modeling in forensic practice.
27 May 2026
Read appraisal →Journal of neuro-oncology
Clinical utility of liquid biopsy in distinguishing true progression from radiation necrosis and pseudoprogression in malignant brain tumor.
BACKGROUND: Distinguishing true tumor progression from pseudoprogression (PsP) and radiation necrosis (RN) following radiotherapy or radiosurgery for intracranial tumors remains a significant clinical challenge. Conventional imaging modalities, including MRI and PET, often lack sufficient diagnostic accuracy, while histopathological confirmation, although definitive, is invasive and not always feasible. Liquid biopsy (LB) has emerged as a promising noninvasive diagnostic approach. METHODS: A systematic review was conducted across PubMed, Embase, Scopus, and Cochrane databases. A total of 964 records were identified, including PubMed (n = 322), Embase (n = 280), Scopus (n = 297), and Cochrane (n = 65), along with three clinical trials identified from trial registers. After removal of 157 duplicates using Covidence, 807 studies were screened by title and abstract. Of these, 749 were excluded, and 58 articles underwent full-text review. Ultimately, 11 studies met the inclusion criteria and were included in the analysis. RESULTS: A diverse range of LB-based biomarkers has been investigated, including immune cell-based markers (e.g., HLA-DRneg/low and VNN2+ CD14+ monocytic myeloid-derived suppressor cells), immune-related proteins (e.g., CXCL11 and MUC-16), circulating tumor cells, cell-free DNA, mitochondrial DNA, B1-SINE elements, microvesicles, and RNA analytes. Plasma was the most used biofluid, with limited evaluation of urine and cerebrospinal fluid. Analytical techniques varied widely, including flow cytometry, PCR-based assays, immunostaining-FISH, and multiplex protein platforms. Several biomarkers showed statistically significant differences among RN, PsP, and tumor recurrence; however, these findings were largely derived from small, heterogeneous cohorts with inconsistent reporting of diagnostic performance metrics. Composite indices, such as the DR-VNN2 index (DVI) and the Necrosis Prediction Index (NPI), showed potential for improving diagnostic differentiation. CONCLUSIONS: LB-based biomarkers show promise for differentiating RN and PsP from tumor recurrence; however, current evidence is limited by small sample sizes, methodological heterogeneity, and lack of standardized diagnostic criteria. Larger prospective studies and validation of composite biomarker models are required to establish their clinical utility. CLINICAL TRIAL NUMBER: Not Applicable.
26 May 2026
Read appraisal →Renal failure
Complication rates of 16- and 18-gauge needles for native kidney biopsies: a systematic review and proportional meta-analysis
This systematic review and meta-analysis evaluated complication rates and diagnostic yield reported in studies of adult native kidney biopsy using 16-gauge (16 G) or 18-gauge (18 G) needles. We included randomized trials and cohort studies of real-time ultrasound-guided biopsies, including case series. MEDLINE, Embase, and CENTRAL were searched through October 2024. Two reviewers independently performed study selection, data extraction, and risk of bias assessment using Joanna Briggs Institute tools. Random-effects meta-analyses estimated pooled proportions with 95% confidence intervals (CI), and univariable random-effects meta-regression explored study-level associations with major complications, transfusion, or gross hematuria. We screened 4,499 titles and abstracts and reviewed 319 full-text articles; 62 studies comprising 68 biopsy series were included. The pooled major complication rate in studies using 16 G needles was 1.83% (95% CI: 1.20-2.79) and 1.29% (95% CI: 0.78-2.13) in studies using 18 G needles, with no statistically significant difference. Mean glomerular yield was 18.8 with 16 G and 17.5 with 18 G needles. In study-level meta-regression, studies with higher prevalence of acute kidney injury, lower mean estimated glomerular filtration rate, or lower mean hemoglobin reported higher pooled complication rates. Most studies were single-arm cohorts; between-needle differences therefore reflect indirect study-level contrasts. Interpretation is limited by retrospective design and heterogeneity across studies. Overall, studies using both needle sizes reported low complication rates and similar diagnostic yield, although definitions and reporting varied. Direct comparative studies are needed to determine whether meaningful differences exist. What was knownKidney biopsy is essential for diagnosing many medical kidney diseases and guiding treatment, requiring adequate tissue samples for subsequent analyses.Modern biopsy techniques use spring-loaded, ultrasound-guided devices with smaller gauge needles, but optimal needle size remains uncertain.While 14G needles are associated with higher complication risk, evidence on whether 16G or 18G needles differ in safety or diagnostic yield is conflicting.This study addsIn this systematic review and meta-analysis of 62 studies involving 22,208 adult native kidney biopsies, we found no statistically significant difference in major complication rates between studies using 16G and 18G needles.In study-level meta-regression analyses, studies with a higher prevalence of acute kidney injury, lower mean estimated glomerular filtration rate, and lower mean hemoglobin reported higher pooled major complication rates.Potential impactStudies using both 16G and 18G needles reported similarly low major complication rates, although comparisons are based on indirect evidence with substantial heterogeneity.Findings support the ethical feasibility and clinical relevance of a large, randomized controlled trial to definitively guide needle size selection in native kidney biopsies.
26 May 2026
Read appraisal →Head and neck pathology
Digital Pathology in Head and Neck Squamous Cell Carcinoma: Translational Advances and Clinical Integration for Pathologists, Oncologists, and Surgeons
PURPOSE: Artificial intelligence (AI)-enabled digital pathology has advanced rapidly in head and neck squamous cell carcinoma (HNSCC), but its readiness for clinical implementation remains uncertain. This review evaluates the translational maturity of AI-based digital pathology applications in HNSCC and their proximity to routine clinical use. METHODS: A structured literature search of PubMed and Scopus identified studies published between January 2020 and March 2026. Studies were included if they applied AI or machine learning to histopathologic or whole-slide images in HNSCC or related oral malignancies and reported diagnostic, prognostic, biomarker, or treatment-response outcomes. Given the narrative scope of this review, representative studies aligned with key clinical domains were selected for qualitative synthesis. A six-stage translational maturity framework was used to categorize applications based on development stage, validation, and clinical integration. RESULTS: Of 444 identified records, 358 unique studies were screened, from which representative HNSCC-specific AI digital pathology studies were selected for detailed analysis. Most applications-including diagnostic classification, dysplasia grading, prognostic modeling, and therapy-response prediction-remain at early translational stages (Stage 0-1), typically limited to retrospective, single-center cohorts with minimal external validation. Biomarker quantification and HPV prediction show relatively greater maturity, with some studies approaching Stage 2, reflecting external validation and early prospective evaluation. However, calibration, decision-curve analysis, and outcome-linked endpoints are rarely reported. No HNSCC-specific AI pathology tools have demonstrated outcome-linked deployment or achieved regulatory-grade implementation, and evidence for workflow integration, clinical decision impact, and patient-centered outcomes remains limited. CONCLUSION: AI-enabled digital pathology in HNSCC remains an early-stage field. Despite promising technical performance, most applications lack the prospective validation, workflow integration, and outcome-based evidence required for clinical adoption. Progress will depend on multi-institutional prospective studies, standardized reporting of clinical utility, and demonstration that AI-assisted decisions improve patient management and outcomes.
26 May 2026
Read appraisal →Neurosurgical review
The role of preoperative thrombocytic factors on survival in patients with glioblastoma: a meta-analysis and synopsis of the literature
Glioblastoma (GBM) is the most common malignant primary brain tumour and is associated with poor prognosis. Platelet-related factors have been linked to outcomes in GBM, but evidence remains inconsistent. This review evaluates their prognostic value for survival. We conducted a systematic review and meta-analysis of studies on preoperative thrombocytic factors in GBM. PubMed, MEDLINE, and Embase were searched from inception to January 2025 using MeSH terms. Eligible studies included observational cohort studies of adults (≥ 16 years) with WHO grade 4 diffuse astrocytoma (GBM), ≥ 30 participants, and ≥ 3 months' follow-up after resection. Random-effects meta-analysis using restricted maximum likelihood with Hartung-Knapp adjustment was used to pool hazard ratios (HRs) of high vs. low parameters on overall survival (OS). Study quality was assessed with the Newcastle-Ottawa Scale. 21 studies were included. 13 (n = 2609) reported HRs of high vs. low platelet: lymphocyte ratio (PLR, median threshold = 150), with high PLR significantly associated with worse OS (pooled HR = 1.46, 95% CI [1.23, 1.74]). Eight studies (n = 1921) assessed platelet count (PC, median threshold = 208*109/L), showing high PC was a borderline predictor of worse OS (pooled HR = 1.38, 95% CI [1.00, 1.90]). Four studies (n = 1234) examined mean platelet volume (MPV, median cut-off = 9.05 fL), which qualitatively demonstrated worse OS in patients with high MPV or high MPV: PC ratio. One study assessed platelet distribution width (PDW, threshold = 14.7 fL), finding worse OS in the high PDW group. High preoperative PLR is associated with poor prognosis in GBM, while high PC demonstrates borderline increased risk, which may help refine risk stratification and guide future mechanistic studies.
25 May 2026
Read appraisal →Computer assisted surgery (Abingdon, England)
An automatic detection model for spread through air spaces in postoperative pathological sections based on deep learning in NSCLC
Spread through air spaces (STAS) is recognized as an aggressive pattern of invasion in lung cancer and has been associated with poorer survival outcomes. However, STAS is frequently overlooked or misdiagnosed during routine pathological diagnosis. We analyzed 129 pathological slides from 91 STAS-positive patients with non-small cell lung cancer (NSCLC). An artificial intelligence framework consisting of a tumor region segmentation algorithm and an object detection algorithm was developed. The segmentation algorithm was first used to isolate the main tumor region, followed by STAS detection using an improved object detection model. The segmentation module achieved a Jaccard similarity of 0.846. The proposed object detection algorithm demonstrated superior performance with a precision of 0.738, recall of 0.747 and average precision (AP) of 0.784 and F1 score of 0.742, outperforming other object detection methods. Both segmentation and detection results met diagnostic requirements, with higher accuracy observed in lung adenocarcinoma (LUAD) than in lung squamous cell carcinoma (LUSC). In external validation, the model achieved a precision of 0.670, recall of 0.705 and AP of 0.732 and F1 score of 0.687. Additionally, the AI-derived STAS counts showed substantial agreement with pathologists (interclass correlation coefficient = 0.703). Kaplan-Meier survival analysis revealed that the number of STAS events was significantly associated with disease-free survival (DFS) in stage I LUAD (p < .05). We propose a deep learning-based artificial intelligence framework for automated STAS detection and quantification in digital whole-slide images of NSCLC. This model holds promising potential to assist pathologists in achieving more comprehensive and accurate diagnosis of STAS.
25 May 2026
Read appraisal →Medicine
Survival prediction of colorectal cancer using 101 machine learning methods based on immune-related genes: A machine learning study
Colorectal cancer (CRC) is characterized by high incidence and mortality rates. Early identification of high-risk CRC patients and timely intervention are crucial for reducing mortality rates. This study aims to develop a prognostic model incorporating immune-related genes using 101 machine learning algorithms. We utilized data from 630 CRC patients in The Cancer Genome Atlas Program database and the Gene Expression Omnibus database as a validation set. We identified immune-related genes from the ImmPort repository and conducted differential gene expression analysis. We developed 101 machine learning models, including random survival forest, elastic net, LASSO, Ridge regression, stepwise Cox, Coxboost, partial least squares regression for Cox, supervised principal component analysis, generalized boosted modeling, and survival support vector machines. The model with the highest mean concordance index was selected as the optimal prognostic model. The Ridge regression model demonstrated the most robust performance with a mean concordance index of 0.67. Patients with higher immune-related gene risk score (IRGRS) had significantly lower survival rates (log-rank test, P < .001). Univariate and multivariate Cox regression analyses confirmed IRGRS as an independent prognostic factor. Nomograms successfully predicted overall survival at 1, 2, and 3 years. IRGRS correlated with immune cell infiltration levels and stromal activity in the tumor microenvironment. High IRGRS scores were associated with higher tumor immune dysfunction and exclusion scores, suggesting potential differences in response to immune checkpoint inhibitors. In addition, high IRGRS patients exhibited greater sensitivity to certain chemotherapy drugs. The IRGRS score is a potent predictor of survival in CRC patients. This study offers a new perspective for CRC prognosis and supports the development of personalized treatment strategies.
24 May 2026
Read appraisal →ACS sensors
Urine-Based Noninvasive Detection of Prostate Cancer Using Human Olfactory Receptor-Embedded Nanodiscs
The diagnosis of prostate cancer (PCa) is limited by the low specificity of prostate-specific antigen (PSA) testing, which contributes to overdiagnosis and patient exposure to unnecessary invasive prostate biopsies. Here, we report a urine-based diagnostic platform that combines a six-member human olfactory receptor-embedded nanodisc (OR-ND) sensor array with fluorescence sensing and machine learning to detect PCa-associated volatile organic compounds (VOCs). Six ORs were reconstituted into lipid nanodiscs and evaluated using urine samples from a strictly curated subcohort of 40 PCa patients and 33 healthy controls (n = 73) to establish baseline sensor responsiveness. Subsequently, to ensure diagnostic robustness, machine learning classifiers were developed and cross-validated using an expanded data set of 290 samples, achieving an accuracy of 0.890 and an AUC of 0.964. Analysis of the full receptor data set revealed distinct response patterns, and statistical screening with correlation filtering identified OR2W1, OR51E1, and OR51E2 as the most informative features. Using these selected receptors, a random forest classifier achieved an accuracy of 0.890 and an AUC of 0.964, demonstrating high sensitivity and specificity. OR response patterns showed a closer association with Gleason score than with serum PSA levels, indicating that urinary VOC signatures capture tumor-related metabolic information complementary to conventional biomarkers. These results demonstrate that an OR-ND sensor array coupled with machine learning enables accurate and noninvasive detection and classification of PCa from urine samples. Our study provides a modular framework extensible to other VOC-associated diseases.
23 May 2026
Read appraisal →Analytica chimica acta
Optimized HSSE-GC-MS and machine learning for forensic gender classification of human scent from clothing
BACKGROUND: Clothes are considered a valuable piece of evidence in forensic investigations because of the underlying information that can be extracted from them. Human scent is one kind of trace evidence that can be extracted from clothes, which can link a specific person or location to the crime. This study optimized a headspace sorptive extraction (HSSE) method coupled with gas chromatography-mass spectrometry in combination with machine learning for objective discrimination of gender from human scent traces on clothing for forensic applications. RESULTS: The HSSE was optimized using the Box-Behnken design and Response Surface Methodology to maximize the Euclidean distance between the total ion sum spectrum (TIS) of two independent samples. The optimized extraction parameters were determined at 100 °C extraction temperature, 180 min extraction time, and 5 × 5 cm cloth dimension at m/z range 101 - 250 which produced an R2 of 0.9874. Method validation demonstrated an acceptable absolute error of 6.60%. Intra- and inter-day precisions were calculated for each m/z from 101 to 250 to remove outliers from the dataset for the multivariate analysis. Using the optimized extraction method, 62 samples were analyzed and the pre-processed TIS from the samples were subjected to various supervised machine learning algorithms. Support vector machine (SVM) and partial least squares-discriminant analysis (PLS-DA) models achieved perfect 100% accuracy for gender classification in both training and test sets. Random forest (RF) and linear discriminant analysis (LDA) also showed high test set accuracies of 93% and 86%, respectively. SIGNIFICANCE: This integrated approach, combining optimized stir bar HSSE-GC-MS with different machine learning algorithms using the TIS untargeted approach, provides a fast and automatic gender classification from human scent traces on clothes that can be used as a rapid screening technique in forensic investigations to narrow down suspect or victim profiles.
22 May 2026
Read appraisal →Journal of medical Internet research
Benchmarking Large Language Models and Prompt Engineering Strategies in Microsatellite Instability Cancers: Evaluation Study
BACKGROUND: The reliability of general-purpose large language models (LLMs) for complex clinical tasks in specialized domains such as microsatellite instability (MSI) cancers remains critically uncharacterized. The absence of a domain-specific benchmark to evaluate and guide the optimization of their capabilities across diverse clinical tasks poses unevaluated risks to patient safety. OBJECTIVE: This study aimed to develop and validate Microsatellite Instability Cancer Benchmark (MSIC-Bench), a novel, two-tiered benchmark for MSI cancer, covering both consensus and frontier knowledge. Using this framework, we aimed to systematically assess LLM performance across various prompting strategies, identify task-specific weaknesses, and reveal effective pathways for performance improvement. METHODS: We developed MSIC-Bench, a 511-question benchmark derived from clinical guidelines and a curated knowledge base. Three state-of-the-art LLMs (GPT-4o, [OpenAI], Gemini 2.5 Pro [Google], and Claude Opus 4 [Anthropic]) were evaluated using 4 prompting strategies, including vanilla, chain-of-thought, reflection of thoughts, and retrieval-augmented generation (RAG), under both multiple-choice and open-ended modalities. Performance was assessed on accuracy, safety (honesty), error composition, and token usage. RESULTS: LLMs demonstrated a significant "scaffolding effect," with accuracy dropping substantially in open-ended scenarios. For non-RAG strategies, the primary failure mode was an internal knowledge deficit. The integration of RAG proved to be the most effective intervention. A domain-aligned RAG strategy not only significantly improved accuracy in complex decision-making tasks but also fundamentally shifted the system's primary bottleneck from knowledge deficits to retrieval failures. In terms of safety, RAG induced a favorable shift from high-risk fabrications to safer refusals, though this introduced a safety-utility trade-off in the form of false refusals. Notably, our hybrid-RAG configuration, which combined both knowledge sources, demonstrated the most robust and generalizable performance across all tasks. CONCLUSIONS: Current LLMs lack the specialized knowledge required for reliable application in MSI oncology. A well-designed RAG architecture is the pivotal intervention to address this gap. However, its success is not automatic; it transforms the nature of system failure, making retrieval precision and knowledge base quality the new critical determinants of performance and safety. Our findings establish a clear directive for developing trustworthy clinical artificial intelligence: focus must shift toward optimizing the retrieval component and curating high-quality, comprehensive knowledge sources. MSIC-Bench provides a robust framework to guide these future efforts.
22 May 2026
Read appraisal →mSystems
Insects shape the cadaver decomposition microbiome and postmortem interval estimation accuracy
The breakdown and recycling of carrion is a crucial ecological process that largely relies on a community of necrophagous insects and microbes. Recent work has shown that a specialized microbial network, likely dispersed throughout the environment by insects, assembles during cadaver decomposition to break down flesh regardless of climate and geography. Because of their broad distribution and successional nature, decomposer microbes have been used in machine learning models to predict the postmortem interval (PMI) of human remains, an important contribution to the field of forensics. How factors such as an indoor environment, which alters insect activity, impact the composition of microbial communities decomposing human remains is unclear. Here, we investigate the effects of enclosed shelter on microbial community assembly and successional patterns during human decomposition and provide important considerations for PMI modeling. Compared to outdoor cadavers, we show that indoor cadavers experienced delayed colonization of key decomposer microbes over the course of decomposition due to restricted insect access. Consequently, machine learning models trained on outdoor cadavers frequently underestimated the PMI of cadavers decomposing indoors. Delayed colonization by blow fly maggots (Diptera: Calliphoridae) was correlated with higher PMI prediction errors, suggesting that insects are an important source of microbial decomposers that drive PMI model predictions. Incorporating microbial data from indoor cadavers and insect activity into PMI models significantly improved prediction capabilities for both indoor and outdoor decomposition environments. Ultimately, we demonstrate the important role insects play in the maintenance and distribution of microbes that help to recycle vertebrate remains.IMPORTANCEMicrobes are critical for the decomposition and recycling of organic matter. Recently, microbiome-based models have shown promising performance in estimating the postmortem interval (PMI). However, many deaths occur indoors, yet no studies have investigated the impact of enclosed shelter on the cadaver microbiome in a controlled setting. Here, cadavers were decomposed indoors, and we found that blow fly maggots serve as an important source of decomposer taxa that significantly alter the cadaver microbiome following infestation. Notably, PMI estimation models trained on outdoor data sets failed to accurately predict the PMI when insect colonization was delayed. We show that incorporating 16S rRNA amplicon data from cadavers decomposing indoors, along with environmental variables, significantly improves PMI estimates, suggesting a microbiome-based forensic tool may be feasible across decomposition environments. Importantly, this research demonstrates the critical ecological role insects play in the dispersal of specialized microbes that are involved in the breakdown and recycling of vertebrate remains.
22 May 2026
Read appraisal →Cell systems
Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease states
Single-cell RNA sequencing (scRNA-seq) is a prominent tool for studying human disease biology. The availability of massive scRNA-seq datasets and advanced machine learning has driven the development of single-cell foundation models that provide versatile cell representations based on expression. To understand disease states, we need to account for entire tissue ecosystems, simultaneously considering many different interacting cells. Here, we tackle this challenge by generating patient-level representations derived from multi-cellular expression contexts measured with scRNA-seq of tissues. We develop PaSCient, a machine learning model that employs a multi-level representation learning paradigm and provides importance scores at the cell and gene levels for fine-grained analysis of disease characteristics. We apply PaSCient to a large-scale scRNA-seq atlas of 12.5 million cells from over 2,700 patients. Comprehensive benchmarking demonstrates the superiority of PaSCient in disease classification and multiple downstream applications, including dimensionality reduction, feature prioritization, and patient subgroup discovery.
22 May 2026
Read appraisal →Oral health & preventive dentistry
Screening for Periodontitis Using Blood Biomarkers and Demographic Data: A Machine Learning Study
PURPOSE: Periodontitis is a common chronic disease associated with systemic conditions such as diabetes and cardiovascular disease. Diagnosis typically relies on dental examinations and radiographs, which may be underutilised by individuals who avoid, delay, or lack dental care. This study evaluated the potential of routine blood biomarkers and demographic data for screening moderate-to-severe periodontitis. METHODS AND MATERIALS: Data were obtained from the National Health and Nutrition Examination Survey (NHANES) 2011-2012 adults aged ≥ 30 years (N = 3,338). Periodontal status was classified using CDC/AAP definitions. An XGBoost classifier was trained on 77 features spanning demographics, complete blood count, glycemic and hemo-globin markers, heavy metals, and additional biochemical assays. Model performance was assessed with Accuracy, Precision, Recall, and F1 score. SHapley Additive exPlanations (SHAP) were used for interpretability. Subgroup analyses were conducted by age and gender. RESULTS: The model achieved 61.1% Accuracy, 57.4% Precision, 94.6% Recall, and an F1 score of 71.5%. Performance was higher in males (F1 = 78.2) than in females (F1 = 63.9%). SHAP identified age, gender, blood cadmium, blood lead, and glycohaemoglobin (HbA1c) as top predictors. CONCLUSION: Routine blood biomarkers and demographics can be leveraged for non-dental screening of periodontitis, offering a feasible preventive strategy in primary care. The model achieved high recall, minimising false negatives, and identified biologically plausible predictors. This approach may help flag at-risk individuals, particularly in underserved populations, and support integration of oral health into general medical care.
21 May 2026
Read appraisal →Journal of clinical pathology
AI triage of duodenal biopsies improves workflow
AIMS: To develop, deploy and evaluate artificial intelligence (AI) for triaging duodenal biopsies within a National Health Service (NHS) histopathology laboratory, with the aim of improving reporting turnaround times for clinically significant diagnoses. METHODS: The pathway was developed in the UK in an NHS laboratory. Rule-based automation software was used to find all newly scanned duodenal biopsy slides. Those with case numbers ending in an odd number were exported for AI triage and if they had significant AI predicted abnormalities they were prioritised for reporting. The cases with even numbers followed the routine reporting pathway. RESULTS: 313 cases (517 duodenal slides) were processed by the routine pathway, and 329 cases (533 duodenal slides) were processed by the AI triage pathway. AI processing took about 70 s per slide. The AI classifier had a sensitivity and positive predictive value (PPV) as follows: normal small bowel: 99.6%, 95.7%; coeliac disease: 86.7%, 100%; gastric heterotopia: 84.6%, 95.7%; adenoma: 88.9%, 88.9%; adenocarcinoma: 50.0%, 100%. In the AI triage workstream coeliac disease, and non-neoplastic abnormalities as a group, were reported quicker than in the standard workstream (6 days vs 10 days and 7 days vs 10 days, respectively, both p<0.005), but neoplastic lesions were not reported quicker. The cost of deployment and operation was reasonable. CONCLUSIONS: An NHS histopathology laboratory successfully developed and implemented an AI-based triage system for duodenal biopsies, achieving high diagnostic accuracy and significantly improving turnaround times for coeliac disease and non-neoplastic abnormalities as a group. This study demonstrates the feasibility and clinical value of locally developed AI tools within routine diagnostic practice.
21 May 2026
Read appraisal →Genome medicine
DNA methylation biomarkers-based pan-cancer classifier: predictive modeling for cancer classification
BACKGROUND: Machine-learning (ML) driven molecular diagnostics based on omics data has a potential to revolutionize personalized medicine. However, implementation of ML into diagnostic protocols is hindered by methodological challenges which often lead to inflated performance assessment of models during development followed by poor performance of these models in implementation phase. Here, we aimed to develop and validate a pan-cancer classification framework based on DNA methylation data, that addresses methodological challenges of omics data powered ML. METHODS: We curated a primary dataset of DNA methylation profiles for 10756 samples, that included 54 healthy and cancer tissue types and validation dataset comprising data for 2306 samples from 28 independent studies. The classification framework was build using custom biomarkers selection strategy based on effect size metric that considers variance and class imbalance. The ML models were trained, tuned and evaluated using nested cross-validation approach. Local outlier factor algorithm was built into the inference pipelines to identify and filter samples displaying technical or biological anomalies. Additionally, for methodological validation of our framework we used methylation profiles for 3905 central nervous system (CNS) tumors. RESULTS: We found that relatively simple ML models outperformed complex algorithms such as deep neural network. A logistic regression classifier achieved a balanced accuracy (BACC) of 0.90 to classify 54 cancer and healthy tissue types using methylation levels at 1208 CpG sites. Similarly, our CNS tumor classifier also based on logistic regression algorithm reached a BACC of 0.94 across 59 CNS tumor subtypes. The anomaly filtering improved performance across all categories of samples tested. CONCLUSIONS: Our study demonstrates that DNA methylation profiling, when combined with carefully controlled ML practices allows for development of robust solutions that might substantially increase the efficacy of oncological diagnosis. Finally, we deployed our inference pipelines for public access via secure web platform - https://opp.pum.edu.pl/ .
21 May 2026
Read appraisal →The British journal of dermatology
Evaluation and enhancement of the prognostic ability of the eighth edition of TNM staging in cutaneous malignant melanoma: a population-based study, using machine learning, of 111 871 patients
BACKGROUND: Melanoma is the fifth most common cancer in the USA and the UK, with global incidence on the rise. The TNM staging system guides treatment decisions and predicts patients' outcomes. OBJECTIVES: To evaluate the prognostic ability of the eighth edition TNM (TNM-8) staging system to predict overall (OS) and melanoma-specific survival (MSS) in cutaneous malignant melanoma (CMM), and to explore the potential of machine learning (ML) methods to enhance melanoma prognostication. METHODS: The records of adult patients diagnosed with CMM from 2018 to 2022 were extracted from the Surveillance, Epidemiology, and End Results (SEER) Program database. TNM-8 was evaluated using Kaplan-Meier plots and OS and MSS probabilities. Fine-Gray competing risk and accelerated failure time (AFT) models evaluated factors affecting MSS and OS, respectively. ML models were used to evaluate the predictive ability of TNM stages for OS and MSS, compared with that of multiple clinically important prognostic variables. RESULTS: Altogether, 111 871 patients with CMM were included in the analysis, with OS and MSS as survival endpoints. Most T (tumour), N (node), M (metastasis) and TNM-8 stage categories had distinct MSS and OS probabilities, except in the N1 and N2 stages at 12 months and in OS for TNM-8 stages 2 and 3 at 12, 36, 48 and 59 months. Fine-Gray and AFT models showed that age, sex, race/origin, tumour site, histological type, ulceration, Breslow thickness, mitotic rate, number of positive lymph nodes and M stage were important prognostic variables for MSS and OS. ML models showed that TNM had a higher predictive prognostic ability for MSS than OS and that including clinically important prognostic variables in addition to TNM stage has higher discriminative prognostic ability for OS and MSS (testing C-indices range 0.84-0.85 and 0.89-0.92, respectively) than using TNM staging alone (testing C-indices range 0.67-0.72 and 0.82-0.87, respectively). CONCLUSIONS: This proof-of-concept study demonstrated that although TNM staging retains prognostic value, adding important prognostic variables and using ML could improve prognostication for patients with melanoma. ML could be used to develop interactive clinical decision-support tools to improve the prognostication of individuals with melanoma. Cutaneous malignant melanoma is a common type of skin cancer. A guide called the ‘TNM’ is often used to decide what treatment patients should get. It also helps doctors decide how long patients need specialist care for. The guide is also used to help determine what the outlook for a patient might be. Lots of factors can affect the outcome for a person with the disease. These include a person’s age, sex and race. They also include factors related to the tumour, whether lymph glands are involved and whether the cancer has spread to other organs. Not all these factors are included in the current TNM guide. An accurate staging system is important. It will ensure that patients are followed-up and treated appropriately. This will help avoid unnecessary treatment or surveillance. In this study, we used a type of artificial intelligence (AI) to test how well the latest edition of the TNM can determine what the outlook for patients with melanoma is. We also used it to see if adding other important factors could improve its ability to predict the outlook for these patients. We included over 100,000 patients with melanoma from a large database called SEER. We found that using AI in addition to the current TNM guide could enhance the prediction of outcomes for patients with melanoma. The findings suggest that AI could be useful in helping health professionals predict outcomes for patients with melanoma.
20 May 2026
Read appraisal →Apoptosis : an international journal on programmed cell death
Single-cell profiling and machine learning identify cuproptosis-related fibroblast subpopulations and fibrogenesis modulator AEBP1 in endometriosis
Endometriosis is characterized by progressive fibrosis and limited therapeutic options. Cuproptosis, a copper-dependent form of regulated cell death, has been implicated in multiple pathological conditions, but its relevance to fibroblast-mediated fibrotic progression in endometriosis remains unclear. Single-cell RNA sequencing data from normal, eutopic, and ectopic endometrial tissues were analyzed to assess cuproptosis-related gene (CRG) activity and fibroblast heterogeneity. Pseudotime analysis, cell-cell communication analysis and high-dimensional weighted gene co-expression network analysis were performed to identify disease-associated fibroblast states and candidate fibrosis-related genes. Machine learning approaches were applied to prioritize candidate hub genes. Functional validation was conducted in endometrial stromal cells, and a mouse model of endometriosis was used to assess the effects of tetrathiomolybdate (TTM), a copper chelator. Elevated CRG activity was enriched in a distinct fibroblast subpopulation with profibrotic transcriptional features. Network and machine learning analyses consistently prioritized AEBP1 as a candidate fibroblast-associated hub gene linked to cuproptosis-related signatures. In vitro, CuCl2 plus elesclomol treatment was associated with increased AEBP1 and fibrosis-related marker expression, accompanied by changes in β-catenin pathway-related proteins, whereas FDX1 or AEBP1 knockdown attenuated these effects. In vivo, TTM treatment reduced lesion burden, fibrotic marker expression and collagen deposition in ectopic lesions. Cuproptosis-related molecular alterations are associated with fibroblast activation and fibrotic progression in endometriosis. Targeting copper metabolism may have therapeutic potential in limiting lesion fibrosis.
19 May 2026
Read appraisal →Biomedical physics & engineering express
Oral squamous cell carcinoma diagnosis with time and frequency domain features from optical coherence tomography A-scan signals
Optical coherence tomography (OCT) is extremely useful in the screening and detection of oral cancers. But various challenges, such as its subjectivity, operator dependence in interpretation, and lack of quantitative outcomes, have been delaying its adoption in clinical decision-making. The objective of this research is to quantify various A-scan features embedded in the OCT signal through advanced signal processing techniques and machine learning algorithms.Ex vivoimaging of biopsied oral tissues (normal mucosa, carcinomain situ(CIS), well-differentiated, and poorly differentiated oral squamous cell carcinoma) was performed using a spectral domain OCT system. Our A-scan dataset consisted of representative 1D signals obtained from different regions of the tissue bed. A set of 12 time- and 8 frequency-domain features were computed on each A-scan, and ten machine learning models were evaluated for binary and multi-label classification. LightGBM achieved the highest performance in both binary (accuracy: 0.8847,F1: 0.8878, AUC: 0.9539) and multi-label classification (accuracy: 0.8248,F1: 0.8201, AUC: 0.964). LightGBM was selected as the final model based on its superior and consistent performance across both classification paradigms. Our proof-of-concept feasibility study demonstrates good accuracy for differentiating oral mucosal tissues, highlighting the biomarker signature of A-scans.
19 May 2026
Read appraisal →Journal of molecular neuroscience : MN
Transcriptomic Analysis and Multiple Machine Learning Approaches Identify ZDHHC20 and Its Highly Correlated Gene AK5 as Biomarkers in Multiple System Atrophy
Multiple system atrophy (MSA) is a fatal neurodegenerative disorder lacking effective diagnostic tools. While protein palmitoylation is crucial for neuronal function, its specific role in MSA pathogenesis remains unexplored. We integrated bulk and single-nucleus RNA sequencing (snRNA-seq) data from postmortem MSA brain tissues. Eight machine learning algorithms were utilized to screen palmitoylation-related genes. Downstream analyses, including functional enrichment, cellular deconvolution, and pseudotime trajectory inference, were then conducted. ZDHHC20 and its highly correlated gene, AK5, were identified as hub genes. Both demonstrated significant downregulation in MSA, particularly within the cerebellar white matter. Functional enrichment analysis linked this expression pattern to mitochondrial dysfunction and impaired energy metabolism. Furthermore, snRNA-seq revealed that ZDHHC20 and AK5 are predominantly expressed in oligodendrocytes and exhibit lower expression levels along the developmental trajectory in MSA compared to healthy controls. ZDHHC20 and AK5 represent promising biomarkers for MSA. These findings provide new insights into the diagnosis and treatment of MSA.
18 May 2026
Read appraisal →European journal of cancer (Oxford, England : 1990)
Invasive lobular and ductal breast cancers: a systematic review and metanalysis in association with BRCA1/2 mutation status
BACKGROUND: Invasive lobular breast carcinoma (ILC) differs from invasive ductal breast carcinoma (IDC) with respect to genetic alterations and risk factors. We aimed to quantify differences in the prevalence of germline BRCA1/2 mutations between these two patients' populations. MATERIALS AND METHODS: We conducted a systematic literature search to extract data on the association between BRCA1/2 mutation status and breast cancer (BC) histological subtype (ILC and IDC). Summary odds ratios (SOR) and 95% CI were calculated using random effects univariate and bivariate models and between-study heterogeneity investigated through meta-regression and subgroup analyses. RESULTS: Twelve studies, published between 1998 and 2025, were considered, including 8004 BC women. BRCA1 mutations were significantly less frequent in patients with ILC than IDC (SOR=0.32, 95%CI (0.16-0.65)) whereas no association was found overall for BRCA2 (SOR=1.28, 95%CI (0.95-1.72)). The difference between the association with BRCA1 and BRCA2 was statistically significant (p-value<0.001). There was no indication of publication bias in BRCA1 (Egger's and Begg's test p-value=0.23, 0.12). The between study heterogeneity was 29% in BRCA1 and 0% in BRCA2. Excluding papers with high risk of bias, BRCA2 mutations were more frequent in patients with ILC than in IDC (SOR=2.56, 95%CI (1.15-5.7)). This association was primarily driven by the bivariate random-effects model, which accounts for the correlation between BRCA1 and BRCA2 estimates. CONCLUSIONS: In studies with lower risk of bias, germline BRCA2 mutations were more frequent in patients with ILC than IDC. Conversely, BRCA1 mutations are more frequently observed in IDC, particularly among younger patients and those with a positive family history of BC.
17 May 2026
Read appraisal →Clinica chimica acta; international journal of clinical chemistry
A laboratory-driven clinical decision support system algorithm for personalized and automated cardiovascular risk stratification in primary care patients.
OBJECTIVE: To develop and evaluate an automated clinical decision support system (CDSS) capable of computing both categorical and exact-percentage cardiovascular risk (CVR) in routine clinical practice. METHODS: We developed and implemented an automated CDSS (AlinIQ®) for CVR assessment within the Clinical Laboratory Department of Hospital Universitari i Politècnic La Fe (València, Spain), applied to patients referred from Primary Care. The analytical profile-requested either via automatic trigger or proactive clinician order-included total cholesterol, HDL-C, LDL-C, non-HDL-C, triglycerides, lipoprotein(a) [Lp(a)], serum creatinine, and estimated glomerular filtration rate. Additional required inputs were smoking status, systolic blood pressure, country of origin, and age at diabetes onset. The CDSS automatically computed SCORE2, SCORE2-OP, SCORE2-Diabetes, and SCORE2 Asia-Pacific, generating both categorical strata and exact-percentage CVR. Lp(a)-adjusted CVR was derived using coefficients from the Spanish Atherosclerosis Society. Following the ESC 2025 Focused Update, patients meeting predefined clinical criteria for moderate, high, or very high CVR were directly assigned to the corresponding category without SCORE calculation. The system also incorporated modifying risk factors, generating standardized interpretive comments and personalized lipid targets. RESULTS: Over one month, 2289 screenings were requested; 189 (8.3%) were excluded. A total of 171 patients (7.5%) were classified as high risk based on score-based calculation (164 [95.9%] triggered automatically), and 29 (1.6%) as very high risk (23 [79.3%] triggered automatically). 119 individuals (6.8%) were reclassified to a higher risk category after Lp(a)-based adjustment. CONCLUSION: This CDSS provides a scalable and reproducible framework for laboratory-driven cardiovascular prevention.
17 May 2026
Read appraisal →International immunopharmacology
NY-ESO-1 in Triple-Negative Breast Cancer: Systematic Review, Meta-Analysis, and Immunotherapeutic Implications
Breast cancer remains one of the most common types of cancer, including the subtype triple-negative breast cancer (TNBC) which is challenging to treat due to its aggressiveness. Cancer-testis antigens (CTAs), especially New York Esophageal Squamous Cell Carcinoma 1 (NY-ESO-1), have become promising immunotherapeutic targets attributable to their restricted expression profile in normal tissues but overexpressed in TNBC, leading to immunogenicity. This review provides comprehensive discussion of NY-ESO-1 including its structural basis of NY-ESO-1 recognition by T cell receptors (TCRs) and antibodies, epigenetic regulation via DNA methylation or histone modifications, and expression patterns or clinical relevance in TNBC. A systematic meta-analysis of 12 studies comprising 1,545 TNBC patients showed a pooled NY-ESO-1 expression prevalence of 16.1% (95% CI: 11.4-22.2%), with heterogeneity (I2=83.7%) attributable to antibody clone used for NY-ESO-1 detection (E978: 15.1% vs. D8.38: 32.6%, p<0.0001) and scoring methods (composite scoring: 15.9% vs. dual scoring: 16.9% vs. H-score: 10.1% vs. simple threshold: 32.6%, p<0.001). Structural analyses reveal NY-ESO-1157-165 recognition by TCRs, antibodies, and engineered binding scaffolds. We examine preclinical and clinical evidence for NY-ESO-1-targeted therapies, including adoptive cell therapy and peptide vaccines, which show manageable safety profiles and induce immunological responses. Epigenetic regulation is a therapeutic avenue, whereby hypomethylating agents and histone deacetylase inhibitors can upregulate NY-ESO-1 expressions that promote tumor immunogenicity. Nonetheless, challenges persist such as NY-ESO-1 expression heterogeneity, lack of TNBC-specific clinical trials, and inadequate immunogenicity. Future research should standardize NY-ESO-1 detection protocols to identify TNBC patients for NY-ESO-1-targeted immunotherapy, prioritize TNBC-specific trials and combinations with epigenetic priming agents.
16 May 2026
Read appraisal →Computer methods and programs in biomedicine
Explainable machine learning framework for the molecular classification of triple negative breast cancer
BACKGROUND AND OBJECTIVE: The difference in molecular characteristics of Triple negative breast cancer (TNBC) aids in distinguishing between its four prominent subtypes- basal-like 1, basal-like 2, mesenchymal, and luminal androgen receptor. This study presents the first integrative framework that combines explainable AI with machine learning approaches to classify TNBC subtypes. Unlike conventional models, our approach offers interpretability while enabling biomarker prioritization by identifying key hub genes that drive subtype-specific predictions. METHODS: In the experiment 783 cases (BL1 (160), BL2 (75), M (151), LAR (106), non-TNBC (291) reported in Gene Expression Omnibus (GEO) and Genomic Data Commons (GDC) data portal were used for the analysis. The proposed framework comprises modules for the identification of gene signatures for the four-subtype followed by the classification model based on eight different machine learning algorithms. Random Forest classifier was found to be best model with 96 % testing accuracy, which was elected for Explainable framework using Shapley Additive Explanations. RESULTS: Explainable biomarker module could provide a set of 47 biomarkers which is relevant in distinguishing the four types on triple negative breast cancer. The biomarkers could have the potential to be considered for TNBC prognosis in clinical setting. CONCLUSION: Key findings highlight the hub genes CDC20, CDCA2, PIMREG, KIF2C, and CENPW, implicating pathways such as ubiquitin-proteasome signaling and microtubule dynamics. These insights pave the way for biomarker-driven therapies and precision medicine in triple negative breast cancer.
16 May 2026
Read appraisal →European respiratory review : an official journal of the European Respiratory Society
Yield and safety of different biopsy types in interstitial lung disease: a systematic review and meta-analysis
BACKGROUND: Lung biopsy remains an important consideration in the management of interstitial lung disease (ILD). Transbronchial lung cryobiopsy (TBLC) offers an alternative to traditional surgical lung biopsy (SLB) and transbronchial forceps biopsy (TBB); however, up-to-date comparisons between these methods in ILD, particularly fibrotic ILD, remain limited. METHODS: A comprehensive literature search of Medline, Embase and Evidence-Based Medicine Reviews was performed for studies published between January 2000 and September 2025 to identify all citations reporting yield and complications of the three main lung biopsy methods for ILD. RESULTS: A total of 143 studies were included. Pooled multidisciplinary yield (following multidisciplinary discussion) in TBB, TBLC and SLB was 35.3% (95% CI 21.3-52.5), 84.3% (95% CI 81.7-86.5) and 88.6% (95% CI 83.4-92.3), respectively. For fibrotic ILD, the multidisciplinary yield was 12.5% (only one eligible study), 87.6% (95% CI 83.5-90.7) and 87.3% (95%CI 80.5-92.0), respectively. Meta-regression showed an increasing multidisciplinary yield of TBLC with more recent years of patient recruitment and an increasing percentage of fibrotic ILD in each study. The multidisciplinary yield of both TBLC and SLB was 85-90%, suggesting a biopsy "ceiling effect". All evaluated complications were more frequent in TBLC compared to TBB and some were more frequent in SLB compared to TBLC. Several complications were more frequent in fibrotic ILD compared to all ILD. CONCLUSIONS: The multidisciplinary yield of TBLC and SLB is equivalent, with both offering an acceptable safety profile. TBB has low yield, particularly in fibrotic ILD. These findings support using either TBLC or SLB as an initial diagnostic tool in fibrotic ILD, mainly based on patient-physician shared decision-making.
15 May 2026
Read appraisal →JMIR formative research
Automatic Speech Recognition and Large Language Models for Multilingual Pathology Report Generation: Proof-of-Concept Study
BACKGROUND: Accurate transcription of pathology gross examination dictation is important for clinical documentation, but multilingual dictation remains challenging in settings where clinicians mix Chinese and English while final pathology reports are written in English. OBJECTIVE: This study aimed to evaluate whether a Whisper-based automatic speech recognition (ASR) pipeline guided by contextual system messages and combined with open-source large language models (LLMs; Qwen2:72b, Llama3.1:70b, Gemma2:27b) could improve multilingual (Chinese-English) pathology dictation transcription accuracy and generate clinically appropriate English gross description reports. METHODS: We conducted a controlled proof-of-concept study using 125 simulated mixed Chinese-English pathology gross examination audio recordings created by physicians or pathologists. Audio recordings were transcribed using Whisper ASR with and without a contextual system message. The ASR transcripts were then converted into English gross description reports using 3 open-source LLMs: Qwen2:72b, Llama3.1:70b, and Gemma2:27b. Outcomes included character error rate, Bilingual Evaluation Understudy, Recall-Oriented Understudy for Gisting Evaluation (ROUGE)-1, ROUGE-2, ROUGE-L, Metric for Evaluation of Translation with Explicit Ordering, pathologist Win-Tie-Lose rankings, report-level error categories, inference time, and interrater agreement. RESULTS: The ASR contextual system message reduced the mean character error rate from 0.344 (SD 0.176; 95% CI 0.313-0.375) to 0.066 (SD 0.100; 95% CI 0.048-0.084; P<.001). Qwen2:72b achieved the highest automated metric scores, including a Bilingual Evaluation Understudy of 0.644 (SD 0.307), ROUGE-1 of 0.866 (SD 0.163), ROUGE-2 of 0.771 (SD 0.235), ROUGE-L of 0.842 (SD 0.178), and Metric for Evaluation of Translation with Explicit Ordering of 0.805 (SD 0.214). Pathologist-coded total error rates were 16.8% (21/125) for Qwen2:72b, 45.6% (57/125) for Llama3.1:70b, and 92.8% (116/125) for Gemma2:27b. The exact agreement between the 2 pathologists across full ranking categories was 76.8% (96/125; Cohen κ=0.668), and agreement on the top-ranked model or tied top group was 81.6% (102/125; Cohen κ=0.722). CONCLUSIONS: In this proof-of-concept evaluation, contextual prompting improved ASR transcription accuracy, and Qwen2:72b generated the most accurate English pathology reports among the evaluated LLMs. However, the study used simulated audio recordings, a local vocabulary prompt, and report-level rather than term-level clinical annotation. LLM-generated reports should therefore be considered draft documentation requiring pathologist verification, and prospective validation in real clinical workflows is needed before clinical deployment.
15 May 2026
Read appraisal →Endocrine pathology
Impact of Molecular Testing on Surgical Decision-Making in Indeterminate Thyroid Nodules: A Global Meta-Analysis Across Test Generations
Thyroid nodules with indeterminate cytology represent a clinical challenge owing to uncertain malignancy risk, often leading to diagnostic surgery. Molecular testing has emerged as a promising adjunct to improve risk stratification and guide surgical decision-making. However, the clinical utility and impact of different molecular platforms remain debated. The present study evaluates the impact of molecular testing on surgical decision-making in indeterminate thyroid nodules and compares outcomes between first- and second-generation molecular platforms. A PRISMA-guided systematic review and meta-analysis identified 132 studies including 66,448 thyroid nodules, of which 30,292 (45.6%) were indeterminate (Bethesda III/IV). Pooled analyses included studies directly comparing conventional management with molecular testing or different molecular platforms. Primary outcomes were surgical resection rates and risk of malignancy (ROM), stratified by diagnostic approach and test generation. Conventional management demonstrated significantly higher surgical rates than molecular testing group (OR = 2.258, 95% CI: 1.548-3.293, p < 0.001). ROM among resected nodules was lower in the conventional management compared with the molecular testing group (OR = 0.594, 95% CI: 0.388-0.911, p = 0.017). First-generation molecular tests showed higher surgical rates and lower ROM than second-generation assays (OR = 1.709, 95% CI: 1.122-2.601, p = 0.013; OR = 0.665, 95% CI: 0.515-0.858, p = 0.002, respectively). Exclusion of non-invasive follicular thyroid neoplasm with papillary-like nuclear features attenuated differences in malignancy rates. Molecular testing significantly reduces surgical interventions in indeterminate thyroid nodules without evidence of reduced detection of clinically significant malignancy, particularly with second-generation platforms supporting more individualized and evidence-based management strategies.
14 May 2026
Read appraisal →Proceedings of the National Academy of Sciences of the United States of America
Deep-learning endomicroscope with large field-of-view and depth-of-field for real-time in vivo imaging of epithelial cancer hallmarks
In vivo microscopy (IVM) has shown great promise to improve early detection of epithelial precancer, but it suffers from fundamental trade-offs that limit the resolution, field-of-view (FOV) and depth-of-field (DOF). Here, we present PrecisionView, a compact, deep learning-enabled endomicroscope that breaks these constraints and achieves 20 mm2 FOV and 500 µm DOF with 4 µm resolution, representing approximately 5× increase in FOV and 8× larger DOF compared to conventional IVM with similar resolution. PrecisionView integrates a deep learning-optimized phase mask and real-time reconstruction, enabling rapid in vivo assessment of two key hallmarks of cancer: epithelial cell nuclear morphology and subsurface microvasculature through fluorescence and reflectance imaging. By imaging the oral cavity of healthy volunteers and cervical specimens with precancerous lesions, PrecisionView generates large-scale (1 to 3 cm2) coregistered maps of cellular and vascular structures, revealing distinct microscopic patterns associated with anatomic structures and precancerous lesions. Our results suggest the potential of this computational endomicroscope to address the unmet need for early cancer detection at the point of care.
13 May 2026
Read appraisal →Neuroinformatics
Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy
Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biological and neuroscience research. Although unsupervised domain adaptation (UDA) methods can help mitigate domain shifts and reduce the high costs of annotating each domain, they typically have relatively low performance in practical applications. Thus, we investigate weakly supervised domain adaptation (WDA) that utilizes additional sparse point labels on the target domain, which require minimal annotation effort and minimal expert knowledge. To take full use of the incomplete and imprecise point annotations, we introduce a multitask learning framework that jointly conducts segmentation and center detection with a novel cross-teaching mechanism and class-focused cross-domain contrastive learning. While leveraging unlabeled image regions is essential, we introduce segmentation self-training with a novel instance-aware pseudo-label (IPL) selection strategy. Unlike existing methods that typically rely on pixel-wise pseudo-label filtering, the IPL semantically selects reliable and diverse pseudo-labels with the help of the detection task. Comprehensive validations and comparisons on challenging datasets demonstrate that our method outperforms existing UDA and WDA methods, significantly narrowing the performance gap with the supervised upper bound. Furthermore, under the UDA setting, our method also achieves substantial improvements over other UDA techniques.
13 May 2026
Read appraisal →Journal of chromatography. A
Microfluidics in separation science: Fabrication, applications and intelligent systems
The emergence of advanced, innovative microfluidic devices has reshaped analytical separation methodologies and biomolecular diagnostics by introducing highly integrated, miniaturized systems that enable next-generation fluid manipulation, enhanced automation, precision, cost efficiency, and high-throughput capabilities. Advances in fabrication methods, such as soft lithography, photolithography, and 3D printing, have enabled the production of customizable microfluidic platforms from materials such as PDMS, glass, and thermoplastics. These microfluidic systems support a range of analytical functionalities of the technologies, including gas chromatography (GC), high-performance liquid chromatography (HPLC), and electrophoresis, delivering rapid, high-resolution analyses with minimal sample and reagent requirements, quicker analysis, and enhanced uniformity and stability, facilitating high productivity screening, improved sensitivity and portability. Integration of micro-GC systems enables rapid, portable detection of volatile compounds, while microfluidic HPLC and electrophoresis provide precise biomolecular separations and real-time diagnostics. Recent advancements in artificial intelligence (AI) have now brought significant innovations in microfluidic devices, resulting in a new era of intelligent analytical separations, where machine learning algorithms and neural networks are applicable not only for data processing and pattern recognition but also for real-time optimization, anomaly detection, innovative read-out systems, and autonomous system control. The fusion of AI and microfluidics has enabled new approaches to dynamic experimentation, reshaping traditional microfluidics and personalized diagnostics and health care systems, where rapid, reliable analysis is paramount. In this review article, we comprehensively explain the progressive convergence of microfluidics and AI across various electrophoretic and chromatographic analytical separation techniques, elaborating on the latest technological innovations, fundamental fabrication strategies, and emergent applications. The article also presents a forward-looking perspective on how AI-enabled microfluidics enhances automation, scalability, and application-specific customization, which could shape the future of intelligent analytical separation systems.
12 May 2026
Read appraisal →Lasers in medical science
Machine learning enhanced optical spectroscopy for breast cancer diagnosis: A review
This literature review examines the transformative role of machine learning (ML) and deep learning (DL) in enhancing optical spectroscopy for breast cancer diagnosis. By synthesizing advancements from peer-reviewed studies (2015-2025), we evaluate how ML/DL integration improves the detection of malignancy-associated biochemical changes, enabling noninvasive, rapid, and accurate differentiation between healthy and cancerous tissues. This review highlights key spectroscopic modalities, such as Raman, fluorescence, diffusive optical spectroscopy (DOS), and photoacoustic spectroscopy (PAS), and their integration with AI-driven models, such as convolutional neural networks (CNNs), support vector machines (SVMs), and logistic regression. These techniques achieve diagnostic accuracies of up to 94% in subtype classification (e.g., luminal A, HER2-positive) by analyzing spectral biomarkers such as hemoglobin, lipids, and collagen. Challenges such as data variability, model interpretability, and clinical integration barriers are critically assessed. These findings underscore the potential of ML/DL-enhanced spectroscopy to standardize diagnostics, reduce unnecessary biopsies, and personalize treatment monitoring. Future directions emphasize the need for explainable AI (XAI), multimodal data fusion, and large-scale, diverse datasets to bridge translational gaps. By addressing technical, ethical, and regulatory hurdles, this integration promises to advance early detection, improve clinical outcomes, and reshape precision oncology.
11 May 2026
Read appraisal →Molecular omics
Placental metabolomics for assessment of pregnancy complications: a systematic review
Metabolomics is a powerful tool for understanding biological function at the cellular level. While this omics technology has found application in areas ranging from toxicology to cancer, its potential for the study of human pregnancy complications is in its infancy. Proper placental function is critical for a healthy pregnancy and assessing placental metabolism offers a direct window into placental physiology. This review aims to analyse placental metabolomics in pregnancy complications in humans. A systematic search was completed using PubMed and Google Scholar, and the Covidence software was used for the screening process. Following title and abstract screening and full-text review, 32 articles remained and were included in this review. Multiple articles performed metabolomics using mass spectrometry and/or nuclear magnetic resonance to study pre-eclampsia, gestational hypertension, foetal growth restriction, maternal obesity, gestational diabetes mellitus, intrahepatic cholestasis of pregnancy, and preterm birth. A subset of pregnancy complications was investigated in only a single study each (human immunodeficiency virus in pregnancy, neural tube defects, chromosomal disorders, chronic hypoxia, and recurrent pregnancy loss). Univariate analyses identified potential biomarkers of pregnancy complications. Multivariate analyses demonstrated that the placental global metabolic profiles could separate healthy and complicated pregnancies and identified metabolic pathways (e.g. amino acid metabolism, lipid and phospholipid metabolism) to explain pathogenesis and the mechanisms of disease. We highlight knowledge gaps and future directions, emphasizing the need for data replication and inclusion of variables such as biological sex in the field of placental metabolomics.
11 May 2026
Read appraisal →Analytical chemistry
Quantitative Analysis of Multiple Serum Tumor Biomarkers by an Interpretable Stacked Ensemble Model
Surface-enhanced Raman spectroscopy (SERS) offers exceptional sensitivity and specificity for biomolecular detection, particularly in analyzing serum tumor biomarkers. However, its application is hindered by spectral complexity and matrix interference. Although machine learning (ML) has shown promise in SERS data analysis, existing quantitative models for biomarker detection lack generalizability and interpretability. To address these challenges, we developed an interpretable stacked ensemble model (ISEM) that integrates feature selection, ensemble learning, and explainable artificial intelligence (XAI) for quantifying 12 serum tumor biomarkers. To ensure reliable quantitative analysis, we validated the acquired SERS data using uniform and reproducible Au nanoparticle substrates. Preprocessing, least absolute shrinkage, and selection operator (LASSO) feature selection were employed to establish a foundation for accurate quantification. Subsequently, 12 serum tumor biomarkers were quantified, demonstrating the superior performance of ISEM, which achieved a high predictive accuracy, with R2 values exceeding 0.9 for all biomarkers. Crucially, based on the quantitative results, we provided molecular-level interpretability for structure-spectrum correlations using Shapley additive explanations (SHAP), revealing how glycosylation reactions, matrix interference, and spectral overlap influence prediction accuracy. Furthermore, the capability of ISEM to quantify multiple biomarkers in unseen samples was confirmed through validation of its generalizability. Our study establishes an ensemble-driven, interpretable framework for quantitative biomarker analysis in a complex biological matrix, demonstrating significant potential for early cancer diagnosis and screening.
11 May 2026
Read appraisal →Analytical chemistry
FiLM-Enhanced Biologically Informed Neural Networks for Multiclass Omics Analysis and Biomarker Discovery
High-throughput proteomics enables detailed molecular phenotyping but poses challenges for predictive modeling and interpretation due to high dimensionality, sparsity, and nonlinear interactions. Biologically informed neural networks (BINNs) address these challenges by embedding pathway knowledge into network architectures, providing interpretable models of complex omics data. We present BINN-FiLM, which extends conventional BINNs by integrating feature-wise linear modulation, enabling task-specific scaling and shifting of pathway-level activations while preserving a fixed Reactome-based hierarchy. Unlike BINNs that share all pathway parameters across classes, BINN-FiLM captures class-dependent biological rewiring, making it particularly effective for multiclass classification tasks. Multiclass problems are reformulated as multitask binary learning, allowing pathway activations to adapt to disease-specific contexts. We evaluated BINN-FiLM on three multiclass proteomic data sets, and BINN-FiLM consistently outperformed conventional BINNs and standard machine learning models. FiLM modulation parameters revealed task-specific pathway activity, and SHAP-based interpretation identified key proteins and pathways driving disease discrimination.
11 May 2026
Read appraisal →Cancer immunology, immunotherapy : CII
Artificial intelligence-powered H&E-based quantification of spatial tumor-infiltrating lymphocyte distribution identifies prognostic immune niches in colorectal cancer
PURPOSE: The prognostic significance of tumor-infiltrating lymphocytes (TILs) in colorectal cancer (CRC) is well established; however, existing approaches inadequately capture their spatial distribution. We investigated the prognostic implications of TIL spatial distribution in CRC using an artificial intelligence (AI)-based method. METHODS: A total of 202 patients with stage II-III CRC were included. TIL densities in intratumoral (iTIL) and stromal (sTIL) regions were quantified using AI-based analysis of hematoxylin and eosin (H&E)-stained images. Based on proximity to the tumor-stromal border (TSB), TILs were subclassified into core iTIL, bounding iTIL, bounding sTIL, and outermost sTIL. Immunoscore was calculated from CD3+ and CD8+ T-cell densities in the tumor center and invasive margin. RESULTS: Correlations between AI-based and pathologist assessments (iTIL: r = 0.57; sTIL: r = 0.70) were comparable to inter-pathologist correlations (iTIL: r = 0.47; sTIL: r = 0.70). In univariate Cox regression analysis, bounding iTIL, bounding sTIL, and outermost sTIL were significantly associated with recurrence-free survival (RFS), whereas core iTIL was not. Composite TIL and TSB scores were developed by incorporating the prognostically significant regions. In multivariable analysis, the TIL score (p = 0.001), TSB score (p < 0.001), and Immunoscore (p < 0.001) independently predicted RFS. In microsatellite instability-high tumors, only the TSB score remained prognostically significant. CONCLUSION: AI-powered spatial analysis of TILs, particularly the TSB score, demonstrated prognostic performance comparable to conventional Immunoscore, thereby supporting the value of spatial immune profiling and AI-driven analysis of H&E-stained slides for improved risk stratification in CRC.
11 May 2026
Read appraisal →Briefings in bioinformatics
MLN2SVG: domain-aware spatially variable gene detection using contrastive variational autoencoder and multi-level neighbor search
Spatial transcriptomics (ST) technologies have transformed our ability to examine gene expression within intact tissues, yet accurately identifying spatially variable genes (SVGs) remains challenging due to spatial heterogeneity, data sparsity, and incomplete modeling of domain-level dependencies. To address these limitations, we propose MLN2SVG, a domain-aware framework that integrates contrastive variational autoencoding with a multi-level neighbor (MLN) search algorithm to jointly learn tissue domains and SVGs. MLN2SVG constructs a weighted spatial graph to capture both local and long-range spatial relationships, employing a deep contrastive variational autoencoder to align augmented and original data representations while preserving biological diversity. The MLN algorithm dynamically expands neighborhood connectivity to mitigate sparsity and enhance domain coherence. Across multiple human and mouse ST datasets, including dorsolateral prefrontal cortex, breast cancer, and brain tissues, MLN2SVG consistently outperformed existing methods in clustering accuracy, robustness, and biological interpretability. Notably, in breast cancer tissues, MLN2SVG uncovers fine-grained spatial organization of tertiary lymphoid structures, delineating region-specific immune architectures spanning intratumoral, tumor-edge, and extratumoral compartments. Through the integration of spatial domain discovery and SVG detection, MLN2SVG delivers a robust and biologically interpretable framework for uncovering the molecular and structural complexity of tissue organization.
10 May 2026
Read appraisal →European journal of cancer (Oxford, England : 1990)
MuTriM: A multiscale deep learning model integrating longitudinal radiomics and pathomic features for predicting recurrence and adjuvant radiation benefit in breast cancer.
PURPOSE: We present MuTriM, a multimodal deep learning model integrating DCE-MRI and whole-slide pathology to predict survival and radiation benefit in breast cancer. PATIENTS AND METHODS: MuTriM employs an attention-based cross-modal and cross-temporal fusion framework that concurrently integrates DCE-MRI radiomic features with pathomic features of cellular morphology on WSI. MuTriM was trained on the Fudan University Shanghai Cancer Center (FUSCC) cohort (N = 335) and externally tested on the TCGA cohort (N = 126) using matched DCE-MRI and WSI. RESULTS: MuTriM was prognostic of recurrence-free survival (RFS) in a subtype-agnostic setting (HR = 5.26, 95% CI, 1.69-16.4, p = 0.004; C-index = 0.75), outperforming unimodal models based on DCE-MRI alone (C-index = 0.65) or WSI alone (C-index = 0.70). MuTriM was also prognostic among HER2 + (HR = 6.82, 95% CI, 1.08-43.2, p = 0.04) and ER+ populations (HR = 4.61, 95% CI, 1.25-17.1, p = 0.02). A high MuTriM score was associated with improved RFS (HR = 0.15, 95% CI 0.03-0.87; P = 0.03), whereas a low MuTriM score showed no significant benefit (HR = 4.06, 95% CI 0.05-31; P = 0.53) (interaction P = 0.04). Transcriptomic analyses revealed that high-risk tumors showed suppressed cytotoxic T-cell activity and enrichment of extracellular matrix remodeling, neutrophil degranulation, and neuronal signaling, consistent with immune evasion. Upregulation of NRXN1, GABRA3, KCNK3, and KLK12 was linked to worse survival, whereas SYNGR3 and CD207 were associated with favorable outcomes. CONCLUSION: By unifying radiology, pathology, and transcriptomics, MuTriM provides an interpretable multimodal framework for breast cancer prognosis and treatment guidance.
10 May 2026
Read appraisal →Medical image analysis
Context-enriched contrastive auto-encoder with topology learning for medical hyperspectral image classification to diagnose tumors
Deep learning has emerged as a highly effective approach for the automatic classification of medical hyperspectral images (MedHSIs), facilitating the accurate diagnosis of diverse tumors. Most of current methods suffer from the challenges in the separability of latent representation and the preservation of topological structure. To remedy such deficiencies, we propose a novel context-enriched contrastive auto-encoder with topology learning (CCAET) based MedHSI classification for tumor diagnosis. Concretely, we initially employ an auto-encoder (AE) network as the foundational framework to achieve latent representation and data reconstruction. Subsequently, to enhance the separability of the latent representation, we integrate a context-enriched contrastive loss into the AE framework, where both individual pixels and their contextual information are used to redefine contrastive learning, so that small distances between intra-class features and large distances between inter-class features are achieved. Further, we construct a topology-preserved loss by incorporating a graph based approach into the foundational framework, which aims to maintain the topological structure during latent representation learning. Furthermore, we devise a gradient descent-based optimization scheme to optimize the overall loss of the proposed CCAET method, so as to obtain the final latent representation of MedHSI. Finally, we implement soft-max-based label prediction to obtain the classification results. Different from most existing methods, the CCAET approach considers both the separability of latent representations and the preservation of topological structure to enhance MedHSI classification performance. Extensive experimental evidence has been presented to substantiate that the proposed CCAET method outperforms several state-of-the-art techniques in terms of MedHSI classification based tumor diagnosis.
9 May 2026
Read appraisal →Journal of clinical ultrasound : JCU
Integrative Machine Learning Model Leveraging DCE-MRI and PSA Values for Advanced Risk Stratification in Prostate Cancer
PURPOSE: Accurate grading of prostate cancer is critical for treatment strategies and risk stratification. This study aims to develop a machine learning (ML) model integrating Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) pharmacokinetic parameters with Prostate-Specific Antigen (PSA) values to predict ISUP grade metastatic risk groups. METHODS: This retrospective study included 102 patients with histologically confirmed prostate cancer. DCE-MRI pharmacokinetic parameters (Ktrans, Kep, Ve, CER, MaxSlope, IAUGC) were standardized. The dataset was balanced using the Synthetic Minority Oversampling Technique and split into training, validation, and test sets. ML models, including Random Forest, were evaluated using Area Under the Curve (AUC) values. RESULTS: The Random Forest classifier achieved the highest performance, with an AUC of 0.92. Precision-recall analysis identified an optimal threshold of 0.3, balancing sensitivity and specificity for high-risk group detection. SHAP analysis highlighted PSA, MaxSlope, and Kep as key predictors contributing to model accuracy. CONCLUSION: Integrating DCE-MRI parameters with PSA values using ML algorithms enhances the prediction of ISUP grade metastatic risk groups. This method provides a robust tool for metastasis screening and personalized treatment in prostate cancer.
9 May 2026
Read appraisal →Computer methods in biomechanics and biomedical engineering
Modified mutual information feature selection algorithm to predict COVID-19 using clinical data
The COVID-19 pandemic has profoundly impacted health, emphasizing the need for timely disease detection. Blood tests have become key diagnostic tools due to the virus's effects on blood composition. Accurate COVID-19 prediction through machine learning requires selecting relevant features, as irrelevant features can lower classification accuracy. This study proposes Modified Mutual Information (MMI) for feature selection, ranking features by relevance and using backtracking to find the optimal subset. Support Vector Machines (SVM) are then used for classification. Results show that MMI with SVM achieves 95% accuracy, outperforming other methods, and demonstrates strong generalizability on various benchmark datasets.
6 May 2026
Read appraisal →Annals of surgical oncology
CT-based Prediction of Visceral Pleural Invasion in Lung Adenocarcinoma ≤ 3 cm: Enhancing Deep Learning Specificity by Waiving Chest Wall Information
BACKGROUND: Accurate preoperative prediction of visceral pleural invasion (VPI) in lung adenocarcinoma is essential for guiding surgical decision-making. However, existing prediction models often sacrifice specificity when optimized for high sensitivity, increasing the risk of overtreatment. This study aimed to develop a computed tomography (CT)-based deep learning (DL) model that improves specificity by excluding chest wall information. METHODS: We retrospectively enrolled 835 patients with pathologically confirmed lung adenocarcinoma who underwent complete resection at two medical centers. A VPI-DL model was developed using a four-layer convolutional neural network incorporating a novel attention mechanism trained on chest-wall-masked CT inputs. The model was trained on 692 cases and externally validated on an independent cohort of 143 patients. Performance was benchmarked against the consolidation-to-tumor ratio (CTR), a published DL model, and assessments by three thoracic surgeons. Evaluation metrics included area under the curve (AUC), sensitivity, specificity, and accuracy under a high-sensitivity operating threshold. RESULTS: In external validation, VPI-DL achieved an AUC of 0.91, sensitivity of 91%, specificity of 82%, and accuracy of 83%, outperforming the CTR (specificity 63%), the previously published model (specificity 54%), and thoracic surgeons (specificity 57%) at comparable sensitivity levels. The attention-guided architecture effectively reduced spurious correlations and improved interpretability. CONCLUSION: The proposed VPI-DL model improves the specificity of VPI prediction while preserving high sensitivity. By intentionally excluding chest wall information, the model offers a robust and interpretable tool to aid preoperative planning and minimize the risk of both under- and overtreatment in early-stage lung adenocarcinoma.
6 May 2026
Read appraisal →Microscopy research and technique
Deep Learning Integration in Optical Microscopy: Advancements and Applications
Optical microscopy is a cornerstone imaging technique in biomedical research, enabling visualization of subcellular structures beyond the resolution limit of the human eye. However, conventional optical microscopy faces challenges such as optical aberrations, diffraction-limited resolution, low signal-to-noise ratio (SNR), and poor contrast. The exponential growth of bioimaging data further underscores the need for advanced computational tools. Deep learning (DL) is a subset of machine learning that has emerged as a transformative approach to address these limitations, offering enhanced precision, reduced manual intervention, and diminished reliance on domain-specific expertise for image reconstruction, enhancement, and analysis. This review explores the integration of DL into optical microscopy, focusing on key applications including image classification, segmentation, and computational reconstruction. We examine prominent DL architectures such as convolutional neural networks (CNNs), U-Nets, residual networks (ResNets), and generative adversarial networks (GANs)-and their role in advancing diverse microscopy modalities. These frameworks enhance image quality, improve quantitative analysis, and democratize access to high-performance microscopy. Additionally, we discuss persisting challenges, including the demand for large, annotated datasets, dynamic sample variability, model interpretability, and potential data biases. Collectively, DL is poised to revolutionize optical microscopy, shaping its future developments in biomedical imaging.
6 May 2026
Read appraisal →Cytopathology : official journal of the British Society for Clinical Cytology
Comparative Evaluation of Transfer Learning Models for Detecting Malignant Cells in Urinary Cytology
AIMS AND OBJECTIVES: In the present paper, we compared the efficiency of six transfer learning models to detect malignant cells in urine cytology. We also applied an ensemble learning with weighted soft voting to assess its importance in the diagnostic accuracy in urine cytology. MATERIALS AND METHODS: The voided urine samples of total 104 cases of urothelial cell carcinoma (UCC) and 86 cases with no malignancy (benign) were selected. All the 104 cases of UCC were histopathology proven high grade urothelial cell carcinoma (UCC). Urine with negative cytology reports were followed up clinically. There were 446 images of benign samples and 1369 images from malignant samples on 100 x objective. We applied six transfer learning models (DenseNet121, inception_v3, ResNet50, MobileNetV2, VGG16 and Xception) to detect malignant cells in urine. To compare the performance of different models, dynamic training optimization was done and each model was auto stopped after their maximum performance. In addition, an ensemble learning with soft voting was used including the top three models to enhance the diagnostic accuracy. RESULT: Xception transfer model showed the highest sensitivity (88.57%), accuracy (86.55%), precision (80.52%) and FI score (84.35%). It was the best performing model. The other two top performing models were InceptionV3 and ResNet50. The area under curve of receiver operating characteristic (AUCROC) was ≤ 90 in all the transfer learning models. The accuracy, sensitivity, specificity, precision, F1-Score and AUCROC of the ensemble transfer learning model were as follows: 92.10%, 95.41%, 85.51%, 91.23%, 93.24% and 0.977 respectively. CONCLUSIONS: First time, we evaluated a large number of transfer learning models in urine cytology to detect malignant cells. All the models showed high sensitivity, specificity and accuracy. In addition, the ensemble learning technique with soft voting showed remarkable superior performance than individual top three transfer learning models. The techniques transfer learning and ensemble models have high potential to use in routine screening of urine.
6 May 2026
Read appraisal →Journal of medical virology
A Triage Model for HR-HPV Positive Women Based on Methylation of Human and HPV Genes
The aim of this study is to develop a machine learning triage model for HR-HPV positive women based on methylation patterns of human and HPV genes to predict the risk of CIN2 +, and to compare its performance with traditional detection techniques. A total of 512 eligible women participated in the study, with exfoliated cervical cell specimens collected for methylation analysis of both human and HPV genes. Highly methylated gene fragments related to cervical cancer were identified through high density, high association, high MHL (Methylation Haplotype Load) screening and Logistic regression. The samples were divided into a training set and a validation set at a ratio of 7:3, and a machine learning triage model was constructed using CIN2+ as the outcome. Among 512 HR-HPV positive women, 174 (34.0%) had CIN2 +. To construct the random forest model, 10 high methylation human gene fragments were identified from a pool of 45 genes, along with HPV 16, 18, and 52 L2 genes. In the validation set, the random forest model identified 45 samples as positive (38 were true positives) and 112 samples as negative (96 were true negatives). The model achieved an AUC of 0.9, and DeLong test confirmed its performance was significantly superior (p < 0.001) to HPV 16/18 genotyping and cytology testing. The random forest model constructed based on methylation patterns of human and HPV genes demonstrated strong predictive efficacy for CIN2+ in HR-HPV positive women, and may optimize the triage method in cervical cancer screening.
5 May 2026
Read appraisal →Menopause (New York, N.Y.)
Deciphering the predictors of endometrial nonbenign lesions in asymptomatic postmenopausal women via explainable machine learning
OBJECTIVES: Timely identification of endometrial nonbenign lesions led to improved outcomes, but there was a lack of effective predictive models for asymptomatic endometrial thickening. The aim of this study was to develop a strong machine learning (ML) model for assessing the risk of endometrial malignancy in asymptomatic patients after menopause. METHODS: This retrospective study was designed to collect data from 971 postmenopausal asymptomatic women with endometrial thickening. The bootstrap resampling method was used for model training, internal validation, and external validation. With 41 easily accessible characteristics, multifactor regression and least absolute shrinkage and selection operator regression were performed for feature selection. Nine ML algorithms were applied to build a model. To explain the final model and rank feature importance, the SHapley Additive exPlanation (SHAP) method was utilized. Meanwhile, a nomogram was developed to facilitate model interpretation. RESULTS: The comprehensive methodologies identified parity, Doppler flow signals, endometrial thickness, cancer antigen 125, and D-dimer as significant predictors. The logistic regression (LR) model demonstrated superior performance compared with other ML algorithms, achieving an accuracy of 88%, a sensitivity of 78%, a specificity of 98%, and an area under the receiver operating characteristic curve of 0.81. Furthermore, individualized predictions of endometrial malignancy were visualized through a force plot generated by SHAP analysis. A nomogram based on the LR model was subsequently constructed, showing area under the receiver operating characteristic curve values of 0.82, 0.82, and 0.81 for the training, internal validation, and external validation cohorts, respectively. The calibration curve demonstrated excellent consistency. CONCLUSIONS: We developed an LR-based nomogram model and interpreted using the SHAP method, which provided visual insights for detecting endometrial nonbenign lesions in asymptomatic postmenopausal women. This approach would aid clinicians in providing individualized treatment and help avoid unnecessary invasive surgeries.
5 May 2026
Read appraisal →Journal of the European Academy of Dermatology and Venereology : JEADV
A deep learning-clinical nomogram hybrid for predicting sentinel lymph node metastasis in melanoma
BACKGROUND: Melanoma is a life-threatening skin malignancy, with sentinel lymph node metastasis (SLNM) serving as a critical prognostic factor. While machine and deep learning models using histopathology have focused on melanoma diagnosis, limited efforts have aimed to predict SLNM. OBJECTIVES: This study aimed to develop a collaborative machine and deep learning model that integrates histopathological patches and clinical data to predict SLNM in patients with invasive melanoma, thereby aiding decision-making regarding sentinel lymph node biopsy. METHODS: A total of 78 invasive cutaneous melanoma cases (43 SLNM-positive and 35 SLNM-negative) from the University of Yamanashi Hospital (2007-2022) were divided into training (n = 60) and test (n = 18) datasets. A clustering-constrained attention multiple-instance learning (CLAM) model was developed using haematoxylin and eosin-stained whole-slide images. Among the four CLAM variants, the model using a ResNet50trunc encoder trained on whole-tissue regions (CLAM-R50) demonstrated the best performance and was further integrated with a clinical nomogram. Hybrid modelling was performed using logistic regression, a support vector machine and gradient boosting. RESULTS: CLAM-R50 achieved an area under the receiver operating characteristic curve (AUROC) of 0.875, while the clinical nomogram achieved an AUROC of 0.826 on the test set. The gradient boosting hybrid model, termed the Melanoma Indicative Scorer for Sentinel Lymph node Evaluation (MISSLE), demonstrated the highest AUROC of 0.950 (95% bootstrapped confidence interval (CI): 0.933-1.00) on the test set. CLAM-R50 attention maps identified pale cytoplasm and plasma cell-like tumour cells as predictors of positive SLNM, whereas dense melanin deposition and lymphocyte-like tumour cells predicted negative SLNM. CONCLUSIONS: MISSLE integrates histopathological and clinical data to predict SLNM with high AUROC, surpassing the previous reports and offering a tool for clinical decision-making. Limitations include the single-centre design and predominantly Japanese cohort, limiting generalizability. The code and models are publicly available for external validation.
5 May 2026
Read appraisal →Journal of the American Society of Nephrology : JASN
Streamlining the Histopathologic Workflow in Diabetic Kidney Disease with Artificial Intelligence
KEY POINTS: Artificial intelligence models effectively generalized across studies and animal models and reduced translational gaps when applied to human biopsies. Artificial intelligence assistance reduced study evaluation turnaround times by up to 90% versus manual whole slide imaging scoring, matching expert-level performance. Self-supervised learning captured diabetic kidney disease-relevant features and mitigated expert-specific bias. BACKGROUND: Assessment of pathology end points in animal models of diabetic kidney disease is time-consuming and prone to expert bias. In addition, the sparsity of human kidney biopsy data hinders the development of translational models from animals to humans. METHODS: We developed an artificial intelligence (AI)-driven workflow to streamline histopathologic assessments in animal models of diabetic nephropathy. Our approach ( 1 ) detected glomeruli in whole slide images, ( 2 ) enabled fast expert scoring through an annotation tool, and ( 3 ) automated scoring. By leveraging unlabeled preclinical data for self-supervised learning, we enhanced AI scoring performance, reduced expert bias, and enabled the translation of AI scoring from animal models to human biopsies. To translate AI models from preclinical studies to human biopsies, we introduced a method that adjusted the feature extractor to human-specific features during inference without the need for annotated examples. RESULTS: Our annotation tool streamlined glomerular scoring, reducing turnaround time by 80%. Supervised AI models outperformed expert agreement and further reduced turnaround time by 90%, demonstrating generalization across studies involving both the same and different animal models. Without supervision, the self-supervised model achieved a κ value of 0.78, effectively identifying glomerular changes without guidance. Incorporating self-supervised learning into supervised training improved performance to κ=0.84 and reduced bias compared with individual experts ( P < 0.001). Our translational approach achieved a κ value of 0.63 on human glomeruli, although the model was trained exclusively on mouse glomeruli scores, reducing the translational gap by 45%. CONCLUSIONS: In this study, we accelerated and enhanced pathology readouts in a real-life pharmaceutical industry setting. We show that AI-assisted scoring reduced pathologists' workload and expedited study assessments. Self-supervised learning captured intrinsic properties of kidney morphology without expert annotation and reduced expert bias and translational discrepancies, greatly facilitating translational activities in drug development for patients with diabetic kidney disease.
5 May 2026
Read appraisal →Analytical methods : advancing methods and applications
Beyond identification: inferring physical activity from fingerprint lipids using machine learning.
Fingerprints are a widely recognized form of forensic evidence, valued for their ability to link individuals with specific locations. Traditional fingerprint analysis relies on optical imaging to identify a match in a fingerprint database; however, where no match is found, the evidential value of a latent print is limited. Here, we present the first study to integrate matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) with supervised machine learning to infer physical activity from fingerprint chemistry, expanding the utility of fingerprints beyond identification alone. Physical activity labels were derived from a validated questionnaire and converted into binary classes. Supervised machine learning algorithms were trained on the lipid features and evaluated against the survey-derived labels. The top-performing models were an ensemble algorithm based on multiple decision trees and a neural network, which classified physical activity with accuracies of 75 ± 8% and 73 ± 7%, respectively. These results demonstrate that fingerprint lipid chemistry encodes biologically meaningful information related to physical activity and establish a new approach for extracting lifestyle and behavioral indicators from trace evidence, with potential applications in forensic investigations and noninvasive fingerprint-based assessments in medicine.
4 May 2026
Read appraisal →Cytopathology : official journal of the British Society for Clinical Cytology
Application of Artificial Intelligence-Based Transfer Learning Models to the Bethesda System for Thyroid Cytopathology
BACKGROUND: The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) provides a standardised framework for thyroid fine needle aspiration cytology (FNAC). Deep learning approaches, particularly transfer learning, have shown potential for cytology but are rarely applied to TBSRTC categorisation. AIMS AND OBJECTIVES: To evaluate the performance of an ensemble soft voting transfer learning model in categorising thyroid cytology smears according to TBSRTC. MATERIALS AND METHODS: A retrospective study of 94 thyroid FNAC cases with 949 representative images was conducted. Six transfer learning models (Xception, ResNet50V2, DenseNet121, MobileNetV2, InceptionV3, EfficientNetB3) were combined using ensemble soft voting with a weighted average. Model performance was assessed using sensitivity, specificity, precision (PPV), negative predictive value (NPV), F1 score and area under the receiver operating characteristic curve (AUCROC). RESULTS: DenseNet121 achieved the highest overall sensitivity (0.91) and specificity (0.98) among all single models. The weighted ensemble model achieved an F1 score of 0.867, marginally below DenseNet121 but with superior precision (0.882) and NPV (0.968). AUCROC was highest in DenseNet 121 (0.99) followed by the weighted ensemble (0.98). CONCLUSION: This is the first study to apply ensemble transfer learning to TBSRTC categorisation. The approach demonstrated strong predictive accuracy, particularly for benign and malignant categories. Larger datasets, ideally with whole-slide imaging, are needed to further validate these findings.
4 May 2026
Read appraisal →Annals of surgical oncology
Computed Tomography-Pathology Deep Learning Model for the Precise Prediction of Recurrence in Pathological Stage IA Lung Adenocarcinoma
BACKGROUND: The postoperative prognosis of pathological stage IA lung adenocarcinoma (LUAD) exhibits significant heterogeneity. While the tumor node metastasis (TNM) staging system offers limited recurrence prediction capability, this study aims to develop a precise deep learning model for prognostic stratification. PATIENTS AND METHODS: We retrospectively analyzed a consecutive cohort of patients with pathological stage IA LUAD who underwent surgical resection at Zhongshan Hospital Fudan University. Our novel ResNet 3D-Pathology Fusion (Res3D-PF) model-integrating a three-dimensional ResNet backbone with an image-pathology fusion module-was developed to predict recurrence-free survival (RFS) using preoperative computed tomography (CT) images and International Association for the Study of Lung Cancer (IASLC) grading. Model performance was evaluated through receiver operating characteristic curve analysis, with independent RFS predictors identified via multivariable Cox regression. RESULTS: Among 551 patients with stage IA LUAD (median age 61 years; 339 women) divided into training (n = 368) and validation (n = 183) sets, the CT-pathology fusion model achieved superior predictive performance. In the validation cohort, Res3D-PF significantly outperformed the 8th T-stage (AUC 0.837 vs. 0.660, p = 0.001) and IASLC grade (AUC 0.837 vs. 0.684, p = 0.015) for 5-year RFS prediction. Multivariable analysis confirmed Res3D-PF as an independent prognostic factor (HR 15.772, 95% CI 3.384-73.508; p < 0.001). Model-stratified high-risk patients demonstrated significantly reduced 5-year RFS (73.1% vs. low-risk 98.5%, p < 0.001) and shorter median RFS (74.4 vs. 96.2 months, p < 0.001). CONCLUSIONS: We developed and validated a CT-pathology deep learning model that outperforms conventional TNM staging and IASLC grading for predicting postoperative recurrence in stage IA LUAD. This approach enables individualized risk stratification to guide precision treatment strategies.
4 May 2026
Read appraisal →Computer methods in biomechanics and biomedical engineering
Multiple instance learning method based on convolutional neural network and self-attention for early cancer detection.
Early cancer detection using T-cell receptor sequencing (TCR-seq) and multiple instances learning methods has shown significant effectiveness. We introduce a multiple instance learning method based on convolutional neural networks and self-attention (MICA). First, MICA preprocesses TCR-seq using word vectors and then extracts features using convolutional neural networks. Second, MICA uses an enhanced self-attention mechanism to extract relational features of instances. Finally, MICA can extract the crucial TCR-seq. After cross-validation, MICA achieves an area under the curve (AUC) of 0.911 and 0.946 on the lung and thyroid cancer datasets, which are 7.1% and 2.1% higher than other methods, respectively.
4 May 2026
Read appraisal →Radiology. Artificial intelligence
Radiopathomic Graph Deep Learning for Multiscale Spatial-Contextual Modeling of Intratumoral Heterogeneity to Predict Breast Cancer Response to Neoadjuvant Therapy
Purpose To develop an explainable radiopathomic graph deep learning (RPGDL) system for multiscale spatial-contextual modeling of intratumoral heterogeneity and evaluate its performance for the prediction of pathologic complete response (pCR) to neoadjuvant therapy in breast cancer. Materials and Methods The RPGDL system was developed from dual-center retrospective analysis of patients with biopsy-proven invasive breast cancer (May 2018-August 2024). For each tumor, individual radiomic and pathomic graphs were generated from pretherapeutic MRI and hematoxylin-eosin-stained biopsy slide images, respectively. These graphs were then processed by three distinct graph neural networks (GNNs): radiomic, pathomic, and radiopathomic. GNN performance was assessed with the area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), and integrated discrimination improvement (IDI). A multifaceted approach was used to explain the GNNs' predictions. Results The training set included 582 (mean age, 52 years ± 9 [SD]) patients and the external test set 468 (50 years ± 10) patients from centers 1 and 2, respectively. The radiomic GNN achieved AUCs of 0.89 (95% CI: 0.85, 0.93) in the training set and 0.84 (95% CI: 0.80, 0.89) in the external test set; the pathomic GNN achieved AUCs of 0.87 (95% CI: 0.83, 0.91) in the training set and 0.83 (95% CI: 0.78, 0.88) in the external test set, with no significant difference between them (P > .05). The radiopathomic GNN outperformed both single-modality GNNs (training set: AUC, 0.95 [95% CI: 0.92, 0.98]; external test set: AUC, 0.91 [95% CI: 0.87, 0.94]; P < .05; NRI and IDI confirmed). Pathomic graphs dominated probability increases for pCR predictions, while radiomic graphs drove probability decreases for non-pCR predictions. Multifaceted analyses verified GNNs' explainability. Conclusion The developed RPGDL system enabled multiscale spatial-contextual intratumoral heterogeneity modeling for high-performance, explainable prediction of pCR to neoadjuvant therapy in breast cancer. Keywords: Dynamic Contrast-enhanced MRI, Breast, Tumor Response, Radiology-Pathology Integration, Prognosis, Principal Component Analysis, Perception, Supervised Learning, Reconstruction Algorithm Supplemental material is available for this article. © RSNA, 2026.
4 May 2026
Read appraisal →European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology
Machine learning identifies a 10-gene signature predicting hepatocellular carcinoma recurrence and immune-metabolic reprogramming
BACKGROUND: Hepatocellular carcinoma (HCC) remains a major cause of cancer-related mortality, with frequent recurrence after curative treatment. Conventional clinicopathological prognostic systems fail to capture the molecular heterogeneity underlying recurrence, highlighting the need for biologically informed biomarkers. METHODS: We developed a transcriptome-based prognostic model for HCC recurrence using a machine learning-guided feature selection strategy designed to reduce survival-time bias. LASSO-based gene selection was integrated with multivariable Cox regression, and model performance was assessed through stratified cross-validation and independent external validation. RESULTS: Analysis of the TCGA-LIHC cohort (n = 344) identified a stable 38-gene recurrence-associated signature (AUC: 0.715-0.847), which was distilled into a reproducible 10-gene classifier combined with tumor stage. This integrated model effectively stratified patients into high- and low-risk groups (log-rank P < 0.0001) and was independently validated in the HCCDB25 cohort (n = 158; P = 0.031). High-risk tumors exhibited an immune-excluded phenotype with reduced cytotoxic immune infiltration. Gene set enrichment analyses revealed progressive activation of proliferative signaling, metabolic dysregulation, and immune evasion pathways. CONCLUSIONS: The integrated 10-gene-plus-stage classifier is a robust and generalizable predictor of HCC recurrence, providing mechanistic insights into immune-metabolic reprogramming and highlighting potential implications for risk-informed patient stratification in future studies.
4 May 2026
Read appraisal →Current allergy and asthma reports
Interception of Regulatory RNAs on TGF-β Signaling in the Pathogenesis of Idiopathic Pulmonary Fibrosis: A Systematic Review
PURPOSE OF REVIEW: Idiopathic Pulmonary Fibrosis is a type of interstitial lung disease characterized by lung scarring due to excessive extracellular matrix (ECM) deposition. The transforming growth factor-beta (TGF-β) signaling pathway is the master regulator of fibrosis, driving myofibroblast activation and differentiation, epithelial-mesenchymal transition (EMT), and inhibition of ECM degradation. While individual classes of non-coding RNAs (ncRNAs) have been studied in IPF, a comprehensive understanding of how microRNAs (miRNAs), circular RNAs (circRNAs), and long non-coding RNAs (LncRNAs) collectively regulate canonical TGF-β signaling remains lacking. Addressing this gap, this systematic review was conducted which presents current evidence on the integrated roles of ncRNAs in modulating TGF-β signaling in IPF pathogenesis. RECENT FINDINGS: A comprehensive search of PubMed and Web of Science databases (2015-2025), identified 45 eligible studies. miRNAs (19 antifibrotic, 11 profibrotic) directly targeted the core components of the TGF-β signaling pathway, whereas circRNAs (5 antifibrotic, 5 profibrotic) and LncRNAs (6 profibrotic) acted as competing endogenous RNAs and sponged their target miRNAs. Notably, all identified LncRNAs were profibrotic, amplifying the fibrotic signaling pathway. We found that ncRNAs critically fine-tune TGF-β signaling at multiple regulatory nodes, including ligand activation, receptor expression, Smad protein phosphorylation, nuclear translocation, and inhibitory feedback mechanism. The ncRNA-mediated regulatory mechanisms provide valuable insight into IPF pathogenesis and may help identify potential biomarkers and therapeutic targets. Future efforts should prioritize validating in vitro and animal model data in human samples, integrating regulatory network analysis, in vivo functional validation of RNA-based therapeutics, and exploring therapeutic delivery systems to develop an effective ncRNA-based antifibrotic therapy.
3 May 2026
Read appraisal →PloS one
Deep feature optimization using fusion of multiple self-supervised learning approaches and filter-based feature selection for lung cancer histopathology classification
One of the most deadly illnesses in the world is lung cancer, and increasing survival rates require early detection. Lung cancer diagnostics from the imaging modalities is always subjective, and this paves the way for deep learning assisted computer aided techniques. Still, the accuracy of such a technique is the major concern. This research work attempts to enhance lung cancer diagnostics from histopathological images using a previously unaddressed combination of multiple self-supervised learning techniques, filter-based feature selection, and Vision Graph Convolutional Networks. The main contribution lies in optimized feature fusion, and it brings complementary strengths of three different self-supervised learning approaches- contrastive alignment, redundancy reduction, and semantic grouping. The first step involves extracting the key features from histopathological images using a custom Convolutional Neural Network. Three complementary self-supervised learning methods - Deep Cluster, Bootstrap Your Own Latent, and Simple Framework for Contrastive Learning of Visual Representations - are then used to refine each of these features separately. Following optimization, the improved features are combined, and the most significant features from the combined set are found and preserved using a filter-based feature selection technique called Minimum Redundancy Maximum Relevance. Vision Graph Convolutional Neural Network is used as a classifier. Initial experiments are carried out on the 691 histopathological images extracted from the publicly available LungHist700 dataset. This dataset contains histopathological images under three categories: 151 normal subjects, 280 lung adenocarcinoma subjects, and 260 lung squamous cell carcinoma subjects. The proposed approach provided a balanced accuracy of 97% while the plain Vision Graph Convolution Neural Network offers only an 86% balanced accuracy score. Further validation is performed using two more publicly available datasets, namely LC25000 and TCGA UT datasets. The experimental results demonstrate the enhanced lung cancer prediction performance of the proposed approach in all three datasets.
2 May 2026
Read appraisal →Molecular neurobiology
Establishing a Diagnostic Model Based on Plasma CDR1as and Alpha-Synuclein for Mild Cognitive Impairment in Type 2 Diabetes
Emerging evidence implicates cerebellar degeneration-related protein 1 antisense transcript (CDR1as) and alpha-synuclein (α-Syn) in diabetes and cognitive decline, suggesting their potential to serve as biomarkers. This study aimed to evaluate their diagnostic efficacy for type 2 diabetes mellitus-associated mild cognitive impairment (T2DM-MCI) and establish a corresponding diagnostic model using machine learning. T2DM-MCI-associated differentially expressed genes were identified from the hippocampus using the Gene Expression Omnibus and predictive databases. The study involved 529 T2DM patients in two phases (training set = 408, test set = 121). Levels of plasma CDR1as, α-Syn, Aβ1-40/1-42, and ApoE genotype were detected. Three diagnostic models were identified using least absolute shrinkage and selection operator (LASSO) and logistic regression. Their performance was assessed using the area under the curve (AUC), net reclassification index (NRI), and integrated discrimination improvement (IDI). The best-performing model was selected from nine machine learning algorithms. Personalized risk assessment was achieved with the SHapley Additive exPlanations (SHAP). Bio-informatics analysis identified CDR1as and α-Syn as potential biomarkers. Their inclusion in multi-modal panels markedly improved diagnostic accuracy. The Random Forest (RF) model outperformed eight other machine learning classifiers (AUC = 0.975, 95% CI: 0.946-0.999) with the lowest Brier score (0.054). When evaluated on a test set, the RF model maintained robust performance (AUC = 0.901, accuracy = 0.850). An online diagnostic tool was established ( https://www.xsmartanalysis.com/model/list/predict/model/html?mid=6734&symbol=816GyBh9ag1Wr9367341 ). The study preliminarily identified CDR1as and α-Syn as promising biomarkers for T2DM-MCI. Integrating these markers with conventional blood tests showed potential clinical utility for improving diagnostic precision.
2 May 2026
Read appraisal →Biomedical physics & engineering express
BiFUSE-UNet: a novel dual-encoder enhanced TransUNet for polyp segmentation
Polyps are abnormal protrusions that develop on the mucosal surface of the human body, arising from hyperproliferation or aberrant differentiation of mucosal tissue. While some polyps carry a risk of malignant transformation, timely intervention can halt this progression. Accurately segmenting polyp contours in medical images poses significant challenges, primarily due to the high heterogeneity in polyp appearance and morphology, blurry boundaries with background interference, and class imbalance coupled with data scarcity. To address these challenges, this paper presents BiFuse-UNet, a novel dual-encoder TransUNet architecture built upon a bidirectional fusion mechanism. Building upon the original TransUNet architecture, BiFuse-UNet incorporates several key modules. Firstly, a multi-axis attention module (MaxViT block) is integrated to form a dual-encoder structure, which extracts multi-scale local textural features across different dimensions and captures long-range dependencies through self-attention. Secondly, a Merge fusion module is designed, incorporating a Coordinate Attention module and the SaE block from SENetV2, to enhance the model's perception of local and detailed features. Finally, a Biformer module is introduced to strike an efficient balance between global semantics and local details, thereby improving the segmentation accuracy for subtle polyps and early-stage polyps with atypical morphology. Extensive evaluations on the Kvasir-SEG and CVC-ClinicDB dataset demonstrate that BiFuse-UNet achieves state-of-the-art segmentation performance, outperforming seven existing methods on key metrics such as the Dice coefficient, Recall, Precision, and IoU. The proposed model effectively mitigates the challenges of morphological heterogeneity, blurry boundaries, and background interference, leading to highly accurate pixel-level segmentation.
27 Apr 2026
Read appraisal →ACS sensors
Nanobiosensors and Artificial Intelligence Strategies for Glycan Profiling in Cancer Progression: A Critical Review
Glycans are complex carbohydrates that are integral to cancer progression and tumor biology. Conventional methods face challenges due to the structural diversity and low abundance of glycans, limiting the detection of cancer-associated glycan signatures. This bottleneck hampers the accurate monitoring of cancer progression and the development of effective diagnostic tools. Nanobiosensor-enabled glycan profiling overcomes conventional limitations by providing highly sensitive detection of low-abundance glycans and precise discrimination of similar forms through nanoscale electrochemical or optical signal amplification and selective biorecognition. This review evaluates emerging nanobiosensors, including optical modalities such as surface plasmon resonance, localized surface plasmon resonance, surface-enhanced Raman scattering, fluorescence, and colorimetric nanobiosensors. It also covers electrochemical systems, including impedimetric, voltammetric, and amperometric sensors that use nanomaterials to enhance the sensitivity, specificity, and reliability of glycan detection. After a critical evaluation of nanobiosensors, this review highlights their applications for glycan analysis in cancer progression and potential of miniaturized point-of-care platforms. In parallel, this review highlights emerging artificial intelligence (AI) and machine learning (ML) approaches that are being explored to analyse complex biosensor outputs. By enabling multivariate pattern recognition, dimensionality reduction, and nonlinear modeling of biosensor responses, these computational frameworks may facilitate the extraction of diagnostically relevant signatures from high-dimensional optical and electrochemical datasets. The review identifies challenges in standardization and clinical scalability of nanobiosensors and explores future directions, including AI integration to advance early cancer detection and personalized patient management.
27 Apr 2026
Read appraisal →Lab on a chip
MaGIC-OT: an AI-guided optical tweezers platform for autonomous single-cell isolation in microfluidic devices
Automating the isolation of rare cells such as circulating tumour cells (CTCs) within crowded microfluidic environments remains a bottleneck in liquid biopsy workflows. Optical tweezers offer contact-free, selective manipulation but traditionally rely on expert operators. We present MaGIC-OT (machine-guided isolation of cells using optical tweezers), a platform that integrates classical path planning and deep reinforcement learning (DRL) to automate single-cell manipulation inside a microfluidic chip. We built a high-fidelity simulation to train and benchmark control policies and show that cooperative, human-in-the-loop training improves DRL performance. Trained agents outperform expert users in speed and isolation success in silico, and we demonstrate proof-of-concept isolation of a cancer cell from a spiked blood sample on-chip. MaGIC-OT provides a flexible framework for intelligent optical manipulation, aligning microfluidic device design with autonomous control strategies and offering a pathway toward high-purity, label-free single-cell workflows.
26 Apr 2026
Read appraisal →The British journal of ophthalmology
Incidental ocular surface squamous neoplasia in pterygia: a systematic review and meta-analysis
AIMS: Differentiating pterygium from ocular surface squamous neoplasia (OSSN) is important for guiding management. This meta-analysis evaluates the prevalence and risk factors for incidental OSSN in clinically diagnosed pterygia. METHODS: Ovid Embase, MEDLINE, Cochrane Library and Web of Science were systematically searched from January 2000 to February 2025. Included studies analysed ≥100 clinically diagnosed pterygia via histopathology. Random-effects meta-analysis assessed the prevalence of incidental OSSN among pterygia. Risk factors were evaluated using the Mantel-Haenszel and inverse variance methods, and meta-regression analysed the influence of publication year, geographic proximity to the equator, and country-level ultraviolet (UV) radiation exposure. RESULTS: 12 studies, comprising 8688 specimens, identified 202 cases of incidental OSSN (pooled prevalence=1.32%, 95% CI 0.41% to 4.21%, I2=95.3%). Meta-regression revealed that lower OSSN prevalence was associated with greater distance from the equator (OR 0.49, 95% CI 0.28 to 0.83, p<0.01), while higher prevalence was associated with greater UV exposure (OR 2.20, 95% CI 1.17 to 4.14, p=0.01). Publication year had no effect (p=0.98). Age (p=0.18), sex (p=0.45) and lesion location (p=0.60-0.82) did not differ between incidental OSSN cases and benign pterygia. Incidental OSSN prevalence also did not differ between primary and recurrent pterygia (p=0.23). Regional analyses revealed variation in prevalence: Europe (0.29%), Asia (0.76%), North America (1.03%), Oceania (8.57%) and South America (14.97%). CONCLUSIONS: This meta-analysis, based on low- to very low-certainty evidence, identified a 1.32% pooled prevalence of incidental OSSN in clinically diagnosed pterygia, highlighting the potential influence of UV exposure and equatorial proximity. The overlap in demographic and lesion characteristics between benign pterygia and OSSN underscores diagnostic challenges.
25 Apr 2026
Read appraisal →Cell reports. Medicine
A metabolite-augmented FIB-4 machine learning panel achieves superior liver fibrosis staging in chronic liver disease
Accurate, non-invasive liver fibrosis detection is essential for chronic liver disease management, particularly with rising metabolic dysfunction-associated liver disease (MASLD) and chronic hepatitis B (CHB). While the Fibrosis-4 (FIB-4) index is widely used, its performance for advanced fibrosis is limited. We develop Met-FIB using metabolomics and machine learning, integrating FIB-4 parameters (age, aspartate aminotransferase, alanine aminotransferase, and platelet count) with tyrosine and taurocholic acid identified in a CHB discovery cohort (n = 3,251). Validation includes one CHB cohort (n = 729) and two MASLD cohorts (n = 149, n = 155). Met-FIB outperforms FIB-4, FibroScan, and other serum markers across all fibrosis stages. In CHB, Met-FIB achieves 96.3% rule-out sensitivity and 85.4% rule-in specificity for significant fibrosis, with rule-in specificity reaching 98.6% and 98.8% for advanced fibrosis and cirrhosis. In MASLD, corresponding values are 93.9% and 90.2% for significant fibrosis, with >97.9% specificity for late-stage disease. Met-FIB demonstrates clinical utility for non-invasive fibrosis staging across diverse etiologies.
25 Apr 2026
Read appraisal →Human mutation
HSPB6: A Potential Prognostic Biomarker, Inhibiting the Epithelial-Mesenchymal Transition (EMT) Process Through the PI3K/Akt Signaling Pathway Based on the Machine Learning and Experimental Validation
Bladder cancer (BC) is a prevalent malignant tumor worldwide, posing a significant public health burden and challenge to human society. Current therapeutic modalities for BC include surgical treatment, radiotherapy, chemotherapy, targeted therapy, and immunosuppressive therapy. However, almost all patients experience disease progression and ultimately succumb to BC. Our study demonstrated that elevated expression of Heat Shock Protein Beta-6 (HSPB6) correlated with higher clinical grades and stages, establishing it as an independent prognostic risk factor for BC. Enrichment analysis indicated that HSPB6 is associated with the extracellular matrix in BC. Experimental validation revealed that HSPB6 overexpression inhibits the proliferation of BC cell line T24. This effect may be achieved by inhibiting the PI3K/Akt signaling pathway, which in turn leads to inhibition of epithelial-mesenchymal transition (EMT). Furthermore, we developed a prognostic risk model that incorporated DDR2, DPYSL3, MFAP5, PDGFRB, and SPOCD1, allowing accurate prediction of patient outcomes based on immunological status. In conclusion, this study highlights that HSPB6 overexpression can restrain the proliferation of BC cells and inhibit EMT, underscoring its potential as a diagnostic marker and therapeutic target in BC.
23 Apr 2026
Read appraisal →ACS applied materials & interfaces
Flexible, Scalable SERS Substrate with High Sensitivity and Stability for On-Site Detection and Wearable Applications
A key challenge in the commercialization of surface-enhanced Raman scattering (SERS) technology is the scalable and controllable preparation of substrates that simultaneously achieve high sensitivity, uniform signal distribution, excellent reproducibility, and long-term stability. In this study, we report a flexible SERS substrate based on a porous, high-surface-energy nanofilm, designed to serve as a spatially confined template for the uniform growth of silver nanoparticles (AgNPs). This substrate exhibits outstanding SERS performance with an enhancement factor (EF) of 2.05 × 1010 and a detection limit (DL) as low as 1.74 × 10-15 M for rhodamine 6G (R6G). The preparation process is mild, highly reproducible (RSD = 8.53% over 60 consecutive batches), and scalable to 25 cm2 areas. Moreover, the substrate maintains its SERS activity for over three months within a vacuum bag at room temperature. Owing to its excellent adhesion and good flexibility, the substrate can adhere effectively to complex surfaces. The substrate was successfully applied to sensitive in situ detection of trace thiram residues on grape surfaces, achieving a detection limit (DL) of 8.51 × 10-10 g cm-2. Additionally, a wearable sensor was developed based on the substrate and used for the noninvasive monitoring of uric acid levels in human sweat, with a DL of 2.95 × 10-7 M. This work provides a practical strategy for constructing high-performance, scalable, and flexible SERS substrates, advancing their potential for real-time, on-site analysis.
23 Apr 2026
Read appraisal →The Journal of clinical endocrinology and metabolism
An Interpretable Machine-Learning Model for Predicting Occult Central Lymph Node Metastasis in Papillary Thyroid Cancer
CONTEXT: Accurate preoperative prediction of occult lymph node metastasis (OLNM) in clinically lymph node negative (cN0) papillary thyroid carcinoma (PTC) is critical for optimizing therapeutic strategy, particularly for thermal ablation and active surveillance. OBJECTIVE: The aim of this study was to develop an interpretable machine-learning (ML) model to predict the risk of OLNM in cN0 PTC patients. METHODS: This retrospective study analyzed data of 961 cN0 PTC patients (August 2018-August 2023). Multivariable logistic regression identified independent risk factors for OLNM in cN0 PTC. The cohort was randomly divided into the training and test sets, and a subset of patients with tumors sized 1 cm or less was further extracted from the test set for internal validation. Eight ML models incorporating clinical, ultrasonographic, and molecular features were developed and evaluated. Shapley Additive exPlanations (SHAP) enhanced interpretability. RESULTS: RET fusion positivity and BRAF mutation positivity were identified as independent molecular risk factors for OLNM in cN0 PTC, alongside 6 clinical and ultrasonographic variables. Nine predictors were incorporated into the predictive model. The random forest (RF) model achieved optimal performance with an area under the curve (AUC) of 0.906 in the training set and 0.733 in the test set, along with the lowest Brier scores of 0.135 and 0.212, respectively. Analysis of tumors sized 1 cm or less internally validated the model's robustness with an AUC of 0.719. SHAP analysis identified size, age, and clustered punctate echogenic foci as the top predictors. CONCLUSION: This is the first study to identify RET fusion positivity as an independent OLNM risk factor in cN0 PTC. The developed RF model demonstrates moderate predictive performance for OLNM risk and provides a framework for integrating clinical, sonographic, and molecular data, and is deployed as a web calculator (https://predictingoccultlymphnodemetastasis.shinyapps.io/web3/).
23 Apr 2026
Read appraisal →Analytical chemistry
scAClc: A Multi-Objective Adaptive Clustering Framework for Single-Cell Transcriptomics via Contrastive and Resolution-Aware Representation Learning
Single-cell RNA sequencing (scRNA-seq) enables whole-transcriptomic profiling at single-cell resolution, facilitating the construction of virtual cell representations that capture the full spectrum of cellular identities. Realizing this goal hinges on accurate clustering, which remains challenging due to data sparsity, high dimensionality, noise, and the need to specify cluster numbers a priori. We propose scAClc, a novel clustering framework featuring multiobjective optimization and adaptive resolution discovery, designed to address these limitations through three key innovations. First, a Hierarchical Gene Relevance Module integrates global gene variability with local neighborhood-specific signals to eliminate redundancy while retaining biologically informative features. Second, an Anchor-Centered Contrastive Learning Module adaptively selects representative anchors to guide embedding learning, promoting compact intracluster structure and clear intercluster separation. Third, based on the robust low-dimensional embedding, we propose a Self-Adaptive Resolution Discovery Module to automatically infer the number of clusters by jointly modeling intra- and intercluster distances. Extensive experiments on 15 real scRNA-seq data sets demonstrate that scAClc consistently outperforms six state-of-the-art methods across multiple evaluation metrics. Ablation studies further confirmed the complementary contributions of each module. In addition, interpretability analysis effectively mitigates the "black box" nature of clustering models and sheds light on the biological mechanisms underlying cell clustering. The source code is publicly available at https://github.com/scAClc/scAClc.
23 Apr 2026
Read appraisal →Journal of medical genetics
Clinically significant DNA variation from the GENCOV and HostSeq COVID-19 genome sequencing studies
BACKGROUND: Vast amounts of genome sequencing data generated from large-scale research studies like HostSeq provide an opportunity to summarise the spectrum of pathogenic variation in a subset of the Canadian population. Sharing variant-level data with public databases, like ClinVar, is crucial for advancing our understanding of genomic variants related to Mendelian diseases. However, such entries are often incomplete or contain discrepancies which render interpretation and classifications less useful. METHODS: The GENCOV and HostSeq cohorts were annotated and summarised using custom workflows to identify variants with a pathogenic and likely pathogenic (P/LP) classification in ClinVar. These variants were further filtered using custom gene panels, gnomAD frequency, variant type, gene-disease relationship and the number of reputable ClinVar laboratory submissions. Manually assessed variants from the GENCOV study were compared with ClinVar classifications to identify discrepancies. RESULTS: A total of 1956 unique variants were manually classified as P/LP through the GENCOV study. Of these, 65% (1276) were also identified in ClinVar, and among those, 69% (889) had concordant P/LP classifications. The manual assessment of unique exonic variants in GENCOV yielded a higher number of putative P/LP variants (1595), including truncating and missense variants compared with the 127 unique exonic P/LP variants in HostSeq. CONCLUSION: These results highlight that a large proportion of P/LP variation is either absent or has conflicting evidence for pathogenicity in ClinVar, emphasising the importance of periodic reassessment, discrepancy resolution and updates to ensure completeness and accuracy of public databases.
23 Apr 2026
Read appraisal →The Analyst
Third-generation nanopore sequencing: advancing real-time pathogen detection and antimicrobial resistance surveillance in food safety applications
Foodborne diseases impact 600 million people annually, causing 420 000 deaths and over $110 billion in economic losses. Conventional pathogen detection methods take 3-7 days and lack sensitivity for low-abundance pathogens and antimicrobial resistance (AMR) genes. This review evaluates nanopore sequencing's potential in food microbiology, analyzing real-time pathogen detection, AMR surveillance, and performance versus traditional methods. A systematic review of 80 studies (2015-2025) revealed nanopore sequencing reduces detection time to <24 hours with 95-98% species identification accuracy and >90% AMR gene sensitivity, at $50-200 per sample versus $300-800 for traditional whole-genome sequencing. It enables multiplex pathogen detection, viable but non-culturable organism identification, and real-time AMR profiling. However, challenges include error rates of 8-15% in homopolymeric regions and the need for bioinformatics expertise. Addressing challenges, including error rates of 8-15% in homopolymeric regions and the need for bioinformatics expertise, requires strategic mitigation approaches. Despite limitations, advances in base-calling and workflows make nanopore sequencing a transformative tool for next-generation food safety surveillance.
23 Apr 2026
Read appraisal →Annals of medicine
Comparative evaluation of oxidative stress biomarkers F2-isoprostanes and 8-OHdG in Parkinson's disease and Type 2 Diabetes Mellitus: a systematic review and meta-analysis of human studies
BACKGROUND: Oxidative stress is central to type 2 diabetes mellitus (T2DM) and Parkinson's disease (PD). However, the utility of biomarkers for lipid peroxidation (F2-isoprostanes) and DNA damage (8-OHdG) in the comorbidity of PD and T2DM remains unclear. METHODS: We conducted a systematic review and meta-analysis of 54 unique studies of human subjects aged ≥ 50 years (n = 7,521: 3,522 with T2DM, 722 with PD, and 3,277 controls), measuring biomarkers in serum, plasma, or leukocytes. Mixed-effects models quantified standardized differences (Hedges' g) across subgroups. RESULTS: In T2DM, F2-isoprostanes (g = 1.60, 95% CI: 0.95-2.25) and 8-OHdG (g = 2.64, 95% CI: 2.13-3.14) were markedly elevated (p < 0.001). Stronger effects were observed in younger cohorts and serum/plasma samples, with complications like nephropathy exhibiting extreme oxidative stress (g = 5.24). In PD, 8-OHdG was moderately elevated (g = 0.78, 95% CI: 0.18-1.39; p = 0.011), particularly in randomized controlled trials and plasma samples, whereas F2-isoprostanes were not significantly elevated (g = 0.47, 95% CI: -0.43-1.38). High heterogeneity in T2DM (I2 > 90%) reflected methodological variability. CONCLUSION: Distinct profiles - both markers elevated in T2DM but only 8-OHdG in PD - underscore 8-OHdG's potential in PD-T2DM comorbidity. Future research should focus on standardized assays, multi-compartmental or multi-modal sampling, and longitudinal studies to clarify mechanisms and therapeutic targets.
21 Apr 2026
Read appraisal →Chemical Society reviews
Machine learning-driven molecular engineering of nucleic acids
Molecular engineering has played a pivotal role in biomedical fields, driving significant advancements in gene therapy, disease diagnosis, and biosensing. However, nucleic acid molecular engineering faces various challenges including vast design spaces, complex structure-function relationships, lengthy application validation cycles, and inefficient optimization processes. Machine learning (ML), with its superior pattern recognition, multidimensional data integration, and automated optimization capabilities, offers a unique opportunity to construct predictive models of sequence-structure-function relationships, thereby enabling a paradigm shift from empirically driven to data-driven approaches. This review systematically surveys recent progress in ML applications across three major domains: nucleic acid structure construction, performance modulation, and application expansion. It also explores core challenges such as data quality, model interpretability, and experimental validation efficiency, along with potential resolution strategies. These insights are poised to propel nucleic acid molecular engineering from static structure prediction toward dynamic behavior simulation, and from single-molecule design to complex system engineering, guiding future directions in hybrid ML-quantum models and expanded applications to non-canonical nucleic acids for transformative innovation in biomedicine, environmental monitoring, and information technology.
20 Apr 2026
Read appraisal →Oncology reports
Incorporating artificial intelligence into morphological diagnosis of acute leukemias: Current landscape, challenges and prospects (Review)
Acute leukemias (ALs) are a diverse group of hematological malignancies characterized by the abnormal proliferation of immature cells. Microscopic observation of cell morphology based on the French‑American‑British classification remains a fundamental diagnostic method for ALs. However, manual screening from bone marrow smear images is often inefficient, laborious and prone to subjective bias, leading to potential misdiagnosis or missed diagnosis. Artificial intelligence (AI), particularly machine learning (ML), has expanded human capabilities in analyzing complex datasets, leading to breakthroughs in multiple fields, including medical research and clinical practice. Increasingly, ML applications are being developed to diagnose hematological diseases by extracting and aggregating morphological characteristics from peripheral blood and bone marrow smears. However, applying ML methods to recognize cell morphology in hematological diseases presents unique challenges compared with other pathology subspecialties. The present review provided an overview of AI and ML applications in ALs diagnosis, focusing on cell segmentation and data mining methods from microscopy images, and highlights their advantages over manual microscopy.
18 Apr 2026
Read appraisal →Breast cancer research and treatment
Oral selective estrogen receptor degraders in hormone receptor-positive, HER2-negative advanced breast cancer: a systematic review and meta-analysis
PURPOSE: The development of endocrine resistance is frequent in hormone receptor-positive, HER2-negative advanced breast cancer (HR + /HER2-ABC), particularly after CDK4/6 inhibitor exposure. Next-generation oral selective estrogen receptor degraders (SERDs) have been developed to improve estrogen receptor blockade; however, randomized trials have yielded heterogeneous results with uncertain clinical benefit. METHODS: A PRISMA 2020 compliant systematic review and meta-analysis with PROSPERO registration was conducted. PubMed, Embase, and Cochrane CENTRAL were searched through October 2025 for phase II-III randomized trials comparing oral SERDs with standard endocrine therapy (ET) in HR + /HER2-ABC after prior ET. The primary endpoint was progression-free survival (PFS); secondary endpoints included overall survival (OS), objective response rate (ORR), and treatment-related adverse events (TRAEs). Treatment effects were pooled using random effects models with prespecified subgroup analyses by ESR1 mutation status and key clinical characteristics. RESULTS: Six randomized trials, including 2808 patients, were analyzed. Oral SERDs improved PFS versus standard ET in the overall population (hazard ratio [HR] 0.79; 95% confidence interval [CI] 0.70 to 0.89). ORR was higher with oral SERDs (odds ratio [OR] 1.67; 95% CI 1.23 to 2.28), corresponding to absolute response rates of approximately 21% versus 14%. An OS improvement was observed (HR 0.72; 95% CI 0.57 to 0.90), although follow-up was limited. Benefit was concentrated in ESR1-mutated tumors (PFS, HR 0.57; 95% CI 0.48 to 0.67) with no significant PFS advantage in ESR1 wild-type disease. Gastrointestinal adverse events were more frequent with oral SERDs compared with the control ET. CONCLUSIONS: Pooled randomized evidence supports a clinically meaningful benefit of oral SERDs over standard ET after endocrine progression in HR + /HER2-ABC, with the strongest and most consistent efficacy observed in ESR1-mutated disease.
18 Apr 2026
Read appraisal →JMIR formative research
Artificial Intelligence Design for Race-Based Prostate Cancer Stage Classification With Multilayer Perceptron: Feature Selection Optimization Approach
BACKGROUND: Prostate cancer progression exhibits significant variability influenced by biological and racial factors. DNA methylation profiling has shown potential in early cancer detection, but its integration with machine learning across racially diverse populations remains limited. OBJECTIVE: This study aimed to develop a prostate cancer stage classifier for the majority White cohort using DNA methylation data and a multilayer perceptron (MLP) model in order to classify prostate cancer stages into early (stages I-II) and late (stages III-IV) stages and assess its performance when applied to other racial groups to highlight the need for race-specific models. METHODS: Methylation and phenotype data from the TCGA-PRAD (The Cancer Genome Atlas Prostate Adenocarcinoma) dataset were processed using differentially methylated position (DMP) analysis to identify CpG sites correlated with cancer stages. These features were further refined through recursive feature elimination (RFE) and used to train MLP models. Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) were used to interpret the model and identify key DNA methylation features contributing to model predictions. RESULTS: The best-performing model achieved 95% accuracy and up to 99% area under the curve on the majority race (White) training data using 90 selected features. However, performance declined sharply in racial minority groups, revealing the effects of sample imbalance and race-specific methylation patterns. Feature importance examination indicated strong patterns within certain CpG sites driving model predictions. CONCLUSIONS: We propose a race-aware MLP model for prostate cancer stage classification using DNA methylation data, which has been optimized through DMP and RFE-based feature selection. SHAP and LIME confirmed the predictive relevance of selected CpG sites, supporting model transparency. The results highlight high performance within the White cohort but reveal poor generalization to racial minority groups, emphasizing the importance of race-specific modeling strategies.
17 Apr 2026
Read appraisal →Science advances
Enhancing biomedical optical volumetric imaging via self-supervised orthogonal learning
Optical volumetric imaging grapples with inherent noise problems arising from photon budget constraints, light scattering, and space-bandwidth product bottlenecks, all of which degrade structural fidelity and become even more pronounced than in planar imaging. While deep learning presents potential for denoising, supervised methods are hindered by the impracticality of paired datasets, and existing self-supervised approaches fail to fully exploit the intrinsic volumetric structural redundancy inherent to optical imaging. Here, we present a self-supervised volumetric biomedical imaging denoiser (VALID) that leverages intrinsic three-dimensional spatial coherence for highly efficient volumetric denoising through a self-supervised orthogonal learning framework. VALID demonstrates robust denoising performance across diverse imaging modalities, including two- and three-photon microscopy, light-field microscopy, and optical coherence tomography, substantially enhancing structural fidelity in deep-tissue, multimodal, and dynamic imaging scenarios. By combining computational efficiency with zero-shot adaptability, VALID establishes a transformative approach to volumetric image enhancement with structure-aware precision.
16 Apr 2026
Read appraisal →Computers in biology and medicine
Deep learning with limited data: a transfer learning approach for transcriptomic survival prediction
BACKGROUND: Deep neural networks (DNNs) are promising for analyzing high-dimensional transcriptomic data in cancer research but are limited by data scarcity and heterogeneity. Transfer learning (TL), which leverages large datasets to improve performance on smaller ones, has been widely applied in classification and clustering, yet its use in survival prediction remains underexplored. METHODS: We evaluated transfer learning for disease-free survival prediction using RNA-seq data from 7509 patients across 27 tumor types from The Cancer Genome Atlas. A pan-cancer DNN was optimized via random search across 750 configurations. Tumor-specific baseline models were trained independently, while transfer learning models were built with a leave-one-out pre-training strategy followed by fine-tuning on the target tumor. Performance was assessed with the concordance index. Biological relevance was evaluated through a LIME-like interpretability approach and gene-set enrichment analysis. RESULTS: Transfer learning outperformed tumor-specific baselines in 24 of 27 tumor types, with the greatest improvements in smaller cohorts. Fine-tuning consistently enhanced predictions by adapting pan-cancer features to tumor-specific data. Enrichment analysis confirmed that the models captured both general oncogenic mechanisms and tumor-specific pathways. CONCLUSIONS: Transfer learning improves survival prediction from transcriptomic data, especially in small cohorts, by exploiting molecular patterns shared across cancers. These findings support transfer learning as a robust strategy for survival modeling and a step toward foundation models in molecular oncology.
16 Apr 2026
Read appraisal →International immunopharmacology
CXCL9 as a key feature for deep learning-based immune subtyping and prediction of immune checkpoint blockade response in triple-negative breast cancer
BACKGROUND: Immune checkpoint blockade (ICB) therapy has provided a promising treatment option for patients with triple-negative breast cancer (TNBC). However, existing efficacy prediction strategies based on programmed death-ligand 1 (PD-L1) expression and Tumor Mutational Burden (TMB) have significant limitations, leading to inaccurate patient selection. METHODS: This study integrated multi-omics data obtained from GEO, TCGA, and GTEx datasets. Based on ComBat correction results, two deep learning-driven unsupervised clustering methods were constructed to identify potential immune subtypes. These identified TNBC subtypes were subjected to comprehensive bioinformatics analyses to investigate their differences in overall survival, immune cell infiltration, and functional enrichment analysis, which clarified the biological rationale of the proposed classification. Subsequently, differential expression analysis (DEA) and multiple machine learning algorithms were applied to identify subtype-specific features, with the expression and differentiation status of the key feature in immune cells further validated using single-cell sequencing (scRNA-seq). Finally, co-expression networks at multiple cellular levels were constructed to predict the co-expressed regulatory targets of the key feature, and the hypothesized regulatory mechanism was preliminarily validated in in vitro experiments (qRT-PCR, western blotting, immunofluorescence, and ELISA). RESULTS: After 5-fold cross-validation, the AE-K-means clustering method classified TNBC into three distinct latent subtypes. This algorithm exhibited superior classification efficacy compared with the other models (including NMF, ConsensusClusterPlus and VAE-GMM), as demonstrated by markedly elevated Silhouette Coefficients (training: 0.585 ± 0.030; test: 0.698 ± 0.103; validation: 0.611) and substantially reduced Davies-Bouldin Index values (training: 0.623 ± 0.032; test: 0.385 ± 0.218; validation: 0.558) at K = 3. These three identified TNBC subtypes displayed significant differences in overall survival and exhibited pronounced immune heterogeneity. Specifically, the K2 subtype was characterized by high PD-L1 expression and abundant M1 macrophage infiltration, while the K3 subtype displayed an opposing, immunosuppressive microenvironment. Feature selection results from multiple machine learning models were intersected to identify key features including CXCL9, and an RF model constructed based on these intersected genes showed high efficacy, particularly in distinguishing the K2 and K3 subtypes (AUC = 0.941). Further scRNA-seq analysis revealed that CXCL9 was specifically highly expressed in myeloid cells, and the proportion of CXCL9+ macrophages differed significantly between responders and non-responders. Given the strong positive correlation between CXCL9 and IDO1 expression, we subsequently treated macrophages with IDO1 inhibitors and observed a marked upregulation in both the expression and secretion of CXCL9, suggesting that IDO1 overexpression in macrophages may represent a potential mechanism underlying CXCL9 exhaustion in the tumor microenvironment. CONCLUSIONS: Our study developed a novel immune classification system for TNBC, identifying CXCL9 as a key biomarker positively correlated with ICB response and regulated by IDO1. These findings provide a basis for precision immunotherapy in TNBC and support the exploration of IDO1 inhibitors in combination with ICB.
15 Apr 2026
Read appraisal →International immunopharmacology
Machine learning derived proliferating T cell-related signature: a novel biomarker for prognosis and treatment efficacy in clear cell renal cell carcinoma
BACKGROUND: Clear cell renal cell carcinoma (ccRCC) exhibits profound molecular heterogeneity, and reliable biomarkers for predicting clinical outcomes are urgently needed. Proliferating T cells (Tprolif) are central to immune system activation but their related signatures in predicting prognosis and therapeutic effect of ccRCC patients remains unexplored. METHODS: We developed a Tprolif-related RCC score (TRRS) using an integrative machine learning framework. Transcriptomic data from the CheckMate025 trial formed the discovery cohort. The model was validated across multiple independent cohorts, including IMmotion151, JAVELIN Renal 101, TCGA-KIRC, and West China Hospital (WCH) cohort from our center. Multi-omics analyses, including spatial and single-cell transcriptomics, were employed to investigate the associated biology and identify key mediators. RESULTS: The final TRRS model, built from 7 genes, demonstrated robust performance in stratifying patients for overall survival (OS) and progression-free survival (PFS) in training and all validation sets. TRRS was a powerful predictor of improved outcomes not only for immune checkpoint inhibitor (ICI) monotherapy but also for ICI-based combination therapy and targeted therapies. Biologically, a high TRRS was associated with aggressive tumor hallmarks, a distinct metabolic profile favoring aerobic glycolysis and glutamine metabolism, and an immunosuppressive tumor microenvironment despite high immune cell infiltration based on WCH cohort transcriptome expression profile. Through multi-omics screening, we identified CST3 as a key target, with spatial and single-cell analyses confirming its role in promoting tumor malignancy and enhancing cell-cell communication among microenvironment components. CONCLUSION: The TRRS is a novel, validated biomarker that effectively predicts prognosis and therapeutic responses in advanced ccRCC. It reflects critical biological features of tumor aggressiveness and immune evasion, with CST3 emerging as a potential central mediator and therapeutic target.
15 Apr 2026
Read appraisal →ACS nano
Deep Learning Enables Pixel-Level Nanoparticle Distribution Mapping in Routine Histological Sections by Integrating Cancer Associated Fibroblasts Features
The efficient accumulation and uniform distribution of nanomedicine within tumors are critical for achieving therapeutic outcomes. However, conventional medical imaging technologies struggle to efficiently and accurately detect nanoparticles (NPs) distribution, especially in resolving their cellular-level spatial heterogeneity. Existing deep-learning-based predictive models focus on tumor cell density and vascular distribution but do not address the complex spatial relationship between cancer-associated fibroblasts (CAFs) and drug distribution. This study presents NanoNet, a deep-learning framework that leverages fibroblast activation protein (FAP) immunostaining to spatially characterize CAFs and predict NPs distribution at high resolution. NanoNet achieved high predictive accuracy (ICC = 0.963, R2 = 0.9849) by transforming tumor section images into pixel-level NPs distribution maps. The FAP channel contributed substantially to predictive accuracy, indicating its important role in guiding NPs behavior. This study provides a spatially resolved predictive framework that enables pixel-level predictions of NPs distribution from conventional histological sections, with potential applications for optimizing nanomedicine design and personalized nanomedicine.
15 Apr 2026
Read appraisal →Epigenetics
The role of R-loops-mediated epigenetic regulation in genome stability maintenance and disease pathogenesis: a systematic review.
This systematic review synthesizes current evidence linking R-loops - associated processes with epigenetic regulation, genome stability, and human disease, integrating findings across DNA/RNA/protein modifications and 3D genome organization, and highlighting key mechanistic and technical gaps relevant to future studies, including longer-term translational exploration. Following PRISMA guidelines (Registration No.: INPLASY202560055), PubMed and ScienceDirect databases were searched through 18 January 2026. Two independent reviewers conducted blinded screening via the Rayyan platform. From 1290 initial articles, 71 studies met inclusion criteria. Methodological rigour was assessed using a modified SYRCLE risk-of-bias tool. Thematic synthesis identifies R-loops as recurrent intermediates linking transcription, chromatin regulation, and genome maintenance; feedback-like relationships are reported in selected systems. They spatially impede DNMTs to sustain promoter hypomethylation while recruiting TET enzymes for demethylation, and RNA modifications (e.g. m5C/m6A) may tune hybrid stability and, in some contexts, influence effector recruitment. R-loops facilitate the recruitment of histone-modifying complexes (PRC1/PRC2, G9a/GLP), thereby influencing chromatin landscapes and 3D genome architecture - including associations with TAD boundary insulation and with LLPS-related repair compartments in specific contexts. Dysregulation of R-loop homeostasis links to disease-related epigenetic alterations and genome instability with distinct disease-, locus- and cell-state specificity, and its context-dependent roles in diverse disorders involve transcriptional silencing, DNA damage, replication-transcription conflicts, repair pathways, chromatin regulation and mitochondrial genome maintenance. Integrating DRIP-seq with epigenomic profiling and functional tests supports mapping of context-specific relationships.
14 Apr 2026
Read appraisal →Molecular biomedicine
Machine learning integrated clinical-proteomics data identifies a 6-protein panel signature for atherosclerotic severity and enhanced patient stratification
Atherosclerosis, a major cause of adverse cardiovascular events and mortality rates worldwide, stems from sustained lipid accumulation and subsequent chronic inflammation within the arterial walls. An early identification of patients at risk is crucial to prevent life-threatening thrombotic events and provide effective and personalized treatments. Leveraging the power of machine learning (ML) to enhance diagnostics and biomarker discovery, we applied a high-throughput approach using five ML classification algorithms (MLCA), integrating clinical and serum proteomic data from patients with carotid atherosclerotic stenosis (AT, n:60), dyslipidemic patients (DLP, n:55), and healthy controls (HC, n:66). As a result, a robust 6-protein panel (B2M, GPV, MMP9, PLF4, TSP1, and FB isoforms) was identified with a ROC-AUC value > 0.9 for all algorithms applied, highly discriminating AT patients compared to DLP or CTRL. The levels of these proteins were further validated in an independent external cohort, including patients presenting with acute atherothrombotic stroke, corroborating the potential of this panel as biomarker for atherosclerosis severity. In addition, the combined clinical-proteomic ML approach provided a more accurate patient stratification than the clinical or proteomic analysis alone. Mechanistically, the identified biomarkers highlight the importance of platelet activation, uncontrolled angiogenesis and intraplaque haemorrhage in the atherosclerotic process, underscoring the need for multipathway therapies to prevent unwanted thrombotic events.
12 Apr 2026
Read appraisal →PLoS medicine
Spatial omics and AI for clinically actionable cancer biomarkers
Integrating spatial omics with artificial intelligence is likely to advance biomarker research and diagnostics, with the potential to pair mechanistic insight into spatial target biology. By developing scalable, reproducible quantification in routine pathology, it can help bridge discovery, validation, and real-world clinical implementation.
11 Apr 2026
Read appraisal →Journal of clinical oncology : official journal of the American Society of Clinical Oncology
Development of a Classifier for Metabolic Subtypes of Nasopharyngeal Carcinoma to Guide Personalized Immunotherapy Strategies: Biomarker Analysis of the Phase III CONTINUUM and DIPPER Trials
PURPOSE: Personalized immunotherapy strategies are urgently needed for patients with locoregionally advanced nasopharyngeal carcinoma (NPC). We aim to identify biomarkers predictive of immunotherapy benefits, using data from the phase III CONTINUUM (ClinicalTrials.gov identifier: NCT03700476) and DIPPER (ClinicalTrials.gov identifier: NCT03427827) randomized clinical trials. PATIENTS AND METHODS: Tumor samples from 407 patients in the CONTINUUM (discovery cohort) and DIPPER (validation cohort) trials were subjected to RNA sequencing. In the discovery cohort, metabolic gene-based consensus clustering was performed to determine subtypes. A machine learning-based classifier was subsequently developed in the discovery cohort and then applied to the validation cohort to assign metabolic subtypes. Gene set enrichment analyses were used to characterize the biological features of each metabolic subtype. The clinical end point was event-free survival (EFS). RESULTS: In the discovery cohort, three metabolic subtypes were identified with distinct tumor-intrinsic and immune features as well as differential EFS benefits from adding anti-PD-1 to chemoradiotherapy (CRT). Specifically, the MS1 subtype exhibited a significant improvement in 3-year EFS in the anti-PD-1 plus CRT arm compared with the CRT-alone arm (3-year EFS, 90.2% v 69.6%; hazard ratio, 0.27 [95% CI, 0.11 to 0.67]), whereas MS2 (3-year EFS, 94.1% v 93.8%) and MS3 subtypes (3-year EFS, 75.0% v 75.0%) derived no significant survival benefit. The subtype features were preserved in the validation cohort, with consistent prognostic and predictive value. A pooled analysis of both cohorts demonstrated the significant interaction between metabolic subtypes and the treatment effect (Pinteraction = 0.0074). CONCLUSION: In this biomarker study, we defined metabolic subtypes of NPC that predicted the EFS benefit from immunotherapy. This novel molecular classification provides a promising predictive biomarker for personalized treatment decision for patients with locoregionally advanced NPC.
11 Apr 2026
Read appraisal →Biochemical and biophysical research communications
Interpretable prognostic modeling of glioblastoma using cross-cohort transcriptome integration and machine learning approaches
Glioblastoma (GBM) is an aggressive brain tumor with highly variable patient outcomes due to pronounced molecular heterogeneity. Prognosis remains dismal (median survival ∼15 months) and current prognostic models often function as "black boxes," lacking interpretability and limiting clinical utility. There is an urgent need for interpretable prognostic tools to better stratify GBM patients. This study performed cross-cohort, cross-platform transcriptome data integration (TCGA RNA-seq and GEO microarrays) and incorporated inferred immunogenomic features to capture GBM's complexity. An automated machine learning (AutoML) pipeline tested over 100 algorithmic combinations to build an optimal survival prediction model. The final model is a 22-gene signature, and SHAP (SHapley Additive exPlanations) analysis was applied to explain each gene's contribution to risk. Key genes identified by the model (e.g. UBE2W, EID1, HS2ST1) were validated by qRT-PCR and Western blot, confirming their dysregulated expression in GBM cell lines. The 22-gene model achieved a concordance index of ∼0.72 and was validated on independent cohorts (TCGA training and GEO validation), demonstrating robust performance. It effectively stratified patients into high- and low-risk groups with significant survival differences. High-risk tumors were associated with an immune-cell-enriched yet immune-evasive microenvironment, showing greater infiltration of immunosuppressive cells and higher TIDE scores (indicating immune escape). In contrast, low-risk patients had a more favorable immune profile, and their tumors were predicted to be more sensitive to multiple chemotherapeutic agents. This interpretable transcriptome-based integrative prognostic model can serve as a valuable tool for GBM risk stratification and may guide therapeutic decision-making by highlighting potential targets. Not only does it improve outcome prediction, but it also identifies novel prognostic biomarkers, holding promise for personalized treatment and clinical translation in glioblastoma.
10 Apr 2026
Read appraisal →Brain : a journal of neurology
Leveraging machine learning to predict Parkinson's disease using pre-symptomatic proteomics data
In Parkinson's disease, non-motor symptoms precede the characteristic motor manifestations by up to 20 years. However, predicting the disease risk remains challenging. We applied machine learning to 2937 plasma proteins assayed in UK Biobank participants with Parkinson's disease to predict disease outcome up to 14 years before diagnosis. Of the 446 proteins found to be dysregulated in incident cases compared with controls, a subset of 23 predicted disease with an area under the curve (AUC) value of 0.78 in incident and 0.795 in prevalent cases. The utility of the identified proteomic signatures was validated in an independent cohort, based on 16 proteins shared across datasets, leading to a validation AUC of up to 0.76. Parkinson's disease-related pathways, including neuron death and amyloid-β clearance, were enriched up to 9 years before diagnosis. Furthermore, a co-expression network analysis revealed protein modules associated with disease risk and time-to-diagnosis. Our findings underscore the potential of applying machine learning to large-scale proteomics data from pre-symptomatic patients for early disease prediction.
9 Apr 2026
Read appraisal →Journal of clinical microbiology
Identification of Aspergillus at section and species levels by artificial intelligence-based microscopic morphology image recognition
Rapid and accurate identification of Aspergillus species in clinical microbiology laboratories is crucial for aspergillosis diagnosis and antifungal therapy. However, traditional methods still face challenges in distinguishing phylogenetically related species due to their morphological similarities. This study presents FungalNet, a deep learning model integrating ResNet-50 architecture with Focal Loss algorithm, specifically designed to enhance feature extraction for Aspergillus identification. A total of 12,000 high-resolution images were obtained from lactophenol cotton blue-stained slide preparations under a 100× oil immersion objective, among which 311 images were excluded through a novel quality control approach combining fivefold cross-validation and expert manual review. The performance of four deep learning models (FungalNet and three established models) for identifying Aspergillus species and sections was evaluated using the remaining 11,689 qualified images. FungalNet demonstrated superior classification performance, achieving overall accuracies of 98.45% and 97.85% at the section and species levels, respectively. These results indicate that FungalNet shows significant promise for rapid and accurate identification of Aspergillus species. With further optimization and multicenter validation, this tool could potentially be integrated into routine diagnostic workflows to enhance the efficiency and reliability of fungal identification in clinical settings.IMPORTANCEThis study integrates microscopic morphology identification with deep learning to address the challenge of accurate Aspergillus species identification. Twelve clinically isolated Aspergillus species belonging to eight different sections were included. From touch-tape slide preparations with lactophenol cotton blue staining under a 100× oil immersion objective, 11,689 qualified images were collected and analyzed using FungalNet (our proposed model) along with three established models (GoogLeNet, ResNet-50, and Xception). The results showed that FungalNet demonstrated superior performance in Aspergillus identification, achieving the highest classification accuracy at both section (98.45%) and species (97.85%) levels. Given its rapid turnaround time and cost-effectiveness, this AI-based image analysis approach shows promising potential for the rapid and accurate identification of Aspergillus species in clinical microbiology laboratories.
9 Apr 2026
Read appraisal →Genome research
spRefine denoises and imputes spatial transcriptomic data with a reference-free framework powered by genomic language model
The analysis of spatial transcriptomic data is hindered by high noise levels and missing gene measurements, challenges that are further compounded by the higher cost of spatial data compared to traditional single-cell data. To overcome this challenge, we introduce spRefine, a deep learning framework that leverages genomic language models to jointly denoise and impute spatial transcriptomic data. Our results demonstrate that spRefine yields more robust cell- and spot-level representations after denoising and imputation, substantially improving data integration. In addition, spRefine serves as a strong framework for model pretraining and the discovery of novel biological signals, as highlighted by multiple downstream applications across data sets of varying scales. Notably, spRefine enhances the accuracy of spatial aging clock estimations and uncovers new aging-related relationships associated with key biological processes, such as neuronal function loss, which offers new insights for analyzing aging effect with spatial transcriptomics.
8 Apr 2026
Read appraisal →Analytical chemistry
Multicomponent Simultaneous Identification Network (MSINet): An Advanced Deep Learning Model for Boosting Multiplex SERS Detection in Untreated Real Samples
Surface-enhanced Raman spectroscopy (SERS) represents unique advantages for on-site analysis due to its high sensitivity, high specificity, and applicability to gaseous, liquid, and solid samples. However, the complex and unknown components in matrices, as well as competitive adsorptions between targets, will cause signal fluctuation and spectral overlap, which make it challenging to detect multiple targets in untreated real samples. Herein, we designed a deep learning model named the multicomponent simultaneous identification network (MSINet) for analyzing the SERS spectra of untreated samples and output qualitative and content evaluation results of multiple inside targets. The hierarchical feature extraction and multiple feature integration made MSINet robust to signal fluctuations and spectral overlaps while requiring only a small amount of training to quantify target contents in any samples due to its threshold judgment rule. Using the MSINet-assisted SERS detection scheme, the presence and content levels of multiple UV absorbers in seawater, food additives in ready-to-drink cocktails, and biomarkers in human serum could all be determined with ≥0.90 accuracy when facing testing databases. But in contrast, the accuracy in evaluating the target contents in the above untreated samples by the standard curve method was as low as 0.05. The powerful ability to process spectral data, an easy-to-use graphical user interface, and "zero" extra cost make MSINet a universal tool to assist arbitrary SERS sensors in performing high-throughput detection of real samples, leading to great potential in on-site analysis.
8 Apr 2026
Read appraisal →Journal of proteome research
Protein Biomarkers as Molecular Tools for Forensic Biofluid Identification
Forensic proteomics has rapidly established a significant role in forensics, particularly when DNA analysis is insufficient. Proteomics has been frequently recognized for helping reveal useful information about the origin, state and context of forensic samples. Proteins are considered crucial biomarkers in biological samples because of their ability to elucidate cellular functions and post-mortem alterations. Combining advanced mass spectrometry and bioinformatics has increased the importance of proteomics in forensic sciences. The current study examined the use of proteomic technologies, mass spectrometry, and sophisticated software across the key domains of forensic research. The procedure for Post-Mortem Interval (PMI) estimation and body fluid classification proved to be more precise because of the use of machine learning. Peptide biomarkers have helped identify various species by samples of blood, saliva, and semen, and recognize brain, muscles, and skin tissues. Despite significant advancements, the wide acceptance of forensic proteomics remains problematic due to intricate sample stability, high equipment costs, and strict legal standards. Recent advancements in analytical sensitivity, data interpretation tools, and collaborative efforts toward robust protocols position forensic proteomics as an indispensable component of the forensic toolkit. This review indicates the increasing relevance of proteomics in forensic applications, especially relating to PMI estimation, body fluid differentiation, and disease profiling. It promises to significantly enhance the depth of evidentiary interpretation and contribute to more precise and equitable outcomes in the criminal justice system. Proteomic biomarkers need further validation across a range of environments, and standardized protocols should be developed and tested to ensure that proteomics is suitable for forensic use in the courts.
6 Apr 2026
Read appraisal →Annals of oncology : official journal of the European Society for Medical Oncology
Deep learning discriminates thymic epithelial tumors' histological subtypes using digital pathology.
BACKGROUND: Thymic epithelial tumors (TETs) are rare malignancies that pose significant diagnostic challenges due to their heterogeneous histological patterns and substantial interobserver variability in classification. Despite standardized World Health Organization (WHO) classification criteria, diagnostic concordance remains suboptimal, particularly in nonexpert settings, where second-opinion reviews lead to diagnostic reclassification in up to 57% of cases. Deep learning may offer a tool to reduce diagnostic variability and improve the consistency of histological classification. MATERIALS AND METHODS: We trained a deep learning-based model using hematoxylin-eosin (H&E) whole-slide images from The Cancer Genome Atlas as a training dataset. The model incorporated a novel hierarchical loss function designed to reflect clinically relevant tumor groupings based on treatment strategies and patient outcomes. We validated the model on 112 consecutive cases from the University of Chicago, with diagnoses confirmed by an expert thoracic pathologist. Model performances were evaluated using both a three-group hierarchical scheme and the six-class WHO classification. RESULTS: In the clinically relevant hierarchical three-group classification (As: A + AB; Bs: B1 + B2 + B3; and thymic carcinoma), the model achieved an accuracy of 91.1% with Cohen's κ = 0.859, indicating almost perfect agreement. In the six-class classification (A, AB, B1, B2, B3, and thymic carcinoma), the accuracy was 77.7% with κ = 0.716. The model demonstrated 100% sensitivity and 94.6% accuracy for thymic carcinoma detection. Notably, 60% of misclassifications occurred within the same clinical management group, thereby limiting their impact on therapeutic decision making. CONCLUSION: This deep learning model demonstrates strong potential as a diagnostic tool for TETs classification, particularly in settings with limited thoracic pathology expertise. The high sensitivity for thymic carcinoma detection and robust performance across different tissue processing conditions suggest its clinical applicability for improving diagnostic consistency and supporting pathological decision making in both specialized and nonspecialized settings.
4 Apr 2026
Read appraisal →Abdominal radiology (New York)
Artificial intelligence in gastric cancer: a systematic review of machine learning and deep learning applications
BACKGROUND: Gastric cancer (GC) remains a major global health concern, ranking as the fifth most prevalent malignancy and the fourth leading cause of cancer-related mortality worldwide. Although early detection can increase the 5-year survival rate of early gastric cancer (EGC) to over 90%, more than 80% of cases are diagnosed at advanced stages due to subtle clinical symptoms and diagnostic challenges. Artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), has shown great promise in addressing these limitations. OBJECTIVES: This systematic review aims to evaluate the performance, applications, and limitations of ML and DL models in GC management, with a focus on their use in detection, diagnosis, treatment planning, and prognosis prediction across diverse clinical imaging and data modalities. METHODS: Following the PRISMA 2020 guidelines, a comprehensive literature search was conducted in MEDLINE, Web of Science, and Scopus for studies published between 2004 and May 2025. Eligible studies applied ML or DL algorithms for diagnostic or prognostic tasks in GC using data from endoscopy, computed tomography (CT), pathology, or multi-modal sources. Two reviewers independently performed study selection, data extraction, and risk of bias assessment. RESULTS: A total of 59 studies met the inclusion criteria. DL models, particularly convolutional neural networks (CNNs), demonstrated strong performance in EGC detection, with reported sensitivities up to 95.3% and Area Under the Curve (AUCs) as high as 0.981, often exceeding expert endoscopists. CT-based radiomics and DL models achieved AUCs ranging from 0.825 to 0.972 for tumor staging and metastasis prediction. Pathology-based models reported accuracies up to 100% for EGC detection and AUCs up to 0.92 for predicting treatment response. Cross-modality approaches combining radiomics and pathomics achieved AUCs up to 0.951. Key challenges included algorithmic bias, limited dataset diversity, interpretability issues, and barriers to clinical integration. CONCLUSION: ML and DL models have demonstrated substantial potential to improve early detection, diagnostic accuracy, and individualized treatment in GC. To advance clinical adoption, future research should prioritize the development of large, diverse datasets, implement explainable AI frameworks, and conduct prospective clinical trials. These efforts will be essential for integrating AI into precision oncology and addressing the increasing global burden of gastric cancer.
4 Apr 2026
Read appraisal →European radiology
Predictive value of artificial intelligence-based quantitative CT feature analysis for diagnosing the pathological types of pulmonary nodules
OBJECTIVES: Accurate preoperative classification of pulmonary nodules (PNs) is critical for guiding clinical decision-making and preventing overtreatment. This study aims to evaluate the predictive performance of artificial intelligence (AI)-based quantitative computed tomography (CT) feature analysis in differentiating among four pathological types of PNs: atypical adenomatous hyperplasia and adenocarcinoma in situ (AAH + AIS), minimally invasive adenocarcinoma (MIA), invasive adenocarcinoma (IAC), and lung inflammatory nodules (IN). MATERIALS AND METHODS: A total of 462 pathologically confirmed PNs were analyzed. Radiomic features, including CT attenuation metrics, 3D morphometrics, and texture parameters such as entropy and skewness, were extracted using a deep learning-based AI platform. Logistic regression models were constructed using both single- and multi-variable strategies to evaluate the classification accuracy of these features. Moreover, the inclusion of IN as a separate category significantly enhanced the clinical utility of AI in differentiating benign mimickers from malignant nodules. The combined model, which integrated AI-derived features with traditional CT signs, was used to assess the diagnostic performance of the radiomic features in differentiating the four pathological types of nodules. RESULTS: The combined model demonstrated superior diagnostic performance, with area under the curve (AUC) values of 0.936 for IAC, 0.884 for AAH + AIS, and 0.865 for IN. Although MIA showed lower classification accuracy (AUC = 0.707), key features such as entropy, solid component ratio, and total volume effectively distinguished invasive from non-invasive lesions. CONCLUSION: These findings highlight the potential of AI-enhanced radiomics for supporting non-invasive, objective, and individualized diagnosis of PNs. KEY POINTS: Question Can artificial intelligence (AI)-based quantitative CT analysis reliably differentiate benign inflammatory nodules from the spectrum of lung adenocarcinoma subtypes, a common diagnostic challenge? Findings An integrated model combining AI-driven radiomic features and traditional CT signs demonstrated high accuracy in differentiating invasive adenocarcinoma (AUC = 0.936), pre-invasive lesions (AUC = 0.884), and inflammatory nodules (AUC = 0.865). Clinical relevance AI-enhanced radiomics provides a non-invasive, objective tool to improve preoperative risk stratification of pulmonary nodules, potentially guiding personalized management and reducing unnecessary surgeries for benign inflammatory lesions that mimic malignancy.
4 Apr 2026
Read appraisal →Neurological research
Machine learning-based preoperative prediction of IDH mutation status in adult gliomas using clinical features
BACKGROUND: As isocitrate dehydrogenase (IDH) mutation status represents a critical prognostic factor in adult gliomas, there is a demand for a straightforward but effective predictive model to facilitate rapid preoperative diagnosis. METHODS: A cohort of 418 adult glioma patients from our institution were retrospectively enrolled and randomly partitioned into training (70%) and internal validation (30%) sets. Among 9 machine learning algorithms evaluated, AdaBoost demonstrated superior predictive performance based on receiver operating characteristic (ROC) analysis and was subsequently selected as the optimal model. Through feature importance ranking derived from the model, the top 8 most contributory features were identified and incorporated into the final streamlined prediction model. The model's generalizability was further assessed using an independent external validation cohort comprising 206 adult glioma cases. RESULTS: The AdaBoost model demonstrated robust discriminative performance, achieving an area under the receiver operating characteristic curve (AUC-ROC) of 0.901 in the internal validation cohort and 0.849 in the independent external validation cohort. SHAP (SHapley Additive exPlanations) interpretation revealed age as the most influential predictive feature, contributing significantly to the model's decision-making process. CONCLUSIONS: This validated AdaBoost model offers a practical and interpretable solution for preoperative IDH status assessment, demonstrating both diagnostic reliability and biological plausibility through its feature importance profile.
4 Apr 2026
Read appraisal →IEEE transactions on medical imaging
EviVLM: When Evidential Learning Meets Vision Language Model for Medical Image Segmentation
The disparity between image and text representations, often referred to as the modality gap, remains a significant obstacle for Vision Language Models (VLMs) in medical image segmentation. This gap complicates multi-modal fusion, thereby restricting segmentation performance. To address this challenge, we propose Evidence-driven Vision Language Model (EviVLM)-a novel paradigm that integrates Evidential Learning (EL) into VLMs to systematically measure and mitigate the modality gap for enhanced multi-modal fusion. To drive this paradigm, an Evidence Affinity Map Generator (EAMG) is proposed to collect complementary cross-modal evidences by learning a global cross-modal affinity map, thus refining modality-specific evidence embedding. An Evidence Differential Similarity Learning (EDSL) is further proposed to collect consistent cross-modal evidences by performing Bias-Variance Decomposition on differential matrix derived from bidirectional similarity matrices between image and text evidence embeddings. Finally, the subjective logic is used for mapping the collected evidences to opinions, and the Dempster-Shafer's theory based combination rule is introduced for opinion aggregation, thereby quantifying the modality gap and facilitating effective multi-modal integration. Experimental results on three public medical image segmentation datasets validate that the proposed EviVLM can achieve state-of-the-art performance. Code is available at: https://github.com/QingtaoPan/EviVLM.
4 Apr 2026
Read appraisal →IEEE transactions on medical imaging
Self-Paced Learning for Images of Antinuclear Antibodies
Antinuclear antibody (ANA) testing is a critical method for diagnosing autoimmune disorders such as Lupus, Sjögren's syndrome, and scleroderma. Despite its importance, manual ANA detection is slow, labor-intensive, and demands years of training. ANA detection is complicated by over 100 coexisting antibody types, resulting in vast fluorescent pattern combinations. Although machine learning and deep learning have enabled automation, ANA detection in real-world clinical settings presents unique challenges as it involves multi-instance, multi-label (MIML) learning. In this paper, a novel framework for ANA detection is proposed that handles the complexities of MIML tasks using unaltered microscope images without manual preprocessing. Inspired by human labeling logic, it identifies consistent ANA sub-regions and assigns aggregated labels accordingly. These steps are implemented using three task-specific components: an instance sampler, a probabilistic pseudo-label dispatcher, and self-paced weight learning rate coefficients. The instance sampler suppresses low-confidence instances by modeling pattern confidence, while the dispatcher adaptively assigns labels based on instance distinguishability. Self-paced learning adjusts training according to empirical label observations. Our framework overcomes limitations of traditional MIML methods and supports end-to-end optimization. Extensive experiments on one ANA dataset and three public medical MIML benchmarks demonstrate the superiority of our framework. On the ANA dataset, our model achieves up to +7.0% F1-Macro and +12.6% mAP gains over the best prior method, setting new state-of-the-art results. It also ranks top-2 across all key metrics on public datasets, reducing Hamming loss and one-error by up to 18.2% and 26.9%, respectively. The source code can be accessed at https://github.com/fletcherjiang/ANA-SelfPacedLearning.
4 Apr 2026
Read appraisal →Annals of surgical oncology
A Deep Learning-Based Multimodal Clinico-Histology-Genomic Prognostic Model in Prostate Cancer
BACKGROUND: Prostate cancer remains a leading cause of cancer mortality, yet current risk stratification systems inadequately integrate multidimensional tumor characteristics. This study aims to develop a deep learning-based multimodal prognostic model that combines genomic signatures, histomorphological features from whole-slide imaging (WSI), and clinical parameters to improve risk stratification and therapeutic decision-making. MATERIALS AND METHODS: We constructed a deep learning framework using two independent cohorts: The Cancer Genome Atlas (TCGA) for training and the Prostate, Lung, Colorectal and Ovarian (PLCO) trial for external validation. The model sequentially extracted 768-dimensional histopathological features from hematoxylin and eosin (H&E)-stained WSIs, predicted genomic scores, and histopathological scores, and integrated these with clinical variables via Cox regression to generate a multimodal prognostic score. Performance was evaluated through Kaplan-Meier analysis, Harrell's concordance index, and multivariate Cox regression. RESULTS: The prognostic score demonstrated superior prognostic accuracy (C-index: 0.774) compared with unimodal scores (genomic, histopathological, clinical) and NCCN risk stratification (C-index: 0.706-0.746, p < 0.05). High-risk patients identified by the multimodal model had significantly shorter progression-free intervals (HR = 9.088, 95% CI 6.033-13.691, p < 0.0001) and prostate cancer-specific mortality (HR = 8.787, 95% CI 3.238-23.847, p < 0.0001). Subgroup analysis within NCCN high-risk patients revealed distinct survival trajectories (p < 0.001). Gene set enrichment linked multimodal scores to tumor-relevant pathways. CONCLUSIONS: This integrative model eliminates reliance on genomic testing by computationally inferring genomic features from histopathology, while significantly enhancing prognostic precision. By stratifying heterogeneous patient populations and refining existing NCCN classifications, the prognostic score offers clinical potential for personalized risk assessment and optimized therapeutic strategies.
4 Apr 2026
Read appraisal →The Journal of pathology
Integrating artificial intelligence (AI) into colorectal cancer reporting
Artificial intelligence (AI) and deep learning (DL) are transforming cancer research and clinical care, with histopathology playing a central role in this transformation. In colorectal cancer (CRC), the second leading cause of cancer mortality world-wide, multimodal and vision-language models (VLMs) hold particular promise for enhancing the standardisation of histopathology reporting, the understanding of disease biology, and the discovery of novel prognostic indicators. Despite the availability of guidelines and reporting templates for essential prognostic indicators, variability remains in how key features such as TNM staging or tumour deposits are assessed and reported in routine clinical practice. AI-based tools have the potential to support refined extraction of established and extended features directly from whole-slide images. In parallel, recent studies have shown that DL models applied to pathology slides and associated AI-based biomarkers can outperform traditional histopathological prognostic indicators and uncover novel parameters, including tumour-adipocyte interactions, tumour-stroma ratio, and immune cell patterns at the invasive margin. Here, we review recent advances in both domains: AI-assisted standardisation of CRC pathology reporting and AI-driven identification of novel prognostic biomarkers. We highlight the need to refine and standardise CRC reporting practices and propose that a harmonised approach combining established pathology features with AI-derived prognostic indicators could refine risk assessment and improve outcomes for CRC patients. © 2026 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
4 Apr 2026
Read appraisal →Journal of biophotonics
Cell-MICS: Detecting Immune Cells With Label-Free Two-Photon Autofluorescence and Deep Learning
Multiphoton imaging has been widely used for deep-tissue imaging. Although its label-free, metabolic contrast is ideal for investigating inflammation, the label-free two-photon induced autofluorescence is often regarded as less specific compared to conventional antibody markers. In this work, we investigate the potential for multiphoton imaging with computational specificity (MICS) by training a convolutional neural network on images of different immune cells. A low-complexity squeezeNet architecture was able to achieve reliable immune cell classification results (0.89 ROC-AUC, 0.95 PR-AUC for binary classification between T cells and neutrophils; 0.689 F1 score, 0.697 precision, 0.748 recall for multi-class classification between six isolated cell types). Perturbation tests confirmed that the model was not confused by the extracellular environment and that 2P-AF from NADH and FAD is equally important for the classification. In the future, deep learning could provide computational specificity for specific immune cells in unstained tissues, with great potential for label-free in vivo endomicroscopy.
4 Apr 2026
Read appraisal →Critical reviews in oncology/hematology
Artificial intelligence and multi-omics convergence in breast cancer: Revolutionizing diagnosis, prognostication, and precision oncology
Breast cancer (BC) is a highly heterogeneous malignancy and remains a major cause of cancer-related mortality among women worldwide. Advances in multi-omics profiling spanning genomics, transcriptomics, epigenomics, proteomics, and metabolomics have enabled finer subtype stratification and more comprehensive characterisation of tumour biology, thereby accelerating the discovery of diagnostic and prognostic biomarkers and actionable therapeutic targets. Nonetheless, translating multi-layer molecular signals into clinically robust decision support remains challenging because of the high dimensionality and heterogeneity of omics data, cross-cohort and cross-platform variability, and the fragmentation inherent to single-modality analyses. This review summarises how multi-omics studies have refined BC subtype definitions and advanced biomarker and target identification, and then synthesises recent progress in artificial intelligence, particularly deep learning, for integrating multi-omics with imaging, pathology, and clinical variables to improve diagnosis, risk stratification, prognosis prediction, and treatment response assessment. We critically examine representative multimodal integration frameworks and emerging deep learning architectures that learn both shared and modality-specific representations, which in many settings enable more accurate patient-level prediction than unimodal baselines. We further delineate key barriers to clinical translation, including cross-centre heterogeneity and inconsistent endpoint definitions, structural missingness of modalities in real-world workflows, inadequate cross-platform normalisation, limited interpretability and auditability, and a lack of prospective validation. Finally, we propose realistic next steps, including standardised and auditable preprocessing pipelines, missingness-aware fusion strategies, explainable and uncertainty-aware modelling, privacy-preserving multi-centre learning, and prospective, workflow-based evaluation. Collectively, these perspectives provide a roadmap for advancing multimodal AI-multi-omics integration toward reliable clinical deployment in BC management.
4 Apr 2026
Read appraisal →Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery
Multicenter Clinical Validation of an Artificial Intelligence Diagnostic Classification Model for Laryngoscopy Images
OBJECTIVE: To develop and externally validate a computer-aided diagnosis (CADx) model using artificial intelligence (AI) for classifying laryngeal lesions from laryngoscopy images into high-risk (HR), low-risk (LR). STUDY DESIGN: Retrospective multicenter development of a CADx model and external validation on independent cohorts. SETTING: Multicenter tertiary referral hospitals (Italy, India, China, Greece, and Spain). METHODS: Over 20,000 images derived from laryngoscopic examinations were retrieved. Images were annotated based on histopathology or expert consensus. A deep learning model was trained using an internal dataset and evaluated on 2 external datasets to assess generalizability. The CADx model classifies only images containing visible lesions, discriminating between LR and HR categories. Diagnostic performance was measured using standard metrics, including accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Model performance was compared with physicians of varying expertise and ChatGPT-4o. RESULTS: The computer-aided diagnosis model achieved a similar performance across internal and external datasets in distinguishing HR from LR lesions, with accuracy/AUC of 0.90/0.89 internally, 0.85/0.85 on the Greek dataset, and 0.88/0.88 on the Spanish dataset. The model's accuracy was statistically noninferior to that of otolaryngologists and expert laryngologists, and superior to general practitioners and ChatGPT-4o. CONCLUSION: This is a large multicenter clinical validation of a CADx model for laryngeal endoscopy, demonstrating generalizability and performance comparable to clinicians in discriminating between LR and HR lesions. The model's success supports its potential role in augmenting diagnostic capabilities, especially in resource-limited settings. A prospective multicenter clinical trial is underway to assess real-world clinical implementation.
2 Apr 2026
Read appraisal →Cancer Cell
Precision treatment with artificial intelligence assisted subtyping enhances therapeutic efficacy in HR+/HER2- breast cancer: The LINUXtrial.
We report the results of LINUX (NCT05594095), a multicenter, randomized, controlled phase II platform trial aiming to identify effective precision treatments for hormone receptor-positive/human epidermal growth factor receptor 2-negative metastatic breast cancer after resistance to cyclin-dependent kinase 4/6 inhibitor. A total of 105 patients were categorized into four similarity network fusion (SNF) subtypes by artificial intelligence-assisted classification and randomly assigned to receive subtyping-based precision therapy (N = 70) or treatment of physician's choice (N = 35). Results demonstrate superior primary endpoint of objective response rates in the subtyping-based groups compared to controls: 10% versus 0% for SNF1, 65% versus 30% for SNF2, 40% versus 30% for SNF3, and 70% versus 20% for SNF4. Grade 3-4 treatment-related adverse events occurred in 37% of both groups. These findings highlight the clinical benefits of subtyping-based precision therapies, particularly for SNF2 and SNF4 subtypes, warranting further validation in phase III trials.
1 Feb 2026
Read appraisal →Int J Surg
Multi-omics dissection of high TWAS-active endothelial pathogenesis in pulmonary arterial hypertension: bridging single-cell heterogeneity, machine learning-driven biomarkers, and developmental reprogramming
BACKGROUND: Pulmonary Arterial Hypertension (PAH) is a leading cause of cardiovascular-related mortality worldwide. The emergence of single-cell RNA sequencing (scRNA-seq) has enhanced the ability to dissect cellular heterogeneity in PAH at a granular level. Transcriptome-wide association studies (TWAS) leverage expression quantitative trait loci (eQTL) and genome-wide association study (GWAS) data to identify novel susceptibility genes whose genetically predicted expression correlates with disease risk. However, no study has systematically integrated TWAS with scRNA-seq to unravel the pathogenesis of PAH at single-cell resolution. METHODS: Using TWAS analysis, we identified a set of candidate genes genetically associated with PAH. We then evaluated the differential activity of these genes across PAH cell types at single-cell resolution using AUCell, Ucell, ssGSEA (Single Sample Gene Set Enrichment Analysis), and AddModuleScore algorithms. A subset of endothelial cells exhibiting elevated TWAS activity was identified via quartile-based stratification and designated as the high TWAS activity state (HTS) group. Multi-dimensional analyses, including observed-to-expected ratio (RO/E), CellChat, CytoTRACE (CytoTRACE is based on the robust observation that transcriptional diversity decreases during cell differentiation), and scMetabolism, were employed to characterize the functional and communicative properties of HTS cells. Machine learning algorithms were integrated to identify signature genes of the HTS subpopulation, and a benchmarked random forest model was trained to predict HTS status. We performed immunohistochemistry and quantitative reverse transcription- polymerase chain reaction (qRT-PCR) validation of the signature genes (KLF2, RASIP1 and DEPP1) in PAH and control lung tissues to support their expression patterns. RESULTS: We demonstrated that HTS endothelial cells are strongly associated with PAH pathogenesis, exhibiting significant tissue tropism, enhanced roles in intercellular communication, and a progenitor-like function in endothelial differentiation. Machine learning-based feature selection revealed three robust signature genes: KLF2, RASIP1, and DEPP1. These genes demonstrated exceptional predictive power for identifying HTS cells, suggesting their potential as drivers of endothelial dysfunction in PAH. The random forest model, benchmarked against multiple algorithms, achieved high accuracy in predicting PAH progression using these genes. Immunohistochemical analysis of pulmonary artery and qRT-PCR result of lung tissues addressed the elevated expression of KLF2, RASIP1 and DEPP1 in arterial wall post-PAH. CONCLUSION: This study elucidates endothelial cell heterogeneity in PAH and establishes the central role of HTS cells in disease progression, cellular crosstalk, and developmental reprogramming. Our findings bridge the gap between GWAS and scRNA-seq methodologies and provide a transformative framework for understanding PAH mechanisms.
1 Feb 2026
Read appraisal →J Clin Oncol
Genomics Define Malignant Transformation in Myeloma Precursor Conditions
Multiple myeloma (MM) is consistently preceded by monoclonal gammopathy of undetermined significance (MGUS) and smoldering multiple myeloma (SMM). While these precursor conditions are asymptomatic, they are not entirely benign and carry a lifelong risk of progression to MM. Unlike other cancers defined by pathology, malignant transformation from MGUS or SMM to MM has so far relied on demonstration of clinical end-organ damage as morphology and cytogenetics cannot reliably distinguish them. In this study, using genomic data from 374 patients with MGUS or SMM (277 training, 97 validation), to our knowledge, we demonstrate for the first time the ability to identify malignant transformation in MGUS and SMM. We introduce the concept of genomic MM and genomic MGUS to differentiate the subsets of MGUS and SMM that are biologically malignant with genomic features indistinguishable from MM from the subset that is premalignant and unlikely to progress to malignancy. Importantly, we find that most SMM has biological features of malignant transformation indistinguishable from MM. As expected, this subset that we consider having genomic MM is associated with a high risk of progression to MM although some patients remained progression-free beyond 5 years. Conversely, 60% of MGUS and 10% of SMM have no evidence of malignant transformation (genomic MGUS), with no progression during follow-up. Integration of genomic features with the 2/20/20 International Myeloma Working Group model significantly improved the prediction of progression among genomic MM. These findings support the use of genomic criteria to refine the classification and the risk stratification in myeloma precursor conditions.
1 Jan 2026
Read appraisal →Artif Cells Nanomed Biotechnol
Unveiling the ageing-related genes in diagnosing osteoarthritis with metabolic syndrome by integrated bioinformatics analysis and machine learning
Ageing significantly contributes to osteoarthritis (OA) and metabolic syndrome (MetS) pathogenesis, yet the underlying mechanisms remain unknown. This study aimed to identify ageing-related biomarkers in OA patients with MetS. OA and MetS datasets and ageing-related genes (ARGs) were retrieved from public databases. The limma package was used to identify differentially expressed genes (DEGs), and weighted gene coexpression network analysis (WGCNA) screened gene modules, and machine learning algorithms, such as random forest (RF), support vector machine (SVM), generalised linear model (GLM), and extreme gradient boosting (XGB), were employed. The nomogram and receiver operating characteristic (ROC) curve assess the diagnostic value, and CIBERSORT analysed immune cell infiltration. We identified 20 intersecting genes among DEGs of OA, key module genes of MetS, and ARGs. By comparing the accuracy of the four machine learning models for disease prediction, the SVM model, which includes CEBPB, PTEN, ARPC1B, PIK3R1, and CDC42, was selected. These hub ARGs not only demonstrated strong diagnostic values based on nomogram data but also exhibited a significant correlation with immune cell infiltration. Building on these findings, we have identified five hub ARGs that are associated with immune cell infiltration and have constructed a nomogram aimed at early diagnosing OA patients with MetS.
1 Dec 2025
Read appraisal →Gut Microbes
Machine-learning assisted discovery unveils novel interplay between gut microbiota and host metabolic disturbance in diabetic kidney disease
Diabetic kidney disease (DKD) is a serious healthcare dilemma. Nonetheless, the interplay between the functional capacity of gut microbiota and their host remains elusive for DKD. This study aims to elucidate the functional capability of gut microbiota to affect kidney function of DKD patients. A total of 990 subjects were enrolled consisting of a control group (n = 455), a type 2 diabetes mellitus group (DM, n = 204), a DKD group (n = 182) and a chronic kidney disease group (CKD, n = 149). Full-length sequencing of 16S rRNA genes from stool DNA was conducted. Three findings are pinpointed. Firstly, new types of microbiota biomarkers have been created using a machine-learning (ML) method, namely relative abundance of a microbe, presence or absence of a microbe, and the hierarchy ratio between two different taxonomies. Four different panels of features were selected to be analyzed: (i) DM vs. Control, (ii) DKD vs. DM, (iii) DKD vs. CKD, and (iv) CKD vs. Control. These had accuracy rates between 0.72 and 0.78 and areas under curve between 0.79 and 0.86. Secondly, 13 gut microbiota biomarkers, which are strongly correlated with anthropometric, metabolic and/or renal indexes, concomitantly identified by the ML algorithm and the differential abundance method were highly discriminatory. Finally, the predicted functional capability of a DKD-specific biomarker, Gemmiger spp. is enriched in carbohydrate metabolism and branched-chain amino acid (BCAA) biosynthesis. Coincidentally, the circulating levels of various BCAAs (L-valine, L-leucine and L-isoleucine) and their precursor, L-glutamate, are significantly increased in DM and DKD patients, which suggests that, when hyperglycemia is present, there has been alterations in various interconnected pathways associated with glycolysis, pyruvate fermentation and BCAA biosynthesis. Our findings demonstrate that there is a link involving the gut-kidney axis in DKD patients. Furthermore, our findings highlight specific gut bacteria that can acts as useful biomarkers; these could have mechanistic and diagnostic implications.
1 Dec 2025
Read appraisal →J Allergy Clin Immunol
Explainable artificial intelligence predicts inflammatory and spatial heterogeneity from nasal polyp histology
BACKGROUND: Chronic rhinosinusitis with nasal polyps is a heterogeneous disorder characterized by diverse inflammatory signatures and endotypes. OBJECTIVE: We sought to develop a histology-based deep learning network for predicting inflammatory gene signatures and spatial patterns in chronic rhinosinusitis with nasal polyps. METHODS: We developed HE2Signature, a deep learning model, using 70 hematoxylin and eosin-stained whole-slide images of nasal polyps paired with corresponding endotypic signature gene expression profiles derived from transcriptomic data. The model was validated in an internal cohort (n = 30) and tested in an independent external cohort (n = 224) from 4 medical centers. The performance was evaluated using correlation and confusion matrix analyses and receiver-operating characteristic curves. Spatial predictions were validated by immunohistochemistry. RESULTS: The HE2Signature demonstrated strong positive correlations between the predicted and actual expression levels of 28 of the 33 signature genes. The internal validation cohort was stratified into distinct endotypes on the basis of predicted signature gene expression, achieving area under the curve values of 0.833, 0.903, and 0.935 for the T1, T2, and T3 endotypes, respectively. In the external cohort, the combination of HE2Signature-predicted Fc epsilon receptor II and CST1 effectively identified the T2 endotype, with a receiver-operating characteristic value of 0.716. Histopathologic examination of high-prediction patches revealed characteristic features associated with signature gene expression. Heatmaps and immunohistochemistry confirmed the accuracy of the model in mapping spatial gene expression patterns. HE2Signature-predicted spatial expression of signature genes correlated with blood and tissue eosinophil counts, Lund-Kennedy score, and Sino-Nasal Outcome Test-22 score, particularly within subepithelial regions. CONCLUSIONS: Our study introduces the first histology-based, explainable deep learning model capable of predicting inflammatory gene signatures and spatial molecular heterogeneity. This proof-of-concept highlights that artificial intelligence-powered histopathologic analysis can generate digital biomarkers by linking tissue patterns with molecular profiles, providing a clinically applicable framework for endotype-guided precision medicine in chronic rhinosinusitis with nasal polyps.
1 Dec 2025
Read appraisal →Cancer Res
Artificial Intelligence and Multimodality Data Integration Decipher Tertiary Lymphoid Structure Maturity in Gastric Cancer
UNLABELLED: Tertiary lymphoid structures (TLS) are critical components of the tumor microenvironment in gastric cancer, but clinical assessment of TLSs is challenging. The development of automated annotation tools for histopathologic slide analysis could facilitate the identification of TLSs and enhance our understanding of the mechanisms driving TLS maturation. In this study, we generated a transformer-based deep learning model that enables quantitative characterization of TLS maturity from whole-slide images. Application of the model to a large gastric cancer cohort (n = 253) showed that higher TLS maturity correlated with improved patient survival. Integration of single-cell RNA sequencing data from 17 patients with gastric cancer combined with multiplex IHC, flow cytometry, and functional coculture assays identified a key immune circuit in mature TLSs involving CD8+ tissue-resident memory T cells, which recruit activated B cells via the CXCL13-CXCR5 axis to enhance tissue-resident memory T-cell cytotoxicity through granzyme B upregulation. Overall, this study established a clinically applicable artificial intelligence tool and uncovered key immune interactions that regulate TLS maturation and antitumor immunity in gastric cancer. SIGNIFICANCE: A deep learning model demonstrates that higher tertiary lymphoid structure maturity predicts improved gastric cancer patient survival and identifies a key immune circuit, offering a clinically applicable tool that could guide treatment. This article is part of a special series: Driving Cancer Discoveries with Computational Research, Data Science, and Machine Learning/AI.
1 Dec 2025
Read appraisal →Int J Surg
Multi-omic profiling reveals age-specific blood biomarkers and aging-driven B cell remodeling in osteoarthritis
BACKGROUND: Osteoarthritis (OA) pathogenesis involves age-related immune dysregulation, yet non-invasive diagnostic tools and mechanistic insights remain limited. METHODS: We integrated transcriptomic profiling of four OA-affected joint tissues with machine learning to identify potential peripheral blood biomarkers. Weighted gene co-expression network analysis was employed to explore gene modules and pathways associated with OA. Single-cell RNA sequencing was performed on 217 983 joint cells to delineate B cell differentiation trajectories. Flow cytometry was used to validate age-associated B cell imbalances in peripheral blood. RESULTS: We identified five peripheral blood biomarkers: MAPK1, MAP3K8, ING1, LDLR, and NUP153 in distinguishing OA patients from controls (the area under the curve [AUC] = 0.966). Importantly, these markers exhibited age-specific expression profiles; ING1, NUP153, and MAP3K8 were elevated, while MAPK1 was reduced in elderly compared to younger OA patients. A refined predictive model based on these age-specific markers demonstrated superior performance specifically for elderly Knee OA (KOA, AUC: 0.8 vs. 0.7 for younger KOA). These biomarkers correlated with immune cell infiltration and inflammatory cytokines. In osteoarthritic joint tissues, B cells predominantly originated from subchondral bone and synovium. Single-cell analysis identified age-specific B cell differentiation patterns, with elderly KOA patients enriched in an activated B cell cluster (C1). Furthermore, B cells from elderly KOA patients showed altered energy metabolism and increased proportions in peripheral blood, and functionally promoted chondrocyte damage. CONCLUSION: Our findings establish a novel blood-based diagnostic framework for OA and uncover aging-driven B cell remodeling as a key contributor to elderly OA pathogenesis. These findings offer non-invasive diagnostics and immunomodulatory targets for age-specific OA therapy.
1 Nov 2025
Read appraisal →J Clin Oncol
Foundation Model for Predicting Prognosis and Adjuvant Therapy Benefit From Digital Pathology in GI Cancers
PURPOSE: Artificial intelligence (AI) holds significant promise for improving cancer diagnosis and treatment. Here, we present a foundation AI model for prognosis prediction on the basis of standard hematoxylin and eosin-stained histopathology slides. METHODS: In this multinational cohort study, we developed AI models to predict prognosis from histopathology images of patients with GI cancers. First, we trained a foundation model using over 130 million patches from 104,876 whole-slide images on the basis of self-supervised learning. Second, we fine-tuned deep learning models for predicting survival outcomes and validated them across seven cohorts, including 1,619 patients with gastric and esophageal cancers and 2,594 patients with colorectal cancer. We further assessed the model for predicting survival benefit from adjuvant chemotherapy. RESULTS: The AI models predicted disease-free survival and disease-specific survival with a concordance index of 0.726-0.797 for gastric cancer and 0.714-0.757 for colorectal cancer in the validation cohorts. The models stratified patients into high-risk and low-risk groups, with 5-year survival rates of 49%-52% versus 76%-92% in gastric cancer and 43%-72% versus 81%-98% in colorectal cancer. In multivariable analysis, the AI risk scores remained an independent prognostic factor after adjusting for clinicopathologic variables. Compared with stage alone, an integrated model consisting of stage and image information improved prognosis prediction across all validation cohorts. Finally, adjuvant chemotherapy was associated with improved survival in the high-risk group but not in the low-risk group (treatment-model interaction P = .01 and .006) for stage II/III gastric and colorectal cancer, respectively. CONCLUSION: The pathology foundation model can accurately predict survival outcomes and complement clinicopathologic factors in GI cancers. Pending prospective validation, it may be used to improve risk stratification and inform personalized adjuvant therapy.
1 Nov 2025
Read appraisal →Blood
Artificial intelligence in hematology
Artificial intelligence (AI) and its subdiscipline, machine learning (ML), have the potential to revolutionize health care, including hematology. The diagnosis and treatment of hematologic disorders depend on the integration of diverse data sources, such as imaging, pathology, omics, and laboratory parameters. The increasing volume and complexity of patient data have made clinical decision-making more challenging. AI/ML hold significant potential for enhancing diagnostic accuracy, risk stratification, and treatment response prediction through advanced modeling techniques. Generative AI, a recent advancement within the broader field of AI, is poised to have a profound impact on health care and hematology. Generative AI can enhance the development of novel therapeutic strategies, improve diagnostic workflows by generating high-fidelity images or pathology reports, and facilitate more personalized approaches to patient management. Its ability to augment clinical decision-making and streamline research represents a significant leap forward in the field. However, despite this potential, few AI/ML tools have been fully implemented in clinical practice due to challenges related to data quality, equity, advanced infrastructure, and the establishment of robust evaluation metrics. Despite its promise, AI implementation in hematology faces critical challenges, including bias, data quality issues, and a lack of regulatory frameworks and safety standards that keep pace with rapid technological advancements. In this review, we provide an overview of the current state of AI/ML in hematology as of 2025, identify existing gaps, and offer insights into future developments.
1 Nov 2025
Read appraisal →