Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 45 appraisals
Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association
Artificial Intelligence Tools for Gastrointestinal Research: A Practical Guide
Artificial intelligence (AI) tools, including large language models (LLMs) such as ChatGPT, Claude, and Gemini, are increasingly used in biomedical research. However, practical guidance for integrating these tools into the manuscript writing workflow remains limited. This narrative review provides a structured, step-by-step guide for gastrointestinal (GI) researchers and clinicians seeking to use AI responsibly across the stages of manuscript preparation.
2 Aug 2026
Read appraisal →Journal of chemical information and modeling
HyperDC: A Non-Uniform Hypergraph Framework for Dual- and Higher-Order Drug Combination Recommendation Across Diverse Complex Diseases
Complex diseases are commonly characterized by dysregulation across multiple targets and pathways, making drug combinations an important therapeutic strategy. This creates a growing need for computational methods to prioritize candidate combinations, yet current methods face several practical challenges, including cross-disease application, unified prediction of dual- and multidrug combinations, lack of reliable negative labels, and prediction for low-resource diseases. In this study, we proposed HyperDC, a unified cross-disease drug combination recommendation framework. HyperDC constructs a nonuniform hypergraph based on clinical and knowledge-driven drug-disease association data, representing single drugs and dual- and multidrug combinations in a unified modeling space. It further integrates knowledge graph pretraining and adversarial negative sampling to enhance model discrimination across tasks with different difficulty levels. In the unified dual-drug benchmark and disease-specific prediction tasks, HyperDC outperformed representative methods by up to 12.8 and 30.0 percentage points, respectively. In fixed-anchor clinical ranking tasks, HyperDC showed superior performance across multiple top-ranked recall settings and preferentially recalled FDA-approved dual-drug combinations and clinically supported three-drug combinations. In the data-sparse metabolic dysfunction-associated steatohepatitis (MASH) scenario, HyperDC completed a full workflow from anchor-drug identification and combination partner prioritization to in vitro experimental validation: 70% of the top 10 single-drug candidates were supported by recent literature, and 4 of 6 tested combinations showed synergistic lipid-lowering and anti-inflammatory effects, yielding a hit rate of 66.7%. Overall, HyperDC may narrow the screening space, improve prioritization efficiency, and provide methodological support for the development of combination therapy strategies for complex diseases.
29 July 2026
Read appraisal →International ophthalmology
Machine learning-based model for identifying liver injury in patients with thyroid-associated ophthalmopathy
PURPOSE: To explore the relationship between thyroid-associated ophthalmopathy (TAO) and liver injury and establish a model for identifying liver injury by using machine learning so as to provide an effective diagnostic tool for liver injury in patients with TAO. METHOD: A single-center retrospective study was conducted to collect the clinical data of 318 patients with TAO admitted to a hospital from 2016 to 2022. The patients were divided into a TAO liver injury group (104 cases) and TAO normal liver function group (214 cases) according to whether the patients had normal liver function. The multivariate binomial logistic regression model was used to analyse the risk factors for liver injury in patients with TAO. Feature selection was performed using the random forest algorithm. The research data were divided into a training set and a test set at a ratio of 6:4. Taking whether accompanied by liver injury (0 = no, 1 = yes) as the outcome variable, models were established based on logistic regression, random forest, support vector machine, and decision tree. The performance of the models was evaluated using metrics, including sensitivity, specificity, positive predictive value, negative predictive value, Youden index, and accuracy. RESULT: The random forest method was used for feature screening, and variables ranked among the top 10 according to either mean decrease accuracy or mean decrease Gini were selected for model construction. In five-fold cross-validation, the RF model showed the highest accuracy of 0.937 and AUC of 0.977. In the test set, the RF model also showed good discrimination, with an AUC of 0.973, and the SVM model showed the highest AUC of 0.986, while SVM and LR achieved the highest accuracy of 0.914. CONCLUSION: This study shows that a classification model based on machine learning can effectively identify the risk of liver damage in patients with TAO.
18 July 2026
Read appraisal →Gut and liver
Data-Informed Intuition in Hepatology: Integrating Evidence, Context, and Clinical Reasoning
Artificial intelligence and data-driven models are changing hepatology, but expert clinical judgment remains essential. Liver diseases are complex and evolve over time, requiring reasoning that links numerical data with clinical context. We propose data-informed intuition (DII), a conceptual framework bridging evidence-based medicine with clinical experience and reflective reasoning. Instead of presenting a validated prediction model, it proposes DII as an integrative scaffold for clinical reasoning that can be examined and revised. DII is viewed as a trainable skill that improves with data feedback, not mere guesswork. Clinicians continually calibrate their judgment as patient information accumulates. In hepatology, DII helps interpret disease trajectories, adapt predictive scores to context, and handle uncertainty in liver transplantation, hepatocellular carcinoma, acute liver failure, and related conditions. The DII framework describes eight axes (time, rate, magnitude, pattern, context, causality, integration, and uncertainty) that make visible how data and intuition interact in clinical reasoning. Integrating DII into fellowship training and artificial intelligence-assisted systems could nurture clinicians who combine algorithmic precision with human insight. This perspective summarizes the conceptual basis, clinical uses, and educational value of DII, and outlines both a research agenda for its empirical testing and a path toward data-informed professionalism in hepatology.
15 July 2026
Read appraisal →BMC oral health
The association between oral hygiene and metabolic dysfunction-associated steatotic liver disease - a systematic review
BACKGROUND: Given the increasingly evident links between oral health and systemic health, the aim of this review was to investigate whether oral hygiene practices influence the risk or progression of metabolic dysfunction-associated steatotic liver disease (MASLD). The findings support the potential importance of good oral hygiene and regular dental visits, especially for patients with MASLD. METHODS: This systematic review was registered with PROSPERO (CRD420251041530), and PubMed, Scopus, Embase and Web of Science were used for literature research up to June 2026. In accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, screening, study selection and quality check were performed using Rayyan and the Joanna Briggs Institute (JBI) critical appraisal checklists. Studies assessing the potential link between the frequency of oral hygiene procedures and the incidence, prevalence or progression of MASLD were selected for a systematic synthesis. The old terms non-alcoholic fatty liver disease (NAFLD) and non-alcoholic steatohepatitis (NASH) were considered as well. RESULTS: A total of 570 results were identified of which six studies met the inclusion criteria. Five of them reported a correlation between higher tooth brushing frequency and a lower incidence, prevalence or progression of NAFLD/NASH compared to individuals with lower tooth brushing frequency. Notably, one study revealed significantly worse liver parameters among NASH patients without regular dental visits than among those who visited a dentist more than once a year. CONCLUSIONS: An association between oral hygiene habits and NAFLD/NASH was found in all included studies. A greater frequency of daily tooth brushing as well as regular dental visits might have beneficial effects on both the development and progression of fatty liver disease. However, there is not enough evidence to establish causality yet and the impact of confounding factors must be further investigated. CLINICAL TRIAL REGISTRATION: Not applicable.
11 July 2026
Read appraisal →Journal of medicinal chemistry
Machine Learning-Based Models to Predict Drug-Induced Liver Injury (DILI) to Assist Medicinal Chemistry
Drug-induced liver injury (DILI) is a leading cause of drug failure and post-market withdrawals. Traditional preclinical methods fail to detect up to 40-45% of clinical hepatotoxicity cases. Computational approaches, particularly those based on machine learning and deep learning (DL), are emerging as promising tools to support medicinal chemistry and early drug discovery, though their predictive capabilities remain under active investigation. In this perspective, we review the development of DILI annotation data sets, tracing their growth from small collections to large, comprehensive resources. We also outline the evolution of computational methods, from simple descriptor-based models to advanced DL and ensemble approaches that incorporate interpretable features. Finally, we highlight recent efforts to integrate standardized causality frameworks, pharmacogenomics, and mechanistic models, aiming to connect computational advances with clinical relevance. This perspective provides valuable insight for researchers and promotes the development of more robust and consensual DILI prediction strategies.
10 July 2026
Read appraisal →Journal of hematology & oncology
Large language model-guided CAR-T in silico platform for cytokine optimization in liver cancer with low antigen density
CAR-T cell therapy has shown remarkable success in hematologic malignancies but remains limited in solid tumors such as liver cancer due to antigen heterogeneity, low target antigen density, and an immunosuppressive tumor microenvironment (TME). Cytokine engineering can enhance CAR-T persistence and effector function; however, the optimal cytokine payload may vary depending on tumor type, target antigen expression level, and microenvironmental context, making systematic experimental comparison time-consuming and labor-intensive. Here, we applied a large language model (LLM)-based CAR-T in silico platform to systematically evaluate cytokine engineering strategies, including IL-2, IL-7, IL-12, IL-15, and IL-18, in glypican-3 (GPC3)-targeted CAR-T cells for liver cancer. We used cytokine selection as a biologically grounded benchmark to test whether the platform could recover known CAR-T cell-relevant cytokine biology and support future novel predictions. Computational predictions identified IL-15 as the most effective enhancer, particularly against tumor cells with low GPC3 expression. Guided by these results, we generated cytokine-armored GPC3 CAR-T cells and performed in vitro and in vivo validation. IL-15-engineered CAR-T cells exhibited superior proliferation, persistence, and serial cytotoxicity against GPC3-low liver cancer cells. In human liver cancer xenograft models, IL-15-enhanced CAR-T cells achieved improved tumor control compared with conventional and other cytokine-engineered CAR-T cells. The recovery of IL-15 served as a positive benchmark supporting the validity of the LLM-guided CAR-T in silico workflow. Collectively, this study establishes an LLM-guided framework, schema-constrained for rational cytokine selection in CAR-T engineering and identifies IL-15 as a potent enhancer for targeting antigen-low liver cancers.
3 July 2026
Read appraisal →International journal of medical informatics
Artificial intelligence in gastroenterology clinical practice: Scoping review of large language model applications.
BACKGROUND: Advances in artificial intelligence have brought renewed attention to tools that can work with the large amount of written information generated in clinical practice. Among these, large language models (LLMs) stand out for their ability to interpret and generate medical text in a flexible, context-aware way. Gastroenterology, like many specialties, produces a wide range of narrative and semi-structured data, and this has encouraged researchers to explore how LLMs might help clinicians manage everyday tasks. Recent studies have examined their potential contributions to patient education, communication between care teams and patients, decision support, and routine documentation, reflecting a growing interest in how these systems might fit into real-world clinical workflows. OBJECTIVE: This scoping review aimed to map current applications of LLMs in gastroenterology clinical practice, including subspecialty focus, study designs, model types, and reported outcomes. METHOD: Following PRISMA guidelines, a systematic search was conducted in PubMed, Scopus, and Web of Science for studies published between January 2022 and August 2025. Eligible studies included original research assessing LLM applications in gastroenterology clinical practice. Data were extracted on subspecialty, application domain, LLM type, data source, and outcomes. We employed thematic analysis to address our primary research question. RESULTS: 73 out of 2895 studies identified in the initial search met the inclusion criteria. Six subspecialties and six application domains emerged from our review. Hepatology (20/73 studies, 27.3%) and endoscopy (17/73 studies, 23.2%) were the most represented subspecialties. The most frequently investigated application domains were patient education and communication (38 studies) and decision support and clinical guidance (24 studies). Most studies were simulation-based or literature-based cases, although an increasing number have used real-world clinical data, particularly in recent years. The majority evaluated general-purpose models such as GPT-3.5 and GPT-4, with some incorporating retrieval augmentation or fine-tuning. Reported outcomes varied by application domain and included measures of accuracy, concordance, completeness, relevance, safety, reliability, usability, user satisfaction, efficiency, time savings, and educational value. Commonly described limitations included variable reliability, incomplete responses, and challenges in generalizing from simulated to clinical settings. CONCLUSIONS: Research on LLMs in gastroenterology has expanded across multiple subspecialties and application domains. Current evidence is primarily based on simulation studies, with limited but growing evaluation using real-world clinical data. Further work is needed to assess performance in prospective and applied clinical contexts.
2 July 2026
Read appraisal →Life sciences
The interplay of plant polysaccharide structure, gut microbiota metabolism, and host health: Mechanisms and perspectives
Plant polysaccharides, as natural biomolecules, possess the capability to modulate the structure and function of gut microbiota, subsequently influencing host health. Nevertheless, the molecular mechanisms underlying their interactions remain insufficiently understood. This article presents a systematic review of the impact of the chemical structure of plant polysaccharides, including monosaccharide composition and types of glycosidic bonds, on the metabolic preferences of gut microbiota. It emphasizes how structural variations in polysaccharides can promote the proliferation of specific gut microbiota, such as Bacteroidetes and Firmicutes. Additionally, the study analyzes critical enzymatic systems, including glycoside hydrolases (GHs) and polysaccharide lyases (PLs), alongside metabolic pathways associated with the production of short-chain fatty acids (SCFAs) that facilitate the degradation of plant polysaccharides by gut microbiota. Furthermore, it explores the influence of these metabolites on conditions such as obesity, diabetes, inflammatory bowel disease (IBD), and non-alcoholic fatty liver disease. The findings provide a robust theoretical framework for enhancing the utilization efficiency of bioactive polysaccharide components through targeted extraction and characterization techniques, thereby fostering potential advancements in innovative nutritional formulations and pharmacological applications.
16 June 2026
Read appraisal →Med (New York, N.Y.)
Sintilimab and lenvatinib plus hepatic arterial infusion chemotherapy and embolization as conversion therapy for uHCC: A phase 2 trial
BACKGROUND: Transarterial chemoembolization (TACE) or systemic treatments are recommended for unresectable hepatocellular carcinoma (uHCC) but have low conversion-to-resection rates. This single-arm phase II trial (PLATIC) aims to investigate the conversion efficacy of PD-1 inhibitor sintilimab, lenvatinib plus TACE and hepatic arterial infusion chemotherapy (TACE-HAIC) in uHCC. METHODS: 57 uHCC patients received 200 mg of sintilimab and lenvatinib (8/12 mg for body weight <60 kg or ≥60 kg) and TACE-HAIC every 3-4 weeks. The primary endpoint was conversion-to-resection rate. A historical-based cohort treated with TACE-HAIC was included as control. FINDINGS: After a median of three treatment cycles, 44 (77.2%; 95% confidence interval [CI], 0.64-0.87]) patients underwent conversion resection. The objective response rates were 80.7% (95% CI, 0.68-0.90) according to modified Response Evaluation Criteria in Solid Tumors (mRECIST) and 43.8% (95% CI, 0.31-0.58) according to RECIST 1.1. Grade ≥ 3 treatment-related adverse events (TRAEs) occurred in 37 (64.9%) patients; no treatment-related deaths were reported. Among the 44 patients receiving resection, the median progression-free survival (PFS) was 17.3 months, and the median overall survival (OS) was unavailable. After inverse probability of treatment weighting analysis, the PLATIC cohort exhibited longer PFS (hazard ratio [HR] = 0.55, 95% CI, 0.33-0.94; p = 0.020) and OS (HR, 0.50, 95% CI, 0.28-0.92; p = 0.029) than the historical cohort. CONCLUSIONS: Sintilimab, lenvatinib, and TACE-HAIC demonstrated favorable conversion-to-resection rates and acceptable TRAEs in uHCC. FUNDING: Supported by grants from the National Natural Science Foundation of China (no. 82172815 and 82272887) and Cancer Innovative Research Program of Sun Yat-sen University Cancer Center (no. PT22040201).
14 June 2026
Read appraisal →Scientific reports
Performance of GPT-based large language models in hepatocellular carcinoma stratification: liver function assessment, BCLC staging, and treatment recommendations.
Large language models (LLMs) like GPT have been proposed to support complex clinical decision-making. This study evaluated the performance of GPT-based LLM in analyzing clinical, radiological, and laboratory data from patients with hepatocellular carcinoma (HCC) to assess liver function, assign BCLC stage, and recommend treatment. Data from 106 HCC patients (82% male, median age 65 [22-86]) were compiled into anonymized integrated reports. Four GPT-versions (4, o1, o3, 5.4) were prompted-using both short and long instructions-to calculate MELD, ALBI, and Child-Pugh scores, assign BCLC stage, and generate treatment recommendations based on current guidelines. Outputs were compared to expert consensus and tumor board decisions. Errors were categorized by type and source. Time and cost analyses compared GPT to clinical staff. All GPT versions achieved high accuracy (> 85%) in liver function assessment, with MELD calculation being the most error-prone. BCLC staging accuracy ranged from 46.2% (version 4) to 84.0% (o3), with misclassification of radiological reports as the main error source. Reasoning-optimized models (o1, o3) performed best for treatment recommendations, achieving an overall accuracy (correct suggestions and acceptable alternatives) of up to 90.6%. In 9-14% of cases, GPT suggestions were retrospectively more guideline-concordant than tumor board decisions. GPT processing was significantly faster and reduced costs by approximately 300- to 1300-fold compared to clinical staff. GPT-based LLMs show potential as decision-support tools for liver function assessment, BCLC staging, and treatment guidance in HCC. Particularly with reasoning-optimized models and detailed prompting, LLMs may serve as valuable adjuncts in multidisciplinary HCC workflows. However, a non-negligible error rate requires expert oversight and further model refinement.
14 June 2026
Read appraisal →BMJ open
Prediction of ICU length of stay, hospital discharge outcomes and discharge location among ICU-admitted patients diagnosed with viral hepatitis using machine learning: a retrospective cohort study of the MIMIC-IV database
BACKGROUND: Hepatitis, a disease characterised by inflammation of the liver, is a leading global health challenge that contributes to over 1.3 million deaths annually, with hepatitis B and C accounting for many of these fatalities. Intensive care unit (ICU) management of patients is particularly challenging due to the complex clinical care and resource demands. Despite advancements in ICU predictive analytics, limited research has specifically addressed hepatitis patients, creating a gap in optimising care for this population. METHODS: This study focuses on predicting ICU length of stay (LoS), hospital discharge outcomes and discharge location for ICU-admitted viral hepatitis patients using a comparative assessment of machine learning (ML) models. Leveraging data from the Medical Information Mart for Intensive Care-IV database, which includes around 94 500 ICU patient records, this study uses sociodemographic details, clinical characteristics and resource utilisation metrics to develop predictive models such as Random Forest, Logistic Regression, Gradient Boosting Machines and Generalised Additive Model with Negative Binomial Regression. RESULTS: Among 3875 ICU-admitted hepatitis patients, Random Forest classification outperformed Logistic Regression in predicting discharge outcomes, achieving higher accuracy (0.87 vs 0.82) and greater discriminative ability (area under the receiver operating characteristic curve 0.95 vs 0.89). For ICU LoS prediction, Random Forest regression applied to log-transformed LoS demonstrated strong performance (R² up to 0.82), while the generalised additive model with negative binomial distribution explained approximately 76% of LoS variance. Prediction of discharge location yielded moderate performance across Gradient Boosting and multinomial logistic regression models (accuracy 0.55 and 0.56), reflecting challenges associated with multi-class imbalance. Variable importance analyses across ML models consistently identified medication counts, procedure counts, comorbidity burden, age, race and total LoS as the most influential predictors of discharge outcomes and discharge location. CONCLUSIONS: This study demonstrates the value of ML models for predicting clinical outcomes for hepatitis patients, including ICU LOS and hospital discharge status. The results underscore the influence of factors like race and age, revealing disparities that must be addressed in predictive care strategies. While the models show promise, challenges such as variability in prolonged stays and limited multiclass prediction accuracy point to the need for ongoing refinement and research.
11 June 2026
Read appraisal →Critical care explorations
Artificial Liver Support Effectively Removes Immunosuppressive Bile Acids From Circulation in Patients With Severe Liver Failure: A Proof of Concept Study
OBJECTIVE: Bile acids that induce immunosuppression through activation of the Takeda G protein-coupled receptor 5 (TGR5) have recently been identified in the circulation of patients with liver failure and sepsis. These bile acids are associated with increased susceptibility to infection and a high short-term mortality. Furthermore, TGR5 activation by bile acids has been implicated in the development of pruritus. However, therapies targeting TGR5-activating bile acids in patients have not yet been reported. This study investigates the effects of two artificial liver support systems, the Molecular Adsorbent Recirculating System (MARS) and the open albumin dialysis (OPAL). DESIGN: Proof of concept study, multicenter study. SETTING: University Hospital Jena, University Hospital Ulm, and University Hospital Münster, Germany. PATIENTS: Patients with severe liver failure, as defined by the Sequential Organ Failure Assessment hepatic sub-score (i.e., bilirubin > 12 mg/dL). INTERVENTIONS: Patients with severe liver failure were randomized to receive one session of MARS or OPAL for 8 hours, followed by crossover to the other treatment on the next day. MEASUREMENTS AND MAIN RESULTS: Bilirubin, circulating total and individual bile acids, albumin function, and TGR5 activation induced by circulating bile acids were assessed before and after each treatment session. Both OPAL and MARS significantly removed bilirubin, as well as individual and total bile acids from circulation. OPAL was superior to MARS in removing protein-bound lipophilic bile acids and restoring patients' albumin function (i.e., albumin-binding capacity, detoxification efficiency, and binding efficiency). TGR5 activation induced by circulating bile acids was reduced by 60% with OPAL compared with 39% with MARS (median values, p = 0.051). CONCLUSIONS: Artificial liver support systems effectively remove immunosuppressive bile acids from circulation. The clinical implications of bile acid reduction, however, require further study.
11 June 2026
Read appraisal →JMIR research protocols
Implementation of Mobile-Based Programs for Alcohol Cessation in the Treatment of Alcohol-associated Liver Disease: Protocol for a Type 1 Hybrid Implementation-Effectiveness Trial
BACKGROUND: The rising burden of alcohol-associated liver disease (ALD) calls for effective interventions. Alcohol cessation remains the only intervention known to reduce long-term ALD morbidity and mortality. Integrating treatment for alcohol use disorder with medical and hepatology care shows significant promise. OBJECTIVE: This study aims to conduct a randomized, controlled, type 1 hybrid implementation-effectiveness trial in patients with ALD to evaluate an evidence-based smartphone app for alcohol use disorder (Connections). The primary aim is to (1) compare the effectiveness of the Connections app plus usual care to the effectiveness of usual care alone on days of alcohol abstinence for patients with ALD and (2) assess the implementation of the Connections app in the ALD population using a multilevel model of system change to determine facilitators and barriers to the successful adoption of the app at the patient, provider, and clinic levels. METHODS: Study procedures were approved by the Institutional Review Board on March 13, 2024. Patients are recruited from General Hepatology and Multidisciplinary Clinics in Wisconsin and Michigan. Participants are randomized to an intervention (Connections + treatment as usual) or no intervention (treatment as usual). During the 6-month enrollment period, participants complete monthly e-surveys measuring alcohol consumption and quarterly e-surveys measuring patient health indicators and behaviors. Patients earn up to US $240 for participation. RESULTS: This study was funded in September 2023. Recruitment began in June 2024 and is ongoing. As of February 26, 2026, 144 participants have been enrolled in the study. Of these, 65 (45.1%) have completed all the study activities. We aim to recruit 298 participants through 2027, with analysis and results publication estimated in 2028. CONCLUSIONS: Implementation insights highlight the importance of flexibility and strong provider relationships. Challenges include reliance on technology, which limits access for patients with low digital literacy, and the risk of loss to follow-up. This trial is the first fully powered implementation-effectiveness study of a mobile health app for alcohol cessation in ALD, testing a new care model that integrates multidisciplinary expertise. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/94231.
1 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 radiation research
Deep learning-based dose prediction in proton beam therapy for hepatocellular carcinoma: comparison of network architectures and loss functions
In proton beam therapy (PBT) for hepatocellular carcinoma (HCC), deep learning (DL)-based dose prediction offers clinical value by providing immediate reference dose distributions as a guideline tool for treatment planners and enabling virtual PBT dose assessment at institutions lacking PBT facilities to support clinical decision-making. This study proposes a dose gradient-aware DL training approach and a beam arrangement-free framework that predicts dose distributions from computed tomography (CT) images and target/organs-at-risk structures without requiring beam arrangement inputs. Using data from 172 HCC patients, we systematically compared 20 DL models combining five architectures with four loss functions, including a novel dose gradient-aware loss capturing PBT-specific dose distribution characteristics arising from the Bragg peak. Prediction accuracy was evaluated using dose metrics for clinical target volume, planning target volume, and normal liver, 10% dose region volume assessment, visual examination, Dice similarity coefficient (DSC) for 10% dose region, and dose-volume histogram (DVH) analysis. DL models employing dose gradient-aware loss demonstrated reduced prediction errors in target volume dose metrics, achieved the lowest errors in 10% dose region volume when combined with U-Net (MAE: 35.4 cm3, RMSE: 51.3 cm3), attained the highest DSC (0.88 ± 0.05), showed the closest DVH agreement with clinical plans for both target structures and normal liver. A comprehensive evaluation consistently confirmed the superiority of dose gradient-aware loss across all metrics, demonstrating the importance of physics-informed, dose gradient-aware learning for accurate PBT dose distribution prediction. Particularly, DL models combining simple architectures with dose gradient-aware loss predicted doses that closely approximated clinical doses in PBT.
27 May 2026
Read appraisal →Clinical and experimental dermatology
An open-label phase II study of bitopertin in adults and adolescents with erythropoietic protoporphyria or X-linked protoporphyria
BACKGROUND: Erythropoietic protoporphyria (EPP) and X-linked protoporphyria (XLP) are rare genetic disorders characterized by accumulation of protoporphyrin IX (PPIX), painful phototoxic reactions and hepatobiliary disease. No disease-modifying therapies are approved for these conditions. OBJECTIVES: To evaluate the safety and efficacy of bitopertin in adults and adolescents with EPP or XLP. METHODS: BEACON (ACTRN12622000799752) was a phase II, randomized, open-label, parallel-arm study in adult and adolescent participants with EPP or XLP. Participants received an oral, once-daily administration of bitopertin 20 mg or 60 mg for 24 weeks. RESULTS: Twenty-six participants were randomized to 20 mg (n = 14) or 60 mg (n = 12) of bitopertin. The study met its primary efficacy endpoint. Treatment with bitopertin resulted in significant, dose-dependent reductions in PPIX levels compared with baseline at both the 20-mg and 60-mg dose levels (mean -31.7%, SE 7.0; P < 0.001 vs. baseline and mean -57.7%, SE 7.4; P < 0.001 vs. baseline, respectively). Similar efficacy was observed across the adult and adolescent populations. No serious adverse events were reported. Dizziness was the most common adverse event reported with bitopertin, in 9 (64%) and 8 (67%) participants completing the study in the 20-mg and 60-mg dose groups, respectively. CONCLUSIONS: By reducing whole-blood PPIX levels, bitopertin targets the underlying pathophysiology of EPP, resulting in consistent improvements in multiple measures of light tolerance and quality of life. Bitopertin was well tolerated, and most adverse events were mild or moderate in severity.
27 May 2026
Read appraisal →Hepatology communications
Midodrine versus placebo in patients with acute-on-chronic liver failure with ascites-A randomized trial (MIDAS trial)
BACKGROUND: Ascites is common in patients with acute-on-chronic liver failure (ACLF) and can complicate the course of ACLF due to circulatory dysfunction and hemodynamic compromise. Oral midodrine has been variably reported to improve hemodynamics and reduce complications of ascites in patients with decompensated cirrhosis, but its role in patients with high MELD ACLF remains unknown, which we aimed to assess. METHODS: In this single-center, double-blind, randomized trial, patients with ACLF were assigned 1:1 to receive midodrine (5-7.5 mg tid) or a placebo for 30 days, alongside standard care. Transplant-free survival (TFS) at 1 month was the primary outcome, while secondary outcomes included TFS at 3 months, the proportion of patients achieving ascites control, changes in mean arterial pressure (MAP) and plasma renin activity at 1 month, the incidence of cirrhosis complications, and diuretic-related complications. RESULTS: One hundred thirty patients with ACLF were enrolled. Midodrine use was not associated with improvement in TFS at 1 (HR, 0.99 [95% CI: 0.37-2.65]) and 3 months (HR, 0.93 [95% CI: 0.48-1.8]). Ascites control at day 30 (placebo: 9.2% [95% CI: 3.5-19] vs. midodrine: 20% [95% CI: 12.3-33.5]; p=0.08) and 90 (placebo: 44.6% [95% CI: 32.2-57.5] vs. midodrine: 53.8% [95% CI: 41-66.3]; p=0.29) was comparable. Midodrine increased the MAP (1.9 vs. 6.9 mm Hg; p=0.003) with an insignificant reduction in plasma renin activity levels (delta change: 0.22±1.6 vs. -1.6±2.2; p=0.09). Cirrhosis-related and diuretic-related complications were similar in both groups. CONCLUSIONS: Midodrine increases MAP in patients with ACLF and high MELD scores without TFS benefit and does not reduce the rate of ascites-related complications.
25 May 2026
Read appraisal →Medicine
Mechanisms linking primary biliary cholangitis and osteoporosis: A combined clinical and molecular analysis
Primary biliary cholangitis (PBC) is an immune-mediated cholestatic liver disease, and osteoporosis (OP) is a prevalent comorbidity that aggravates the disease burden of PBC patients. Although the co-occurrence of the 2 diseases has been widely observed, the underlying molecular mechanisms remain unclear. Herein, we evaluated the causal link between PBC and OP using Mendelian randomization (MR) and explored shared molecular mechanisms through bioinformatics and machine learning. We performed two-sample MR using genome-wide association study summary data for PBC and OP from the Integrative Epidemiology Unit database. Inverse-variance weighting was used as the primary MR method, with heterogeneity and horizontal pleiotropy tests performed to exclude potential biases. To explore shared molecular mechanisms, we analyzed transcriptomic datasets from the Gene Expression Omnibus database, identified comorbidity-associated differentially expressed genes, and applied multiple machine learning algorithms for biomarker screening and validation, combined with immune infiltration analysis. Our study showed that MR demonstrated that PBC significantly increases the risk of OP, while transcriptomic analysis identified 36 shared differentially expressed genes enriched in key biological pathways such as ribonucleic acid splicing and ubiquitin-mediated proteolysis. Furthermore, using 3 machine learning algorithms, we identified 12 PBC-specific and 4 OP-specific diagnostic genes, whose intersection revealed vacuolar protein sorting 37 homolog C (VPS37C) as a common diagnostic biomarker. In both diseases, VPS37C exhibited an area under the receiver operating characteristic curve value >0.7, demonstrating its robust predictive performance. In addition, VPS37C expression was found to be significantly correlated with the infiltration landscape of multiple immune cell types in both PBC and OP. This study identified VPS37C as a shared diagnostic gene linking PBC and OP, providing new insights into their comorbidity at both genetic and immune levels. Our findings further elucidate the molecular mechanisms underlying the comorbidity of PBC and OP, offer novel clues for understanding their pathogenesis, and highlight promising diagnostic and therapeutic targets for clinical application.
24 May 2026
Read appraisal →BMJ open
What are the views of cancer care administrators and clinicians in England on the use of a machine learning clinical decision support system (ML-CDSS) to predict patients' risk of hepatic and renal deterioration during chemotherapy? A qualitative study.
OBJECTIVE: To explore administrators' and clinicians' views on the factors that influence their use and adoption of a machine learning clinical decision support system (ML-CDSS) to predict patients' risk of hepatic and renal deterioration during chemotherapy. METHODS AND ANALYSIS: This was a qualitative study that used purposive sampling. 18 participants with administration and clinical backgrounds working in cancer care in England were recruited. Qualitative data were collected by conducting semi-structured interviews and a focus group. Data were analysed thematically using the framework method to identify key themes. RESULTS: Participants acknowledged that monitoring blood chemistry is a core component of chemotherapy as it helps clinicians assess patient fitness and treatment response. The ML-CDSS was perceived as a potentially valuable tool for identifying patients at increased risk of hepatic and renal deterioration, supporting clinical decision-making and enhancing care efficiency. However, several concerns were raised regarding its potential implementation in practice. Participants questioned clinicians' willingness and capacity to integrate the tool into their existing workflows. Participants also believed it was important to demonstrate the ML-CDSS's sensitivity, specificity and validity in accurately predicting patients' risk to build clinicians' trust in the tool, demonstrating evidence of its efficacy and effectiveness in practice. CONCLUSION: Administrators and clinicians recognised the potential benefits of the ML-CDSS to enhance the delivery of chemotherapy by identifying patients at risk for hepatic and renal deterioration. Successful adoption in practice depends on building trust with the tool by being transparent in its development, its effectiveness and impact. Future work should demonstrate the ML-CDSS being used in practice to generate real-world evidence.
20 May 2026
Read appraisal →Signal transduction and targeted therapy
HILL: the efficacy and safety of hepatic arterial infusion chemotherapy with the FOLFOX regimen combined with lenvatinib and the PD-L1 inhibitor durvalumab in unresectable hepatocellular carcinoma: a prospective, single-arm, phase 2 clinical trial
Despite numerous available treatment options, the overall prognosis for patients with unresectable hepatocellular carcinoma (uHCC) remains poor. This study aimed to evaluate the efficacy and safety of combining hepatic arterial infusion chemotherapy with FOLFOX (FOLFOX-HAIC), lenvatinib, and the PD-L1 inhibitor durvalumab in this population, with all uHCC patients receiving the triple-combination regimen as initial therapy. The primary objective was progression-free survival (PFS), and secondary outcomes included objective response rate (ORR), disease control rate (DCR), overall survival (OS), and safety. From August 2021 to September 2023, 40 uHCC patients were enrolled, with a median follow-up of 23.1 months (95% confidence interval [CI], 19.0-23.8); 3 deaths and 12 disease progressions were recorded. The median PFS was 15.8 months (95% CI, 8.3-23.3) with a 6-month PFS rate of 77.5% (95% CI, 63-90%), and 1- and 2-year OS rates were 97.5% and 94.0%, respectively. Per modified RECIST criteria, ORR was 75.0% (9 CR/pCR, 21 PR) and DCR was 95.0% (8 SD); median time to response (TTR) was 2.2 months and median duration of response (DOR) was 10.4 months. Seven patients (17.5%) underwent R0 conversion surgery, 3 (42.9%) achieving pCR. Safety was favorable: 85.0% had grade 1-2 adverse events, with grade 3 elevated alanine aminotransferase and thrombocytopenia each occurring in 2 patients (5.0%). No grade 4 adverse events were observed. Collectively, the triple-combination therapy of FOLFOX-HAIC, lenvatinib, and durvalumab exhibits promising therapeutic efficacy, favorable disease control, and a well-tolerated safety profile, providing a potential new treatment option for patients with uHCC. Trial number: NCT04961918.
18 May 2026
Read appraisal →Clinica chimica acta; international journal of clinical chemistry
AI in the Prediction of Hepatic Fibrosis Progression Using Non-Coding RNAs
Hepatic fibrosis is a dynamic and progressive condition that can lead to cirrhosis and hepatocellular carcinoma (HCC) if left untreated. Appropriate assessment of the disease progression of fibrosis is critical for early intervention and individualized treatment regimens. Traditional biopsy techniques are invasive and prone to sampling errors, highlighting the need for less invasive predictive techniques. Non-coding RNAs (ncRNAs), including microRNAs (miRNAs), long ncRNAs (lncRNAs), and circular RNAs (circRNAs), have emerged as key regulators of hepatic fibrogenesis and as a possible biomarker for disease staging and prognosis. The emergence of artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), has revolutionized the comprehensive large-scale analysis of transcriptomic data, enhancing the identification of ncRNA biomarkers and predictive modeling. The AI-based algorithms have been found to be more precise in anticipating fibrosis progression by means of integrating multi-omics data, ncRNA interaction networks, and by improving non-invasive diagnostic tools. This review involves the analysis of AI and ncRNA research in hepatic fibrosis, highlighting recent discoveries, possible challenges, and future opportunities. We address the necessity of standardization of data and clinical validation, as well as discuss the role of AI in identifying biomarkers of ncRNA, predicting the stage of fibrosis and risk stratification. ncRNA analysis with AI has a tremendous potential of transforming the diagnostics and prognostics of hepatic fibrosis, enabling precision hepatology.
17 May 2026
Read appraisal →Clinical cancer research : an official journal of the American Association for Cancer Research
Pembrolizumab Monotherapy in Sorafenib-Treated and Treatment-Naïve Advanced Hepatocellular Carcinoma: Long-Term Follow-up of the Open-Label, Phase II KEYNOTE-224 Study
PURPOSE: In the phase II KEYNOTE-224 study, pembrolizumab showed durable antitumor activity and manageable safety in participants with sorafenib-treated (cohort 1) or treatment-naïve (cohort 2) advanced hepatocellular carcinoma (HCC). We present data after a median follow-up of ∼7 years for cohort 1 and ∼5 years for cohort 2. PATIENTS AND METHODS: Adults with advanced HCC received pembrolizumab 200 mg intravenously every 3 weeks until disease progression or unacceptable toxicity for ≤35 cycles. The primary endpoint was objective response rate per Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST v1.1) by blinded independent central review. Secondary endpoints included overall survival (OS), progression-free survival (PFS), and safety. RESULTS: Overall, 155 participants received ≥1 dose of pembrolizumab (cohort 1, n = 104; cohort 2, n = 51). The median follow-up was 83 months (range, 79.3-87.3) for cohort 1 and 58.8 months (range, 55.3-60.8) for cohort 2. The median OS was 13.2 months [95% confidence interval (CI), 9.7-15.3] and 16.9 months (95% CI, 8.3-23.1), respectively; 24- and 48-month OS rates were 31%/17% and 34%/20%, respectively. The median PFS was 4.9 months (95% CI, 3.5-7) and 4.3 months (95% CI, 2.1-7.8), respectively. Treatment-related adverse events occurred in 76 participants [73.1%; grade 3-5, 27 (26%)] in cohort 1 and 28 participants [54.9%; grade 3-5, 8 (15.7%)] in cohort 2. CONCLUSIONS: Pembrolizumab continued to show durable response and manageable safety in participants with advanced HCC with or without prior systemic therapy, with long-term effects on OS lasting beyond 48 months in some participants despite receiving study treatment for ≤2 years.
17 May 2026
Read appraisal →Clinical cancer research : an official journal of the American Association for Cancer Research
Allogeneic B7-H3-Targeted CAR Vδ1T-cell Therapy in Advanced Solid Tumors: A Phase I Study
PURPOSE: The aim of the study was to evaluate the safety, pharmacokinetics, and preliminary clinical activity of UTAA06, an "off-the-shelf" allogeneic B7-H3-targeted chimeric antigen receptor (CAR) Vδ1T-cell therapy, in patients with pretreated, advanced B7-H3-positive solid tumors. PATIENTS AND METHODS: In this first-in-human, phase I, dose-escalation study (NCT06372236), 10 patients with advanced solid tumors (including gastric, colorectal, hepatocellular, ovarian, and neuroendocrine cancers) were enrolled. Following lymphodepletion chemotherapy (cyclophosphamide and fludarabine), patients received UTAA06 infusion across three dose levels (5 × 108, 8 × 108, or 1 × 109 cells). The primary endpoint was safety. Secondary endpoints included pharmacokinetics and antitumor efficacy. RESULTS: UTAA06 demonstrated a manageable safety profile; no GVHD was observed, and cytokine release syndrome was limited to two transient grade 1 events. A single dose-limiting toxicity (grade 3 pneumonitis) was reported in one patient at the 5 × 108 cell dose level. Although UTAA06 demonstrated signals of biological activity, including transient reductions in serum tumor markers in 50% of patients, no objective response by RECIST v1.1 criteria was observed. Further analysis identified that the limited CAR T-cell persistence was likely driven by subclinical host-versus-graft rejection. CONCLUSIONS: This study provides clinical proof of concept for allogeneic B7-H3-targeted CAR-Vδ1T cells as a safe platform with low risk of GVHD and demonstrable biological activity in solid tumors. However, clinical efficacy was constrained by limited cellular persistence caused by host immune rejection. Future strategies are required to enhance the durability and therapeutic potential of this allogeneic approach.
17 May 2026
Read appraisal →Computers in biology and medicine
Generative deep learning-driven de novo design of targeted MAP4K6 inhibitors
The discovery of selective small-molecule inhibitors for pharmacologically underexplored kinases remains a critical barrier to precision drug development, particularly under data-sparse conditions, where ligand annotations are scarce. Here, we present MolEvoRNN, a generative deep learning (GDL) model that enables the de novo design of chemically valid, structurally diverse, and target-adapted compounds in low-data regimes. Through transfer learning and temperature-controlled sampling, MolEvoRNN efficiently navigates the kinase-relevant chemical space while preserving scaffold novelty, drug-likeness, and synthetic tractability. Applied to MAP4K6, a poorly characterized serine/threonine kinase implicated in hepatocellular carcinoma (HCC), MolEvoRNN generated >49,000 chemically valid molecules with >80% novel Bemis-Murcko scaffolds. MolEvoRNN outperformed the baseline GDL models across key generative metrics, including diversity (1.00), uniqueness (1.00), novelty (1.00), and internal diversity (0.869), demonstrating broad chemical exploration with minimal redundancy. A multilayered virtual screening cascade combining QSAR modeling, pharmacophore mapping, molecular docking, MM-GBSA binding energy estimation, and 1000 ns molecular dynamics simulations identified three lead candidates MINK-5730, MINK-13510, and MINK-16516 with high predicted affinity, favorable ADMET properties, and robust dynamic stability. Unlike end-to-end optimization pipelines, MolEvoRNN decouples generation from evaluation, promoting methodological transparency and rigorous post-hoc triaging. This study establishes a scalable, generalizable paradigm for rational small-molecule design in underexplored target spaces, bridging generative deep learning with structural pharmacology to accelerate early-phase therapeutic discovery.
17 May 2026
Read appraisal →Computers in biology and medicine
Artificial intelligence for metabolic dysfunction-associated steatotic liver disease diagnosis: A systematic review
Metabolic dysfunction-associated steatotic liver disease (MASLD) poses significant diagnostic challenges. We conducted a systematic review of artificial intelligence (AI) applications in MASLD diagnosis, focusing on predictive modeling, screening, imaging analysis, and therapeutic assistance. Following PRISMA guidelines, we searched five databases (Web of Science, SciFinder, Elsevier ScienceDirect, EBSCOhost, Springer) for studies published January 2020-January 2026. Of 1247 initially identified records, 191 studies met inclusion criteria. AI models demonstrate high diagnostic performance across multiple modalities. Deep learning analysis of US, CT, and MRI enables automated steatosis quantification and fibrosis staging with accuracy comparable to expert interpretation. AI integration with multi-omics data facilitates novel biomarker discovery and therapeutic target identification. Despite these advances, model generalisability, standardization, and clinical integration remain challenges. AI holds substantial potential to transform MASLD diagnostics, but prospective validation and implementation strategies are needed before widespread clinical adoption.
16 May 2026
Read appraisal →Gut
Simvastatin in the prevention of recurrent pancreatitis: a triple-blinded randomised clinical trial (the SIMBA trial)
BACKGROUND: Recurrent acute pancreatitis (RAP) or acute-on-chronic flares in chronic pancreatitis (CP) have limited preventive options beyond addressing the underlying aetiology. Statins, due to their anti-inflammatory properties, have been proposed as a potential prophylactic treatment. OBJECTIVE: We aimed to evaluate whether simvastatin could reduce the recurrence of pancreatitis. DESIGN: At 23 centres, we conducted a triple-blind, randomised, controlled, superiority trial enrolling patients with at least two episodes of RAP or CP flares in the previous 12 months. Participants were randomly assigned to receive simvastatin or placebo for 1 year. The primary endpoint was the recurrence of pancreatitis. The target sample size was 144 patients; however, an interim analysis was planned in the event of slow recruitment. RESULTS: A total of 85 patients (42.1% women) were included in the interim analysis. In the intention-to-treat analysis, no significant differences were observed regarding recurrence: 46.2% simvastatin versus 44.4% placebo; OR 1.07, 95% CI 0.43 to 2.66; p=0.88, or time to recurrence. No statistically significant differences were observed in recurrence in per-protocol analysis (35.5% simvastatin vs 41.9% placebo; OR 0.76, 95% CI 0.27 to 2.12; p=0.60). Development of diabetes mellitus was more frequent in the simvastatin group (4 vs 0 patients; OR not calculable, p=0.04). CONCLUSION: This trial, evaluating simvastatin versus placebo for the prevention of pancreatitis, did not demonstrate a reduction in recurrence rate, although results might be underpowered due to early termination. The relationship between statins in these patients and new-onset diabetes requires further investigation. TRIAL REGISTRATION NUMBER: NCT04021498.
14 May 2026
Read appraisal →Journal of chemical information and modeling
In Silico Prediction of Potential Bile Salt Export Pump Inhibitors Using Pharmacophore Models and Consensus Machine Learning
The ATP-dependent bile salt export pump (BSEP) is a transporter responsible for moving bile salts from hepatocytes into bile canaliculi. Inhibition of BSEP is a known risk factor of cholestatic-drug-induced liver injury (DILI) probably caused by the accumulation of toxic bile salts in the liver. Since DILI is a major cause for attrition during drug development and postmarketing withdrawal or black box warnings, an IC50 of BSEP higher than 25 μM is advised. Here, we describe the investigation of several in silico approaches to map potential BSEP inhibitors. A consensus machine learning classification model is presented, which accurately predicts BSEP inhibitors and can assist in the prioritization of in vitro testing. An applicability domain was derived for the model, and it was validated by in vitro measurements of predicted BSEP inhibitors where the model was able to correctly flag eight out of 11 compounds.
13 May 2026
Read appraisal →Pediatric surgery international
Development of a machine learning-based prognostic prediction model and a web-based tool for pediatric hepatoblastoma: a Surveillance, Epidemiology, and End Results (SEER) database study
BACKGROUND: Prognostic evaluation of pediatric hepatoblastoma (HB) remains challenging due to the low accuracy of traditional risk stratification models. This study aims to leverage the U.S. Surveillance, Epidemiology, and End Results (SEER) database to develop and compare several machine learning-based survival models and create an online prediction tool for individualized survival probability estimation in children with HB. METHODS: A total of 614 pediatric HB patients diagnosed from 2000 to 2021 in the SEER database were identified and randomly split (7:3 ratio) into a training set (n = 429) and an internal hold-out validation cohort (n = 185). This split was selected to retain sufficient data for model development while preserving an adequate validation cohort for performance assessment. Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis was used for feature selection, and three prognostic prediction models (Cox regression, random survival forest (RSF), and a deep learning-based survival (DeepSurv) neural network) were developed using the training data. Model performance was evaluated by Harrell's concordance index (C-index), time-dependent area under the receiver operating characteristic (ROC) curve (AUC) at 1, 3, and 5 years, and decision curve analysis (DCA). We also used SHapley Additive exPlanations (SHAP) analysis to interpret the RSF model. Based on RSF-derived risk scores, patients were classified into high-, intermediate-, and low-risk groups for survival analysis. Ultimately, a web-based tool was developed to enable real-time prediction of 1-, 3-, and 5-year survival probabilities using individual patient characteristics. RESULTS: In the validation cohort, the RSF model achieved the highest C-index (0.745), outperforming the DeepSurv (0.720) and Cox regression models (0.709). The RSF also yielded favorable 1-year, 3-year, and 5-year AUC values, and DCA indicated a greater net benefit across clinically relevant threshold probabilities. SHAP analysis highlighted distant-stage disease, surgical treatment status, and tumor extent as key factors influencing survival predictions. Kaplan-Meier curves stratified by the RSF risk groups showed significantly different survival outcomes among high-, intermediate-, and low-risk patients (log-rank P < 0.001 for all comparisons). The finalized online tool allows users to input patient characteristics and obtain estimated 1-year, 3-year, and 5-year survival probabilities, which may assist individualized prognostic assessment as an adjunctive reference. CONCLUSION: The RSF-based prognostic model showed favorable predictive performance compared with the Cox and DeepSurv models in this retrospective SEER-based cohort of pediatric HB. With interpretable model outputs and an accessible web-based interface, the model may serve as an adjunctive tool for individualized risk assessment. However, external validation and prospective evaluation are required before routine clinical implementation.
13 May 2026
Read appraisal →European journal of cancer (Oxford, England : 1990)
Stereotactic body radiotherapy versus hepatic resection for recurrent small hepatocellular carcinoma: A post-hoc analysis with propensity score adjustment from two randomized trials
BACKGROUND: Stereotactic body radiotherapy (SBRT) has been proven effective for treating small hepatocellular carcinoma (sHCC); however, the comparative efficacy of SBRT and surgical resection remains unknown. This analysis aims to compare the outcomes of SBRT and resection in treating recurrent sHCC. METHODS: Two randomized controlled trials enrolled recurrent sHCC undergoing resection (NCT01833286) or SBRT (NCT04047173). Patients with single recurrent HCC ≤ 5 cm were included in this study. The primary endpoint was local progression-free survival (LPFS). RESULTS: A total of 158 patients were included, with 83 and 75 patients assigned to the SBRT and resection cohorts, respectively. The cumulative 3-year LPFS rates were 84.3% (95% CI, 76.1-92.5) with SBRT and 76.8% (95% CI, 67.2-86.4) with resection, respectively (HR, 0.70 [95% CI, 0.35-1.40]; P = 0.311). The median progression-free survival time of the SBRT and resection group was 37.6 (95% CI, 26.0-49.2) and 26.3 (95% CI, 18.8-33.8) months, respectively, with no significant differences (HR, 0.80 [95% CI, 0.53-1.21]; P = 0.287). The 3-year overall survival rates were 90.3% (95% CI, 83.4-97.2) in the SBRT group, and 81.1% (95% CI, 76.5-90.1) in the resection group (HR, 0.53 [95% CI, 0.23-1.20]; P = 0.118). The comparison results remained consistent after adjusting for confounding variables. The incidences of adverse events were similar between the two groups (P = 0.695). CONCLUSIONS: SBRT provides satisfactory tumor control and long-term outcomes, comparable to those of resection. SBRT could be a potential alternative to resection in recurrent sHCC.
10 May 2026
Read appraisal →European journal of nuclear medicine and molecular imaging
Machine learning models classifiers enable a strong prediction of radioembolization-induced liver disease, and define a new bilirubin threshold for selection of patients.
PURPOSE: Selective Internal Radiotherapy (SIRT) is an established treatment option for hepatocellular carcinoma (HCC). However, a major complication is radioembolization-induced liver disease (REILD). METHODS: This retrospective study, analyzed patients treated with SIRT for HCC to identify clinical factors associated with REILD and to predict treatment response. Machine learning (ML) methods were applied to two distinct cohorts to determine predictors of toxicity and response. RESULTS: Among 138 patients analyzed for REILD, ML identified bilirubin as a key predictor. A refined threshold of 26.5 µmol/L (1.55 mg/dL) was associated with toxicity risk. In the response cohort (136 patients), predictive performance was limited, nevertheless tumor dose appeared as the most frequent feature selected by the models. CONCLUSIONS: Bilirubin was confirmed as a critical factor for REILD prediction with the identification of a new threshold that may improve patient risk stratification. While tumor dose appears as the main predictor of treatment outcome, robust response models require additional features.
5 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 →The Korean journal of gastroenterology = Taehan Sohwagi Hakhoe chi
Toward Precise Risk Stratification after the Functional Cure of Chronic Hepatitis B
Chronic hepatitis B remains a major global health challenge despite the advances in antiviral therapy. Although hepatitis B surface antigen (HBsAg) seroclearance is considered a functional cure, liver-related complications, particularly hepatocellular carcinoma, may still occur after viral clearance. This residual risk reflects the lasting impact of host and liver factors rather than ongoing viral activity. Conventional prediction models have attempted to stratify the residual risk after a functional cure but remain limited in their ability to guide individualized management. Recent advances in machine learning have enabled more precise risk stratification by capturing complex host-driven determinants of the long-term outcomes. These approaches support a shift from uniform surveillance toward risk-adaptive monitoring strategies. Nevertheless, post-cure management is emerging as a new clinical priority as more patients achieve a functional cure. Therefore, a functional cure should be viewed not as the end of the disease, but as the beginning of a phase requiring personalized risk assessment and surveillance.
28 Apr 2026
Read appraisal →ACS sensors
Laser-Engineered MXene Heterostructure for Wearable Ammonia Sensors
Exhaled ammonia is a vital biomarker for clinical diagnosis of hepatorenal dysfunction and metabolic disorders. However, conventional sensors are often limited by complex fabrication processes, high operating temperatures, and particularly, compromised selectivity under high-humidity conditions. To overcome these challenges, we developed a laser-assisted heterostructure engineering strategy that enables in situ construction of Schottky barrier in MXene/polyacrylonitrile (PANF) nanofiber membranes, termed as a laser-engineered MXene (LEM) sensor. The laser micropatterning technique provides three key innovations: (1) kinetically controlled deposition of MXene (Ti3C2Tx) with minimal oxidation, (2) self-aligned formation of Schottky barriers through interfacial TiO2/MXene heterojunctions, and (3) creation of hierarchical gas transport channels within the 3D nanofibrous matrix. The optimized LEM sensor exhibits outstanding sensitivity (2.5% ppm-1), a low detection limit (0.2 ppm) at room temperature (25 °C), and humidity operation stability (> 10% response at 90% relative humidity). This performance surpasses that of conventional MXene-based sensors by fivefold in sensitivity without the need for thermal activation. Mechanism studies reveal that the laser-induced heterointerface facilitates charge transfer-dominated ammonia adsorption and desorption kinetics, while the nanofibrous architecture ensures molecular accessibility to active sites. This ambient-processable and scalable fabrication method paves the way for advanced wearable breath analyzers by combining manufacturing versatility, humidity-resistant excellent selectivity, and energy-efficient operation.
26 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 →PloS one
Hepatitis C distribution across diverse population groups in the Eastern Mediterranean Region: An umbrella review
BACKGROUND: Hepatitis C virus (HCV) remains a major public health challenge in the Eastern Mediterranean Region (EMR), with prevalence varying across population groups. This umbrella review summarizes the distribution of HCV infection across diverse populations in the region. METHODS: We conducted an umbrella review of systematic reviews with meta-analyses reporting HCV prevalence in the EMR. PubMed, Web of Science, Scopus, Iranian databases, including Magiran and the Scientific Information Database (SID), were searched. Google Scholar was additionally screened to ensure comprehensive coverage. Pooled estimates were extracted across four population groups: apparently healthy individuals; those with clinical or healthcare-associated exposure risk; patients co-infected with hepatitis viruses or other liver-related diseases; and key populations at increased risk (groups disproportionately affected due to their behaviors and higher vulnerability). For time-period analyses, meta-analyses were grouped into two intervals (before 2015 vs. 2015 and after) based on the median year of data collection of primary studies. Pooled prevalence was calculated using a random-effects model in STATA version 17. RESULTS: A total of 55 meta-analyses were included. The pooled HCV prevalence was 31.0% (95% CI: 27.0-38.0) among key populations, and also 31.0% (95% CI: 12.0-49.0) among patients co-infected with other hepatitis viruses or liver-related diseases. Those with clinical or healthcare-associated exposure risk showed a prevalence of 28.0% (95% CI: 23.0-32.0), whereas the apparently healthy population had the lowest prevalence at 2.0% (95% CI: 1.0-2.0). Subgroup analysis indicated a decline in prevalence among clinically exposed populations after 2015, from 29% to 10%, coinciding with the direct-acting antivirals (DAAs) and strengthened infection-control practices. The highest prevalence was observed among key populations in Libya, healthcare-exposed populations in Morocco, and apparently healthy individuals in Egypt. CONCLUSION: Variation in HCV prevalence across populations in the EMR highlights the need for population-specific strategies to support progress toward World Health Organization elimination targets.
24 Apr 2026
Read appraisal →Nature communications
Donor-derived regulatory dendritic cell infusion and early immunosuppressive drug withdrawal in living-donor liver transplantation: a phase I/IIa trial
Operational tolerance (OT) following complete immunosuppression withdrawal (ISW) is rare ( ~ 13%) in eligible adult liver transplant recipients when initiated 1-2-years post-transplant. Regulatory dendritic cells (DCregs) promote transplant tolerance in pre-clinical models and attenuate immune effector cells in humans. Here, we completed a first-in-human phase I/IIa trial (2-year recruitment; 5 ± 0.5 years follow-up) to evaluate the feasibility, safety and preliminary efficacy of pre-emptive donor-derived DCreg (ddDCreg) infusion 7-days pre-transplant in 15 prospective living-donor liver recipients. Two patients were excluded from analysis for reasons unrelated to the study. ISW began one year post-transplant in candidates with a quiescent/permissive protocol biopsy. ddDCreg infusions were safe, reproducible, and well-tolerated. One-year post-transplant, 8/13 patients were eligible for ISW, 4 achieved complete ISW, 3 remained off all immunosuppression for >1 year. These 3 remained drug-free for 3.0 ± 0.17-years, reflecting a 37.5% OT rate in ISW-eligible recipients. Given the exploratory nature of this trial, additional studies to evaluate efficacy are needed. ClinicalTrials.gov registration number NCT03164265.
19 Apr 2026
Read appraisal →The Journal of clinical investigation
Carriage of rare APOB variants predisposes to severe steatotic liver disease and hepatocellular carcinoma
BACKGROUNDMetabolic dysfunction-associated steatotic liver disease (MASLD) has a substantial inherited component. Rare variants in apolipoprotein B gene (APOB) have been implicated in susceptibility to liver steatosis, but their role in disease progression and outcomes is unclear.METHODSWe investigated APOB rare variants in a case-control cohort of people with advanced MASLD versus healthy controls (n = 510 and 261, respectively), a family-based study (n = 43 and literature meta-analysis), the Million Veteran Program (MVP) cohort (n = 94,885), and the UK Biobank (UKBB) (n = 417,657).RESULTSIn the clinical cohort, APOB variants were enriched in people with advanced MASLD (OR 13.8, 95% CI: 2.7-70.7, P = 0.002) and associated with lower circulating lipids, but higher MASLD activity and fibrosis (P < 0.05). In the family study, APOB variants segregated with hepatic steatosis and fibrosis (P < 0.05). Cross-ancestry meta-analysis of the study cohorts yielded pooled ORs for cirrhosis and hepatocellular carcinoma (HCC) of 1.82, 95% CI: 1.33-2.49 and 3.53, 95% CI: 2.09-5.98, respectively. Variants affecting specifically ApoB100 had a 3-fold greater effect on hepatic lipid metabolism compared with those impairing also ApoB48 and were specifically protective against coronary artery disease (P < 0.05). The variants affected cirrhosis risk similarly, but ApoB48/100 had a larger effect on HCC (P < 0.05).CONCLUSIONSRare APOB variants predispose individuals to advanced MASLD and HCC, with distinct contributions from disrupted VLDL and chylomicrons secretion. These findings highlight the interplay between hepatic and intestinal lipid handling, suggesting that APOB genotyping may enhance MASLD risk stratification and patient identification.FUNDINGEuropean Union, Italian Ministry of Health, Swedish Research Council, Veterans Health Administration, NIH.
16 Apr 2026
Read appraisal →Hepatology communications
Seladelpar in patients with primary biliary cholangitis and compensated cirrhosis: Efficacy and safety from RESPONSE and ASSURE studies
BACKGROUND: Treatment options are limited for patients with primary biliary cholangitis (PBC) and cirrhosis. Seladelpar, a first-in-class delpar (selective PPAR-δ agonist), had generally similar efficacy and safety among patients with versus without compensated cirrhosis in the phase 3 RESPONSE study. Here we provide additional data on seladelpar in patients with compensated cirrhosis from the phase 3 program. METHODS: In RESPONSE, patients with PBC and an inadequate response or intolerance to UDCA were randomized 2:1 to seladelpar 10 mg or placebo for 1 year. Upon completion, patients rolled over into the open-label (seladelpar 10 mg) phase 3 ASSURE study, which also enrolled patients from earlier seladelpar legacy PBC studies. Here, we assessed the composite endpoint [alkaline phosphatase (ALP) <1.67×upper limit of normal (ULN), ALP decrease ≥15%, and total bilirubin ≤ULN], other laboratory changes, and safety in all patients with cirrhosis from RESPONSE and an interim analysis of the ongoing ASSURE study through January 2024. RESULTS: Twenty-seven patients with compensated cirrhosis enrolled in RESPONSE (18 seladelpar, 9 placebo). At month 12, 38.9% and 22.2% of patients in the seladelpar and placebo groups, respectively, met the composite endpoint; mean percent change from baseline in ALP was -37.1% and -10.1%, respectively. Upon rollover to ASSURE (13 seladelpar, 6 placebo), ALP declines were maintained for up to 18 months. An additional 35 patients with compensated cirrhosis in ASSURE from legacy studies had similar reductions in ALP with up to 2 years of treatment. Bilirubin remained overall stable. No treatment-related serious adverse events occurred. Variceal bleeding and/or ascites developed in 3 patients after ≥9 months. CONCLUSIONS: Seladelpar decreased markers of cholestasis and was overall safe and well-tolerated in patients with PBC and compensated cirrhosis.
15 Apr 2026
Read appraisal →Vaccine
The safety and efficacy of in situ vaccine FOLactis for advanced hepatic malignancies.
BACKGROUND: Recent years have witnessed the emergence of a novel research direction in the field of tumor vaccines. An in situ vaccine known as FOLactis, comprised of genetically engineered Lactococcus lactis expressing a fusion protein of Fms-like tyrosine kinase 3 ligand (Flt3L) and co-stimulator OX40 ligand (OX40L), was developed by the Oncology Centre of Nanjing Drum Tower Hospital. The present study was designed to evaluate the efficacy and safety of combination therapy based on intratumoral injection of the in situ vaccine FOLactis and intravenous PD-1 monoclonal antibody in combination with immunoradiotherapy or low-dose chemotherapy in the treatment of advanced hepatic malignancies. METHODS: In this exploratory clinical study, patients with advanced hepatic malignancies were enrolled and randomly assigned to Group A and Group B, corresponding to different treatment regimens. The treatment regimen in Group A consisted of the in situ vaccine FOLactis combined with a PD-1 monoclonal antibody and immunoradiotherapy (5Gy/fraction×3fractions). In contrast, the regimen in Group B included the in situ vaccine FOLactis, a PD-1 monoclonal antibody, and low-dose chemotherapy (cisplatin plus vincristine). All treatments were given in 21-day cycles. The primary observation indicator of the study was the objective response rate (ORR) as defined by RECIST v1.1. Secondary observation indicators included the disease control rate (DCR) and the incidence of adverse events. RESULTS: A total of 18 eligible patients were included in the study. In Group A, the ORR and DCR for targeted lesions were 33.3%(95%CI:12.1-64.6%) and 77.8%(95%CI:45.3-96.1%), while the ORR and DCR for non-targeted lesions were 22.2%(95%CI:3.9-54.7%) and 66.7%(95%CI:35.4-87.9%), respectively. Targeted and non-targeted lesions in Group B did not reduce significantly, and their respective DCRs were 66.7%(95%CI:35.4-87.9%) and 22.2%(95%CI:3.9-54.7%). Patients in Group A experienced no significant adverse events. Patients in Group B experienced grade 1-2 hyperthermia as a side effect. CONCLUSIONS: The combination therapy based on the in situ vaccine FOLactis and intravenous PD-1 monoclonal antibody showed a certain degree of anti-tumor effect, and was safe and well tolerated in patients with advanced hepatic malignancies. TRIAL REGISTRATION: The Ethics Committee of Nanjing Drum Tower Hospital approved this study (approval number 2022-101-01). The associated trial is registered at ChiCTR.gov.cn (ChiCTR2200060660).
12 Apr 2026
Read appraisal →Global public health
Seroprevalence of hepatitis C virus among refugees, asylum seekers, and internally displaced populations within Africa: A systematic review and meta-analysis
Hepatitis C virus (HCV), an often overlooked public health concern, is highly prevalent among marginalized groups. Refugees, asylum seekers, and internally displaced people (RASIDP) constitute an underserved population in healthcare. Given that displacement rates are increasing and that HCV is endemic to many African countries, we aimed to determine the prevalence of HCV among RASIDP communities in Africa. Studies investigating HCV prevalence within RASIDP communities across Africa were identified via the following database searches: Ovid MEDLINE, EMBASE, Web of Science, APA PsycINFO, and the WHO Africa Index Medicus. Seroprevalence estimates were meta-analysed using a random-effects model, with data stratified by participant region, age, and gender. Across 9 studies, we estimated a pooled HCV seroprevalence of 3.63% (95% CI: 0.54, 9.16) among RASIDP in Africa. Seroprevalence varied by region of origin and age, with those from Northern Africa and those aged > 40 years having the highest seroprevalence, at 10.03% (95% CI:9.03, 11.13) and 5.70% (95% CI: 0.81, 14.21), respectively. RASIDP communities represent a marginalised and vulnerable population that often faces significant barriers to accessing healthcare. Our findings show that HCV seroprevalence within these communities varies by region and age, thus suggesting a need for targeted screening approaches.
12 Apr 2026
Read appraisal →Journal of clinical oncology : official journal of the American Society of Clinical Oncology
Transarterial Chemoembolization Combined With Camrelizumab and Rivoceranib for Unresectable Hepatocellular Carcinoma (CHANCE2005/CARES-005): A Randomized Phase II Trial
PURPOSE: Transarterial chemoembolization (TACE) alone has shown limited efficacy in improving survival among patients with unresectable hepatocellular carcinoma (HCC). This phase II trial compared TACE combined with camrelizumab (anti-PD-1 antibody) and rivoceranib (vascular endothelial growth factor receptor 2 inhibitor) versus TACE in unresectable HCC. METHODS: Patients with unresectable HCC (Barcelona Clinic Liver Cancer stage A to C without extrahepatic metastases) and Child-Pugh class A liver function were randomly assigned (1:1), stratified by macrovascular invasion, previous tyrosine kinase inhibitor treatment, and number of previous TACE procedures, to receive TACE combined with camrelizumab (200 mg once every 3 weeks) and rivoceranib (250 mg once daily; TACE-C-R) or TACE alone. The primary end point was progression-free survival (PFS) per composite criteria (progression per Response Evaluation Criteria in Cancer of the Liver version 5, transient deterioration to Child-Pugh class C, or TACE failure or refractoriness) in the intention-to-treat population. RESULTS: Between December 28, 2020, and October 29, 2023, 200 patients were randomly assigned (100 in each group). Median PFS per composite criteria was significantly longer with TACE-C-R than with TACE (10.8 months [95% CI, 8.8 to 13.7] v 3.2 months [95% CI, 2.4 to 4.2]; hazard ratio, 0.34 [95% CI, 0.24 to 0.50], P < .001). Grade ≥3 treatment-related adverse events occurred in 74.5% (70 of 94) of patients with TACE-C-R and 22.3% (23 of 103) of patients with TACE, with the most common being increased AST (29 [30.9%] and 13 [12.6%]) and increased ALT (23 [24.5%] and 14 [13.6%]). CONCLUSION: The addition of camrelizumab and rivoceranib to TACE showed statistically significant improvement in PFS for patients with unresectable HCC, with a manageable safety profile. Follow-up for further overall survival analysis is ongoing.
10 Apr 2026
Read appraisal →Journal of medical Internet research
Machine Learning in Predicting the Risk of Esophagogastric Variceal Bleeding Among Patients With Liver Cirrhosis: Systematic Review and Meta-Analysis
BACKGROUND: Liver cirrhosis (LC) can lead to several complications. Esophageal variceal bleeding (EVB) and esophagogastric variceal bleeding (EGVB) are particularly severe, leading to a high risk of mortality. Early identification of esophageal varices and esophagogastric varices is essential. Several studies have constructed prediction models for EVB and EGVB in patients with LC. However, robust systematic evidence to prove their performance is lacking. OBJECTIVE: We included original studies that developed prediction models for esophageal or gastric variceal bleeding in patients with LC under different modeling variables. This study aimed to review the predictive performance of various models for EVB or EGVB in patients with LC, providing insights into the development or updating of simplified scoring tools in the future. METHODS: PubMed, Web of Science, Embase, and the Cochrane Library were searched up to August 21, 2024, to collect original full-text studies on machine learning (ML) in the prediction of EVB and EGVB in patients with LC. The models were evaluated using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Subgroup analyses were carried out based on the modeling variables. RESULTS: In total, 21 studies were included, with 7011 patients with LC, among whom 1412 (20.14%) developed EVB and 733 (10.45%) developed EGVB. The meta-analysis results suggested that the pooled c-index, sensitivity, and specificity of the prediction model for predicting EVB in the validation set were 0.85 (95% CI 0.77-0.92), 0.93 (95% CI 0.87-0.96), and 0.66 (95% CI 0.46-0.82), respectively. The pooled c-index, sensitivity, and specificity of the prediction model for predicting EGVB in the validation set were 0.89 (95% CI 0.85-0.94), 0.77 (95% CI 0.66-0.85), and 0.81 (95% CI 0.67-0.90), respectively. The subgroup analysis based on modeling variables revealed that, for predicting EVB, the c-index in the validation set was 0.84 (95% CI 0.80-0.88) for models based on clinical features, 0.82 (95% CI 0.69-0.96) for radiomics-based models, 0.78 (95% CI 0.67-0.89) for models based on radiomics and clinical features, and 0.97 (95% CI 0.95-1.00) for models based on endoscopic features. Subgroup analyses based on modeling variables revealed that, for predicting EGVB, the c-index in the validation set was 0.91 (95% CI 0.86-0.96) for models based on clinical features and 0.85 (95% CI 0.75-0.96) for models based on radiomics and clinical features. CONCLUSIONS: ML methods are feasible for predicting EVB and EGVB in patients with LC. Nevertheless, the number of included original studies is limited. In the future, more studies with larger sample sizes are needed to promote the application of ML in the early assessment of EVB and EGVB in patients with LC in clinical practice.
9 Apr 2026
Read appraisal →Physics in medicine and biology
End-to-end testing of an online adaptive radiotherapy workflow for liver tumors using a dynamic Thoraco-abdominal anthropomorphic phantom.
Objective.Adaptive radiotherapy (ART) requires robust end-to-end (E2E) testing tools capable of reproducing organ deformation, physiological motion, and multimodal imaging properties. TheToraco-abdominalAnthropomorphic Phantom withMotion forAdaptiveRadiotherapy (TAM-ARa) is a dynamic anthropomorphic phantom developed to support the design, validation, and quality assurance of online ART workflows.Approach.The phantom was constructed with anatomically realistic bone, lung, and abdominal organ models fabricated from tissue equivalent materials. Modular components allowed simulation of interfractional and intrafractional anatomical variations, including ventilator driven respiratory motion, abdominal deformation, and variable gastric filling. CT, CBCT, and 3T MRI scans were acquired to assess imaging performance. Two E2E tests of an online adaptive intensity-modulated radiotherapy (IMRT) workflow for liver tumors were performed on a Varian Ethos (ETHOS, Varian, USA) system. Multiple deformation scenarios were investigated, including a static reference configuration, two abdominal and one thoracic deformation for ionization chamber (IC) dosimetry, and a static plus abdominal deformation scenarios for radiochromic film dosimetry.Main results.The TAM-ARa phantom demonstrated realistic radiological characteristics, with CT Hounsfield units and MRI relaxation times closely matching reportedin vivovalues. The modular architecture allowed reproducible and controlled abdominal deformations, while setup and dosimeter placement were completed within minutes. In E2E tests for adaptive IMRT of liver tumors, excellent agreement was achieved between measured and planned dose distributions after the treatment plan was adapted. IC E2E measurements showed that online adaptation consistently restored accurate dose delivery under deformation, reducing deviations to below 3%. Independent film measurements confirmed sub-millimeter geometric accuracy and full planning target volume coverage after adaptation, demonstrating effective compensation of deformation-induced errors.Significance.The TAM-ARa phantom provides a versatile and reproducible platform for multimodal E2E testing and validation of online ART workflows. Employing its realistic anatomical design, modular structure, and motion capabilities, TAM-ARa was successfully applied for E2E tests to validate a workflow for adaptive IMRT of liver tumors.
8 Apr 2026
Read appraisal →The American journal of gastroenterology
A Large Language Model Assistant for Summarizing Hepatology Referral Documents
INTRODUCTION: To use a large language model (LLM) to create accurate and useable summaries of patient records for clinicians triaging new hepatology referrals. METHODS: We developed a comprehensive list of data elements required to triage a new hepatology referral and engaged in an iterative prompt engineering process to instruct an LLM to extract relevant data from patient referral documents. The final prompt was used on 50 original patient records from June to July 2025 to generate corresponding artificial intelligence (AI) summaries, which were assigned to 2 providers to review and triage according to their usual process. We assessed time to triage original vs AI files and accuracy of the AI files. A linear mixed-effects model was used to determine an adjusted time ratio comparing the time to triage AI files vs original files. RESULTS: AI-generated summaries were significantly shorter than original files (median [interquartile range] 2 [2-3] vs 23 [10.2-38.8] pages, P < 0.001). AI summaries had high accuracy (median [interquartile range]: 94.6% [86.5%-97.3%]) with a low hallucination rate. Use of the AI summaries led to a 60% reduction in triage time (adjusted mean triage time of 37.2 seconds for AI files vs 94.2 seconds for original files, P < 0.001). DISCUSSION: The use of an LLM led to significantly reduced document length, maintained an appropriate level of accuracy, and led to a significant decrease in clinician time to review the patient record. Future steps involve creating a fully automated workflow that is integrated into the electronic health record for widespread use.
4 Apr 2026
Read appraisal →