Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 10 appraisals
Journal of chemical information and modeling
Machine Learning for RNA-Targeting Drug Design
Targeting RNA with small molecules offers significant therapeutic potential. Machine learning could substantially accelerate preclinical drug discovery, from hit identification to lead optimization. Yet a limitation emerges: drug design machine learning models, designed for proteins, are not readily applicable to RNAs because of fundamental differences between RNAs and proteins in both structural characteristics and interactions with small molecules. RNA-specific approaches have consequently emerged, primarily focusing on binding site identification and virtual screening. In this review, we comprehensively compare machine learning tools for RNA-targeting drug design according to the tasks they address, their methodology and their relevance in RNA-specific contexts. As open challenges will catalyze new method development, we emphasize the need for standardized, drug design-specific evaluation approaches. We provide clear guidelines to establish these standards and present a benchmark assessing the ability of current machine learning models to predict specific drug-RNA interactions.
28 July 2026
Read appraisal →Molecular genetics and genomics : MGG
The use of artificial intelligence in advancing molecular biology in Africa: a narrative review
Artificial intelligence (AI) is rapidly becoming a core methodological pillar of molecular biology and precision medicine, and Africa is a uniquely consequential setting for this transition because the continent combines the world's greatest human genomic diversity with the most severe underrepresentation of that diversity in the datasets and reference resources on which AI models are built and benchmarked. This narrative review examines, for a genetics and genomics readership, where AI-driven methods are already strengthening African molecular biology, where the supporting evidence remains preliminary, and what is required to translate technical capability into scientifically robust and equitable benefit. The central argument is that AI is especially consequential in African molecular biology, not simply because it automates analysis, but because it can help unlock insight from African genomic diversity, pathogen biology, and clinically relevant multi-omics data that remain underrepresented in global models. Across core molecular domains, AI is accelerating protein structure prediction, high-throughput variant calling and pan-genomic reference construction, genome-wide association analysis, transcriptomic interpretation, drug discovery, and CRISPR guide design. African initiatives such as H3Africa, the African Genome Variation Project, H3ABioNet, and the H3D Centre show that locally generated datasets and African-led computational pipelines can already support meaningful discovery, from improved variant interpretation to structure-guided therapeutic prioritization. At the same time, persistent barriers remain, including underrepresentation of African genomes in training data and reference genomes, uneven computational infrastructure, limited interdisciplinary training, fragmented governance, and the risk that AI-derived benefits will remain inaccessible to the populations whose data enable them. We conclude that the future impact of AI in African molecular biology will depend less on adopting global tools in the abstract and more on building African-led datasets, validation pipelines, governance frameworks, and translational pathways that make molecular discovery both scientifically robust and equitably useful. Looking ahead, the central perspective offered by this review is that Africa's exceptional genomic diversity should be treated as a scientific asset rather than an analytical liability: realising this will require population-representative pan-genome references, sustained computational capacity, and governance structures that ensure African populations are not only the source of the underlying data but also the principal beneficiaries of the discoveries it enables.
23 July 2026
Read appraisal →BMC health services research
Computational forecasting using Swedish data in the vaccination phase of the COVID-19 pandemic: a systematic literature review deliberating modelling relevance for public health and healthcare.
BACKGROUND: The benefits of computational forecasting in the later phase of the COVID-19 pandemic when vaccines and clinical pharmaceutical interventions were available have seldom been assessed. We aimed to evaluate computational forecasting research applied to Swedish populations in the vaccination phase of the pandemic. METHODS: A systematic search was performed on March 8, 2024 in the electronic databases PubMed, Scopus, Cochrane library, Embase, Love platform and Epistemikos. An updated version of the Risk of bias Opinion Tool (ROBOT) was used to assess the quality of evidence reported in the papers identified in the search. The articles fulfilling the quality criteria were assessed for suitability for meta-analysis. Data were extracted from the selected articles for synthesis of characteristics, and a thematic analysis was used for a qualitative synthesis of the contents. RESULTS: Of 2034 unique publications identified in the database search, 6 articles satisfied the selection and quality criteria. Variability in the reporting of forecasting performance results was found to make a quantitative meta-analysis of forecast performance infeasible. The data synthesis showed that statistical modeling using Bayesian calibration was the most common methodological approach. No external model validation was reported, but 5/6 articles included internal model corroboration data. The primary theme resulting from the qualitative synthesis of article content was design or refinement of computational models with demonstration of model use in health service practice as a secondary theme. None of the articles referred to health service policymaking as the primary research context. CONCLUSION: Computational forecasting research using Swedish population data from the vaccination phase of the COVID-19 pandemic was deployed in a model design context. While methodological knowledge was developed, most of the research was not initiated to solve the public health and healthcare problems at hand. Our results indicate that the alignment between computational forecasting research and policymaking needs in the vaccination phase of pandemics can be enhanced.
13 July 2026
Read appraisal →Chemical communications (Cambridge, England)
An update on polydiacetylene-based solid-supported sensing platforms for environmental and health monitoring.
Polydiacetylenes (PDAs) are a unique class of conjugated polymers renowned for their pronounced chromo- and fluorogenic responses to external stimuli, enabling direct optical transduction of chemical and biological interactions. While early PDA-based sensing systems predominantly relied on solution-phase assemblies, their limited structural stability, reproducibility, and deployability have constrained practical applications. In recent years, the immobilization of PDAs onto solid supports has emerged as a powerful strategy to overcome these limitations, transforming responsive supramolecular polymers into robust, functional sensing platforms. Solid-supported PDA architectures offer enhanced mechanical stability, improved environmental tolerance, controlled molecular organization, and compatibility with portable and field-deployable devices. This review provides a comprehensive and application-oriented overview of solid-supported polydiacetylene systems for environmental and health monitoring. Emphasis is placed on the role of support materials, fabrication strategies, and structure-process-property relationships that govern sensing performance. Key applications in environmental pollutant detection and biomedical diagnostics are critically examined, alongside comparative performance metrics and design considerations. Current challenges, including signal irreversibility, environmental interference, and scalability, are discussed, and future directions toward sustainable fabrication, wearable devices, and integrated smart sensing platforms are outlined. By positioning solid-supported PDAs as adaptive interfaces between molecular recognition and macroscopic readout, this review highlights their potential as next-generation materials for decentralized and real-world sensing applications.
8 July 2026
Read appraisal →Scientific reports
Differentially private federated learning for localized control of infectious disease dynamics
In times of epidemics, swift reaction is necessary to mitigate epidemic spreading. For this reaction, localized approaches have several advantages, limiting necessary resources and reducing the impact of interventions on a larger scale. However, training a separate machine learning (ML) model on a local scale is often not feasible due to limited available data. Centralizing the data is also challenging because of its high sensitivity and privacy constraints. In this study, we consider a localized strategy based on the German counties and communities managed by the related local health authorities (LHA). For the preservation of privacy to not oppose the availability of detailed situational data, we propose a privacy-preserving forecasting method that can assist public health experts and decision makers. ML methods with federated learning (FL) train a shared model without centralizing raw data. Considering the counties, communities or LHAs as clients and finding a balance between utility and privacy, we study a FL framework with client-level differential privacy (DP). We train a shared multilayer perceptron on sliding windows of recent case counts to forecast the number of cases in the future, while clients exchange only norm-clipped updates and the server aggregates updates with DP noise. We evaluate the approach on COVID-19 data on county-level during two phases: November 2020 and March 2022 (Omicron). As expected, very strict privacy ([Formula: see text]) yields unstable, unusable forecasts. At a moderately strong but still privacy-preserving level ([Formula: see text]), the DP model closely approaches the non-DP model: [Formula: see text] (vs. 0.96) and mean absolute percentage error (MAPE) [Formula: see text] in November 2020; [Formula: see text] (vs. 0.90) and MAPE [Formula: see text] in March 2022. Overall, our results support the feasibility of privacy-preserving collaboration among health authorities for local forecasting. In the evaluated COVID-19 phases, client-level DP-FL delivered useful county-level predictions with formal privacy guarantees under the stated threat model. The appropriate privacy budget should nevertheless be re-evaluated for other epidemic phases and applications.
8 July 2026
Read appraisal →The Journal of dermatological treatment
Intralesional human papillomavirus vaccination for cutaneous verrucae: a systematic review and meta-analysis of therapeutic efficacy
OBJECTIVES: To evaluate the efficacy of intralesional human papillomavirus (HPV) vaccination in the management of cutaneous warts. METHODS: A comprehensive search of PubMed, MEDLINE, Embase, Scopus, and ClinicalTrials.gov was conducted in accordance with a registered PROSPERO protocol (CRD420251170324). Chronic or persistent warts were defined as lesions lasting more than six months or showing inadequate response to conventional therapies. The primary outcome was complete wart clearance, and pooled risk ratios (RRs) with 95% confidence intervals (CIs) were calculated using a random-effects model. RESULTS: Six studies were included. Intralesional HPV vaccination was associated with a significantly higher rate of complete clearance compared with intralesional normal saline (RR 18.54; 95% CI 6.59-52.18). Subgroup analyses demonstrated comparable efficacy between bivalent and quadrivalent vaccines. Reported adverse events were mild and localized. CONCLUSION: Intralesional HPV vaccination demonstrated significant therapeutic efficacy in the treatment of cutaneous warts and represents a promising immunotherapeutic option for patients with persistent or treatment-refractory disease.
30 June 2026
Read appraisal →International journal of medical informatics
Accuracy and completeness of large language models in Epidemic keratoconjunctivitis Queries: A Comparative study
BACKGROUND: Large language models (LLMs) are increasingly applied in clinical contexts, yet their reliability in disease-specific ophthalmic domains remains insufficiently characterized. Epidemic keratoconjunctivitis (EKC), a highly contagious adenoviral ocular infection, represents a critical area where accurate diagnostic and therapeutic information is essential. This study aimed to assess and compare the accuracy and completeness of responses generated by two widely used LLMs, namely ChatGPT and Meta AI, to standardized ophthalmology questions related to EKC. METHODS: This cross-sectional expert evaluation study was conducted between January and March 2025. Thirty-four structured questions covering five EKC domains (etiology, clinical features, diagnosis, treatment, and prognosis) were developed using authoritative ophthalmology sources. Responses generated by ChatGPT (Plus subscription, web interface) and Meta AI (web interface) were independently scored by two fellowship-trained cornea specialists using a five-point Likert scale for accuracy and completeness. Inter-rater agreement was assessed using Cohen's κ and mean absolute error (MAE). RESULTS: Both models demonstrated strong overall performance, with mean accuracy and completeness scores of 4.87 and 4.90 for ChatGPT and 4.87 and 4.93 for Meta AI, respectively. Agreement between expert raters was substantial (κ range 0.78-0.88). Domain-specific analysis revealed consistently high scores across all categories, with Meta AI showing slightly higher completeness, particularly in diagnostic and symptom-related responses. CONCLUSION: LLMs exhibit consistently strong performance and domain consistency when addressing ophthalmic queries related to EKC. Their performance supports their potential use as adjunct informational and educational tools for ophthalmic conditions such as EKC, particularly for structured knowledge retrieval, treatment explanation, and patient counseling, provided that use remains under appropriate professional oversight.
15 June 2026
Read appraisal →Clin Dermatol
Chancroid.
Chancroid, caused by Haemophilus ducreyi, is a sexually transmitted genital ulcerative condition associated with inguinal bubo formation. The relative prevalence of chancroid has dramatically declined based on surveillance findings in those few endemic settings where the appropriate diagnostic tools exist; however, laboratory-based diagnostics are lacking to assist clinical management and support etiological surveillance in most parts of the world. Recent yaws surveys within the Western Pacific region indicate that H ducreyi has re-emerged as a frequent cause of chronic skin ulceration. Although there have been no antimicrobial susceptibility studies for three decades, it is assumed that a cure remains possible with extended-spectrum cephalosporins, macrolides, or fluoroquinolones. HIV-1-infected patients require careful followups due to reports of treatment failure with single-dose regimens. Buboes may need additional treatment with either aspiration or excision and drainage.
1 Jan 2026
Read appraisal →Clin Dermatol
Gonorrhea.
Neisseria gonorrhoeae, a Gram-negative intracellular pathogen, causes gonorrhea. Although usually sexually transmissible, it can be acquired by direct inoculation. Untreated gonococcal infections have deleterious impacts, including adverse pregnancy outcomes, ectopic pregnancy, infertility, and even blindness. Extended-spectrum cephalosporins remain the mainstay of therapy, and gonococcal culture is essential to determine susceptibility to these agents. Antimicrobial resistance is a global public health concern, and a few new agents are in the pipeline. Gonorrhea control programs rely on health education, access to diagnostic testing (where possible), effective therapy, and partner notification. Introducing inexpensive, sensitive, and specific point-of-care tests will aid antimicrobial stewardship efforts in countries using the syndromic management approach. Targeted vaccination of higher-risk populations with cross-protective outer membrane vesicle-based meningococcal B vaccines might reduce N. gonorrhoeae transmission in the future. Doxycycline postexposure prophylaxis may further reduce gonococcal incidence in the short term; however, its long-term impact on the human resistome/microbiome remains unknown.
1 Jan 2026
Read appraisal →Cell
A generative deep learning approach to de novo antibiotic design
The antimicrobial resistance crisis necessitates structurally distinct antibiotics. While deep learning approaches can identify antibacterial compounds from existing libraries, structural novelty remains limited. Here, we developed a generative artificial intelligence framework for designing de novo antibiotics through two approaches: a fragment-based method to comprehensively screen >107 chemical fragments in silico against Neisseria gonorrhoeae or Staphylococcus aureus, subsequently expanding promising fragments, and an unconstrained de novo compound generation, each using genetic algorithms and variational autoencoders. Of 24 synthesized compounds, seven demonstrated selective antibacterial activity. Two lead compounds exhibited bactericidal efficacy against multidrug-resistant isolates with distinct mechanisms of action and reduced bacterial burden in vivo in mouse models of N. gonorrhoeae vaginal infection and methicillin-resistant S. aureus skin infection. We further validated structural analogs for both compound classes as antibacterial. Our approach enables the generative deep-learning-guided design of de novo antibiotics, providing a platform for mapping uncharted regions of chemical space.
1 Oct 2025
Read appraisal →