Readable research linked to original sources
Articles
Browse normalized, publication-ready research with direct links to its evidence and source.
Loading articles data…
Readable research linked to original sources
Browse normalized, publication-ready research with direct links to its evidence and source.
Loading articles data…
Readable research linked to original sources
Browse normalized, publication-ready research with direct links to its evidence and source.
12 articles
Newest firstTeledermatology expands access to dermatologic expertise in rural settings, yet diagnostic uncertainty persists in low-resource primary care. This retrospective study evaluated MedGemma-4B-IT, a compact multimodal vision-language model, as adjunctive clinical decision support for challenging diagnostic cases. We analyzed 77 zero-concordance cases (360 clinical photographs) from a Dermatology Extension for Communit…
Open article record in new tab ↗To characterise the potential learning effects from a GenAI-based clinical decision support tool (CDST), we examined clinician behaviour within a cluster-randomised trial. The tool, AI Consult, parsed clinician notes written (in real-time) to document patient encounters and would raise green, yellow, or red flags to indicate no, potential, or critical risks of harm (respectively) in decisions the clinician made. O…
Open article record in new tab ↗BackgroundSouth Africas public healthcare system serves most of the population through approximately 3,900 primary healthcare clinics characterised by long waiting times and high volumes of repeat-prescription visits. No published pre-arrival digital triage system operates across all 11 official South African languages while aligning with the South African Triage Scale (SATS). This paper reports the design and pre…
Open article record in new tab ↗Evaluating the outputs of generative AI (GenAI) models in healthcare remains a significant bottleneck for the safe and scalable deployment of these tools. Human expert raters remain the gold standard for assessing the accuracy, contextual appropriateness, and empathy of AI-generated responses, but their assessments are costly, inconsistent, and difficult to scale. The concept of "LLM-as-a-judge" systems, i.e., AI…
Open article record in new tab ↗BackgroundLarge language models (LLMs) are increasingly used in healthcare, but standardized benchmarks fail to capture their validity and safety in real-world scenarios. Evaluating their quality and reliability is critical for safe integration into practice. MethodsFour fictitious clinical vignettes (orthopedics, pediatrics, gynecology, psychiatry) were developed by independent specialists and tested in four conv…
Large language models (LLMs) have demonstrated strong performance in medical contexts; however, existing benchmarks often fail to reflect the real-world complexity of low-resource health systems accurately. This study developed a dataset of 5,609 clinical questions contributed by 101 community health workers (CHWs) across four Rwandan districts and compared responses generated by five large language models (LLMs)…
BackgroundRetrieval-augmented generation (RAG) is an emerging artificial intelligence (AI) strategy that integrates encoded model knowledge with external data sources to enhance accuracy, transparency, and reliability. Unlike traditional large language models (LLMs), which are limited by static training data and potential misinformation, RAG dynamically retrieves and integrates relevant medical literature, clinica…
Open article record in new tab ↗BackgroundDistinguishing between non-severe and severe dengue is crucial for timely intervention and reducing morbidity and mortality. Traditional warning signs recommended by the World Health Organization (WHO) offer a practical approach for clinicians but have limitations in sensitivity and specificity. This study evaluates the performance of machine learning (ML) models compared to WHO- recommended warning sign…
Open article record in new tab ↗PurposeThe open, prospective Community-Based chronic Care Lesotho (ComBaCaL) cohort is the first study to comprehensively investigate socioeconomic indicators, common chronic diseases and their risk factors in a remote rural setting in Lesotho. It serves as a platform for implementing nested trials using the Trials within Cohorts (TwiCs) design to assess community-based chronic care interventions. Here, we present…
BackgroundUsing artificial intelligence (AI) to help clinical diagnoses has been an active research topic for more than six decades. Past research, however, has not had the scale and accuracy for use in clinical decision making. The power of AI in large language model (LLM)-related technologies may be changing this. In this study, we evaluated the performance and interpretability of Generative Pre-trained Transfor…
Despite their long history, it can still be difficult to embed clinical decision support into existing health information systems, particularly if they utilise machine learning and artificial intelligence models. Moreover, when such tools are made available to healthcare workers, it is important that the users can understand and visualise the reasons for the decision support predictions. Plausibility can be hard t…
Open article record in new tab ↗ProblemBayesian Networks (BN) can address real-world decision-making problems, and there is enormous and rapidly increasing interest in their use in healthcare. Yet, despite thousands of BNs in healthcare papers published yearly, evidence of their adoption in practice is extremely limited and there is no consensus on why. MethodA preliminary review was conducted to identify research gaps and justify the conduct of…
Open article record in new tab ↗