Mary‐Anne Hartley

Evaluating large language models as clinical decision support tools in primary healthcare settings: Protocol for a multi-country comparative validation study on expert-adjudicated hypothetical vignettes (hypMOOVE-PHC)

Paul Macharia, Chiyembekezo Kachimanga, Muhidin K. Mahende, Evelyne Mapunda et autres

ABSTRACT Introduction Large language models (LLMs) have the potential to strengthen clinical decision-making in low-resource primary healthcare (PHC) settings. However, most LLMs are developed and benchmarked in high-resource settings and evidence on their safety and contextual appropriateness in Sub-Saharan Africa remains limited. …

Kenya, us, Malawi, Tanzanie, ch (code pays fourni par la source)

Expert Evaluation of Clinical Large Language Models in Intensive Care Medicine: A Multi-rater Assessment Study (Preprint)

Julian Klug, Raphaël Burger, Jean Bonnemain, Lionel Carrel et autres

BACKGROUND Large language models are increasingly being used for clinical decision support. Yet, a systematic evaluation of the performance and trustworthiness of such models in the intensive care unit (ICU) is lacking. OBJECTIVE This study aims to create an evaluation framework for …

ultrai-lung-ultrasound

Trevor Brokowski, Véronique Suttels, Ablo Prudence Wachinou, Aboudou Rasisou Hada et autres

Federated modular clinical decision support networks for collaborative learning in resource-limited settings

Cécile Trottet, Jonathan Doenz, Pierrette M. Mastel, Victor Rwandarwacu et autres

Abstract Imperfect interoperability (IIO), where health facilities record different, often sparse subsets of clinical variables, remains a major barrier to deploying models trained with Federated Learning (FL) in global health settings. We introduce FedMoDN, a novel federated modular neural network architecture for …

ch, us, ie, Tanzanie (code pays fourni par la source)

The Lancet HIV Commission on ageing and HIV: a global perspective

Amy C. Justice, Keri N Althoff, A Mark Clarfield, Brenda Crabtree Ramirez et autres

us, il, mx, Afrique du Sud, Kenya, hk, Ouganda, ch, Malawi, gb, de, cl, it, br, Éthiopie, Botswana, au, be, ru, my (code pays fourni par la source)

Measurement-Based Mental Health Care for Adolescents in Africa: Protocol for a Computerized Adaptive Test

Bianca Moffett, Mary A. Bitta, Darryn Williams, Jonathan Doenz et autres

Abstract Background Adolescent mental health care is constrained not only by limited treatment capacity but also by the absence of precise and efficient tools to identify and triage those in need. Measurement-based mental health care relies on standardized assessments to guide identification, …

Afrique du Sud, gb, Kenya, us, ch, au, ph (code pays fourni par la source)

Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety

Fay Elhassan, David Sasu, Alexandra Kulinkina, Lars Klein et autres

We evaluate whether clinician pairwise preferences provide a reliable signal of clinical safety in large language model (LLM) evaluation using expert feedback from MOOVE (Massive Open Online Validation and Evaluation), a clinician-led platform collecting blinded pairwise preferences alongside multi-criterion rubric ratings. Clinicians …

Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety

Fay Elhassan, David Sasu, Alexandra Kulinkina, Lars Klein et autres

We evaluate whether clinician pairwise preferences provide a reliable signal of clinical safety in large language model (LLM) evaluation using expert feedback from MOOVE (Massive Open Online Validation and Evaluation), a clinician-led platform collecting blinded pairwise preferences alongside multi-criterion rubric ratings. Clinicians …

ch (code pays fourni par la source)

Fully Open Meditron: An Auditable Pipeline for Clinical LLMs

Xavier Theimer-lienhard, Mushtaha El-Amin, Fay Elhassan, Sahaj Vaidya et autres

Clinical decision support systems (CDSS) require scrutable, auditable pipelines that enable rigorous, reproducible validation. Yet current LLM-based CDSS remain largely opaque. Most "open" models are open-weight only, releasing parameters while withholding the data provenance, curation procedures, and generation pipelines that determine model …

Fully Open Meditron: An Auditable Pipeline for Clinical LLMs

Xavier Theimer-lienhard, Mushtaha El-Amin, Fay Elhassan, Sahaj Vaidya et autres

Clinical decision support systems (CDSS) require scrutable, auditable pipelines that enable rigorous, reproducible validation. Yet current LLM-based CDSS remain largely opaque. Most "open" models are open-weight only, releasing parameters while withholding the data provenance, curation procedures, and generation pipelines that determine model …

us (code pays fourni par la source)

Evidence and Gap Map of evidence syntheses on sex- and gender-specific health and health care: a scoping review protocol

Jesús López-Alcalde, Cong Wang, Diana Buitrago-Garcia, Concepción Campos-Asensio et autres

The general aim of this scoping review is to identify and characterise evidence syntheses that specifically examine how sex, gender, gender identity, gender modality, and sexual orientation are associated with health conditions and health care outcomes. The review will also tackle intersectionality …

Evidence and Gap Map of evidence syntheses on sex- and gender-specific health and health care: a scoping review protocol

Jesús López-Alcalde, Cong Wang, Diana Buitrago-Garcia, Concepción Campos-Asensio et autres

The general aim of this scoping review is to identify and characterise evidence syntheses that specifically examine how sex, gender, gender identity, gender modality, and sexual orientation are associated with health conditions and health care outcomes. The review will also tackle intersectionality …