Generative AI-enabled clinical decision support system in primary care: a pragmatic, cluster-randomized trial

Rigorous evidence on the performance of large language models (LLMs) in real-world, low-resource clinical settings remains limited. Here we conducted a pragmatic, cluster-randomized trial in 16 primary care facilities in Kenya. Clinical officers were randomized to use the electronic medical record with or without LLM assistance. The primary outcome was an expert-adjudicated composite of treatment failure events experienced within 14 days of enrollment. Between 22 April and 16 July 2025, 9,691 patients were enrolled, overseen by 103 clinical officers (52 in the LLM-assisted arm and 51 in the control arm). Treatment failure occurred in 102/4,693 patients (2.2%) in the intervention arm and 94/4,654 (2.0%) in the control arm (adjusted odds ratio 0.77, 95% confidence interval 0.55 to 1.08, P = 0.13). The primary outcome did not differ significantly between groups. No serious adverse events were judged related to the intervention, and independent review of the adverse events did not identify a safety signal. In this trial, LLM assistance was safe but did not reduce treatment failure within 14 days and any benefit, if present, is probably modest.Pan-African Clinical Trials Registry: 202502499779176.

Authors

Institutions

Publication Details

Journal
Nature Medicine
Published
2026-06-26
DOI
https://doi.org/10.1038/s41591-026-04503-6
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Generative AI-enabled clinical decision support system in primary care: a pragmatic, cluster-randomized trial

Conrad Wanyama, Sarah Kiptinness, Najib Adan, Xiaoxuan Liu et al.
Nature Medicine
Artificial Intelligence in Healthcare and Education
article

Generative AI-enabled clinical decision support system in primary care: a pragmatic, cluster-randomized trial

Conrad Wanyama, Sarah Kiptinness, Najib Adan, Xiaoxuan Liu, Paul Mwaniki, Lynda Isaaka, Vaishnavi Menon, Mira Emmanuel-Fabula, Alastair Keith Denniston, Jaspret Gill, Bilal Akhter Mateen, Lucinda Archer, Ambrose Agweyu, Richard D. Riley, Robert Korom
article en

Abstract

Rigorous evidence on the performance of large language models (LLMs) in real-world, low-resource clinical settings remains limited. Here we conducted a pragmatic, cluster-randomized trial in 16 primary care facilities in Kenya. Clinical officers were randomized to use the electronic medical record with or without LLM assistance. The primary outcome was an expert-adjudicated composite of treatment failure events experienced within 14 days of enrollment. Between 22 April and 16 July 2025, 9,691 patients were enrolled, overseen by 103 clinical officers (52 in the LLM-assisted arm and 51 in the control arm). Treatment failure occurred in 102/4,693 patients (2.2%) in the intervention arm and 94/4,654 (2.0%) in the control arm (adjusted odds ratio 0.77, 95% confidence interval 0.55 to 1.08, P = 0.13). The primary outcome did not differ significantly between groups. No serious adverse events were judged related to the intervention, and independent review of the adverse events did not identify a safety signal. In this trial, LLM assistance was safe but did not reduce treatment failure within 14 days and any benefit, if present, is probably modest.Pan-African Clinical Trials Registry: 202502499779176.

Nature Medicine
Birmingham City University (GB), Program for Appropriate Technology in Health (US), Kenya Medical Research Institute (KE), London School of Hygiene & Tropical Medicine (GB), Program for Appropriate Technology in Health (IN), Kenya Paediatric Research Consortium (KE), Penda Health (KE), NIHR Birmingham Biomedical Research Centre (GB), University of Birmingham (GB)
Bill and Melinda Gates Foundation, University Hospitals Birmingham NHS Foundation Trust, National Institute for Health and Care Research, Department of Health and Social Care, Birmingham Biomedical Research Centre
Openalex Percentile: Top 9%
Artificial Intelligence in Healthcare and Education
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.