Actively Recruiting
Evaluation of Large Language Models for Acute Conditions in Resource-Limited Settings Contextual Awareness, Safety, and Accuracy Study
Led by Ecole Polytechnique Fédérale de Lausanne · Updated on 2026-11-03
3000
Participants Needed
4
Research Sites
N/A
Total Duration
AI-Summary
What This Trial Is About
Researchers are evaluating large language models LLMs as clinical decision support tools in healthcare settings of low and middle income countries. These settings often face challenges such as time pressure, limited diagnostic resources, and inconsistent access to current clinical guidelines. This observational study, part of the MOOVE project, aims to rigorously assess LLMs performance and safety compared to human clinical care in real-world acute condition cases. The study is non-interventional and conducted during routine outpatient care in participating facilities. Patient clinical and demographic data collected during visits are used to retrospectively prompt the LLMs without affecting patient treatment. The LLM outputs and human care plans are reviewed by independent clinical experts. Implementation feasibility is also assessed by gathering clinician feedback on the LLM interface, output clarity, relevance, safety perceptions, and alignment with clinical workflows and guidelines. Participants are followed up at 7 and 28 days after enrollment to collect clinical outcomes for evaluating LLM safety and performance. The study also monitors clinician experience and organizational readiness for future LLM implementation from week 4 until study completion. Outcome measures include performance scores at day 0 and safety thresholds at days 7 and 28, alongside ongoing implementation feasibility research. The total study duration extends through 2026.
CONDITIONS
Brief Title
Massive Online Open Validation and Evaluation of Large Language Models for Resource Constrained Settings - a Study of Contextual Awareness, Safety, and Accuracy
Research Team
M
Mary-Anne Hartley
K
Kristina Keitel
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here