OpenEvidence clinical question-answering platform: systematic review of early evaluations
Abstract
Abstract Background OpenEvidence answers clinical questions using retrieval augmented generation on curated sources with explicit citations. The company reports that over 40% of U.S. physicians (~ 400,000) consult it daily. Although several studies have evaluated the platform, the evidence base remains heterogeneous. Objective To systematically review studies evaluating OpenEvidence for clinical question answering and decision support. Methods A systematic search of MEDLINE/PubMed, Scopus, Web of Science, and Google Scholar was conducted from database inception to January 2026. Peer-reviewed studies evaluating OpenEvidence in clinical or clinically simulated contexts were included. Study selection, data extraction, and risk-of-bias assessment were performed independently by two reviewers in accordance with PRISMA guidelines. Results Eleven studies published between 2024 and 2026 were included in the analysis. OpenEvidence was evaluated as the primary platform in eight studies and as a comparator in three. OpenEvidence demonstrated the ability to generate evidence-supported responses and avoided fabricated citations. Performance was strongest in structured, guideline-based contexts. However, accuracy varied in complex clinical scenarios, and the platform often reinforced rather than altered clinical decisions. Limitations included dependence on the available retrieval context, interpretive errors despite accurate citations, variability across clinical domains, and the fact…
How strong is the evidence?
Evidence Hub reads this as a systematic review. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.