OpenEvidence drew 271 million queries from 952,008 U.S. clinicians between January 2024 and June 2026, according to a study published Oct. 15 in JAMA.
Researchers from Somerville, Mass.-based Mass General Brigham and Boston-based Harvard Medical School analyzed query logs from OpenEvidence users with verified National Provider Identifiers. Vishal Patel, MD, and Samuel Finlayson, MD, PhD, contributed equally as lead authors, and Anupam Jena, MD, PhD, oversaw the study.
Dr. Finlayson and two other co-authors, including OpenEvidence’s chief medical officer, were OpenEvidence employees during the study. The company provided the data and contributed to the analysis.
Monthly active users grew from 355 in January 2024 to 703,265 in June 2026. Average monthly queries per active user rose from 18 to 39.5, and month-over-month retention climbed from about 70% to 90%.
Physicians accounted for 556,200 users. Nurse practitioners and physician assistants used the platform most intensively, at 44.5 queries per active user-month, compared with 37.1 for physicians. Physicians within a decade of medical school graduation made up 24.3% of the physician workforce but submitted 61.8% of physician queries.
Treatment and management accounted for 33.1% of physician queries, and diagnosis accounted for 13.9%. Physicians also frequently looked beyond their own field. Out-of-specialty queries ranged from 35% among oncologists and hematologists to 88% among emergency physicians.
The authors said most clinical AI evaluations test diagnostic accuracy and knowledge recall. Performance on treatment selection, medication guidance and evidence synthesis, which they said dominate real-world use, remains largely unmeasured.
Because the study covered only queries in a single platform’s main question interface, the authors described the counts as lower bounds on use.
The post OpenEvidence drew 271M queries from 952,000 clinicians in 2.5 years appeared first on Becker's Hospital Review | Healthcare News & Analysis.