Truace
Subscribe

Clinician Use of an Artificial Intelligence-Enabled Clinical Information Platform

Importance: Despite growing interest in the use of artificial intelligence (AI) in medicine, empirical evidence on how clinicians use these tools is limited. Objective: To characterize clinician use of an AI-enabled clinical information platform, the distribution of use across the clinical workforce, and the purpose of submitted queries. Design, setting, and participants: This cross-sectional study analyzed clinicians with National Provider Identifier-verified accounts of a commonly used AI-enabled clinical info…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-1544· cite & verify
Clinician Use of an Artificial Intelligence-Enabled Clinical Information Platform
Doctor Wenlock outside St Thomas's Hospital - geograph.org.uk - 3101668 by PAUL FARMER. CC BY-SA 2.0 · https://creativecommons.org/licenses/by-sa/2.0

In brief

A cross-sectional analysis of verified clinician accounts on the OpenEvidence platform covered January 2024 through June 2026. About 952,000 clinicians, including roughly 556,000 physicians, sent 271 million queries, and a large language model classified the purpose and topic of a stratified sample of 38.8 million of them.

The findings show AI information tools becoming part of routine clinical practice within a short period, and they show who relies on them most. The study describes usage patterns rather than patient outcomes, so whether the queries improved care, or how accurate the answers were, is not established by this analysis.

Main points

  1. Average monthly queries per active user rose from 18.0 to 39.5 over the study period.
  2. Nurse practitioners and physician assistants each averaged 44.5 queries per active user-month, versus 37.1 for physicians.
  3. Physicians within a decade of graduation had a use ratio of 2.54, and residents and fellows 1.84.
  4. Use was lower in ophthalmology (0.23), radiology (0.24) and orthopedics (0.24) than in oncology and hematology (2.00).
  5. Diagnosis accounted for 13.9% of queries, well below treatment and management at 33.1%.

The gain

Clinicians adopted an AI clinical information platform at scale, with monthly active users rising from 355 to 703,265 and heavy use for treatment and management questions.

The rundown

The study used National Provider Identifier-verified accounts, which lets usage be compared with each group's share of the national workforce. Use ratios above 1 indicate overrepresentation relative to workforce size.

Specialty differences were notable. Oncology and hematology (2.00), internal medicine (1.88) and family medicine (1.80) used the platform more than average, while procedural and diagnostic specialties used it far less.

Many queries went beyond clinicians' own specialties. Queries on topics outside a physician's own specialty ranged from 35% among oncologists and hematologists to 88% among emergency department physicians, suggesting the tool is used to reach unfamiliar clinical areas.

Sources

  1. Peer-reviewedJAMA2026-10-15

The debate