UnknownNCT07199231

A Comparative Performance Evaluation of Four Publicly Available Large Language Models Against Gold Standard Medical References

Sponsor: Cambridge Health Alliance

Trial Details

Condition	AI (Artificial Intelligence), Large Language Model, Generative Artificial Intelligence
Intervention	AI clinical reference tool
Status	Unknown
Participants	20
Est. Completion	30 May 2026
Last Updated	22 May 2026

Primary Outcome

Clinical Appropriateness: Mean with SD; Clinical Appropriateness: Median; Clinical Appropriateness: Interrater Reliability

Eligibility Criteria

Inclusion Criteria

Inclusion Criteria: * Active trainees PGY-1 through PGY-6 in Internal Medicine, Family Medicine, Adult Psychiatry, or Child Psychiatry at Cambridge Health Alliance * Must agree to the study protocol requirements outlined in the study description. Exclusion Criteria: * Anyone who does not meet inclusion criteria * Residents who plan to leave CHA prior to the end of the study collection period.

Trial Sites

Countries

United States

View Registry Entry

Related Analysis

First Real-World Study Evaluates AI Clinical Decision Tools in Resident Training — Cambridge Health Alliance Trial

Cambridge Health Alliance launches first real-world study comparing AI clinical decision tools with traditional medical references in resident training. The trial evaluates OpenEvidence, ChatGPT, Claude, and Gemini for clinical appropriateness in actual patient care settings.

Read full article →

This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service