CI

At a glance

ClinicalIndex Comparison Record
N/ACompleted· 27 enrolled
Drug / intervention
OpenEvidence +1 moreother
Likely dose
Not stated in record
Structured eligibility isn't available for this trial yet — see the full criteria in the Eligibility tab below.

Standardized by ClinicalIndex from the ClinicalTrials.gov record · verify against the source.

Search/NCT07037940
NCT07037940N/ACompleted

Comparing Clinical Key AI and GPT-4 for Diagnostic Reasoning and Management Decisions

Montefiore Medical Center·interventional·Posted Jun 26, 2025·Updated Apr 9, 2026

In Brief

A clinical study evaluating OpenEvidence and GPT-4 for Large Language Models. Completed, enrolled 27 participants across 2 sites.

Detailed Summary

Clinical decision support tools powered by artificial intelligence are being rapidly integrated into medical practice. Two leading systems currently available to clinicians are OpenEvidence, which uses retrieval-augmented generation to access medical literature, and GPT-4, a large language model. While both tools show promise, their relative effectiveness in supporting clinical decision-making has not been directly compared. This study aims to evaluate how these tools influence diagnostic reasoning and management decisions among internal medicine physicians.

Study Details

Study Typeinterventional
Allocation--
Masking--
Primary Purpose--
CountriesUnited States
Collaborators--

Timeline

N/ACompletedFinished
2026
First PostedJun 26, 2025
Enrollment StartJul 3, 2025
Primary CompletionDec 30, 2025
TodayJul 2, 2026
Enrollment to primary: 6 monthsPosted 1.0 years ago

Interventions

OpenEvidenceother

Medical information platform which uses retrieval-augmented generation to access medical literature

GPT-4other

A chatbot application developed that uses GPT-4, a large language model, to engage in conversational interactions with users.