← Back to Search

GPT-4 for Diagnosis

N/A
Waitlist Available
Led By Jonathan H Chen, MD, PhD
Research Sponsored by Stanford University
Eligibility Criteria Checklist
Specific guidelines that determine who can or cannot participate in a clinical trial
Must have
Timeline
Screening 3 weeks
Treatment Varies
Follow Up during evaluation
Awards & highlights
No Placebo-Only Group

Summary

This trial will compare the performance of using a language model called GPT-4 to traditional diagnostic tools. The goal is to see if using GPT-4 helps with diagnosing medical cases.

Who is the study for?
This trial is for licensed physicians who have completed at least two years of post-graduate medical training (PGY2) and specialize in internal medicine, family medicine, or emergency medicine.
What is being tested?
The study is testing the impact of using GPT-4, an advanced language model, on doctors' diagnostic reasoning abilities compared to traditional decision support tools in case-based scenarios.
What are the potential side effects?
Since this trial involves a software tool rather than a medication or device, there are no direct physical side effects. However, potential risks could include data privacy concerns and reliance on AI for clinical decisions.

Timeline

Screening ~ 3 weeks
Treatment ~ Varies
Follow Up ~during evaluation
This trial's timeline: 3 weeks for screening, Varies for treatment, and during evaluation for reporting.

Treatment Details

Study Objectives

Study objectives can provide a clearer picture of what you can expect from a treatment.
Primary study objectives
Diagnostic reasoning
Secondary study objectives
Time Spent on Diagnosis

Awards & Highlights

No Placebo-Only Group
All patients enrolled in this study will receive some form of active treatment.

Trial Design

2Treatment groups
Active Control
Group I: Usual resourcesActive Control1 Intervention
Group will not be given access to GPT-4 but will be encouraged to use any resources they wish besides large language models (UpToDate, Dynamed, google, etc).
Group II: GPT-4Active Control1 Intervention
Group will be given access to GPT-4.

Find a Location

Who is running the clinical trial?

University of MinnesotaOTHER
1,423 Previous Clinical Trials
1,619,735 Total Patients Enrolled
Stanford UniversityLead Sponsor
2,468 Previous Clinical Trials
17,496,232 Total Patients Enrolled
Beth Israel Deaconess Medical CenterOTHER
853 Previous Clinical Trials
12,929,899 Total Patients Enrolled
~26 spots leftby Nov 2025
Unbiased ResultsWe believe in providing patients with all the options.
Your Data Stays Your DataWe only share your information with the clinical trials you're trying to access.
Verified Trials OnlyAll of our trials are run by licensed doctors, researchers, and healthcare companies.
Back to top