Can a smarter AI display help doctors make better diagnoses?

NCT ID NCT07457840

First seen Jun 25, 2026 · Last updated Jul 15, 2026 · Updated 3 times

Summary

This study tests whether showing AI predictions as a shift from a doctor's own initial guess (Bayesian update) improves diagnostic accuracy compared to showing raw AI probabilities. About 100 healthcare professionals will review 8 simulated patient cases involving chest pain or shortness of breath. The goal is to see if this approach helps doctors make more accurate diagnoses and trust the AI more, even when the AI is misleading.

What this could mean

Our plain-language read of the trial. This is informational only — not medical advice or a prediction.

Active substance
Bayesian-updated post-test probability display
What this could lead to
If successful, this could improve how doctors use AI tools to make more accurate diagnoses.
What could go wrong
This is a small, early-stage study using simulated cases, not real patients. Results may not translate to actual clinical settings.

This is an AI summary of the original study and may miss details. Read our disclaimer.

Get updates

Get notified about this study

Sign up to get updates when this study changes or when new studies for DIAGNOSTIC DECISION MAKING are added.

Our safety recommendation!

By submitting, you agree to our Terms of use

As listed by the trial registrant

The condition terms exactly as the trial's registrant entered them.

Contacts and locations

Locations

  • ZSFG

    San Francisco, California, 94110, United States