AI in the clinic: nudges may stop doctors from blindly trusting ChatGPT

NCT ID NCT07328815

Completed Knowledge-focused Sponsor: Lahore University of Management Sciences Source: ClinicalTrials.gov ↗

First seen Jun 27, 2026 · Last updated Jun 27, 2026

Summary

This study tested whether behavioral nudges can reduce automation bias—when doctors uncritically accept AI recommendations. 72 physicians evaluated clinical cases with AI-generated suggestions, some containing errors. Half received nudges showing the AI's baseline accuracy and color-coded confidence signals. The goal was to see if these cues help doctors spot mistakes and improve diagnostic accuracy.

What this could mean

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

Active substance: behavioral nudge intervention
What this could lead to: If successful, this could lead to safer integration of AI tools like ChatGPT in medical diagnosis, helping doctors avoid blindly trusting incorrect AI suggestions.
What could go wrong: This is a small, completed study with 72 participants using simulated cases, so results may not apply to real-world clinical settings or larger populations.

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 DIAGNOSIS are added.

Our safety recommendation!

By submitting, you agree to our Terms of use

Conditions

The condition(s) this trial relates to.

disease

As listed by the trial registrant

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

DIAGNOSIS

Contacts and locations

Locations

Lahore University of Management Sciences

Lahore, Punjab Province, 54792, Pakistan

More trials for these conditions

Other studies related to the condition(s) this trial covers.