Chatbot boosts doctor trust in AI for bleeding emergencies?
NCT ID NCT05816473
First seen Jun 24, 2026 · Last updated Jun 27, 2026 · Updated 1 time
Summary
This study tested whether adding a chatbot interface makes doctors more likely to trust and use an AI tool that predicts risk in patients with upper stomach bleeding. 108 medical residents participated in simulated emergency scenarios, some using the AI alone and others using the AI with a chatbot. The goal was to measure changes in trust and usability, not to treat real patients.
What this could mean
Our plain-language read of the trial. This is informational only — not medical advice or a prediction.
- Active substance
- Large Language Model (LLM) chatbot interface
- What this could lead to
- If successful, this could show how to design AI tools that doctors trust and actually use in emergencies like stomach bleeding.
- What could go wrong
- This was a small simulation study with 108 residents, not real patients. Results may not translate to actual hospital settings or other user groups.
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 GASTROINTESTINAL HEMORRHAGE are added.
By submitting, you agree to our Terms of use
Conditions
The condition(s) this trial relates to.
As listed by the trial registrant
The condition terms exactly as the trial's registrant entered them.
Contacts and locations
Locations
-
Yale New Haven Hospital
New Haven, Connecticut, 06510, United States
More trials for these conditions
Other studies related to the condition(s) this trial covers.
- Medical glue vs. internal bleeding: a new hope?
- Could a common gut drug clear the way for life-saving endoscopy?
- Can dry plasma save lives in the field? new trial aims to find out
- Experimental antibody shows promise for rare amyloid disease
- Rare liver disease study could change how doctors treat dangerous complications