AI doctor assistant tested in 1,000 ICU patients to cut errors
NCT ID NCT07293078
First seen Jan 05, 2026 · Last updated Jun 18, 2026 · Updated 28 times
Summary
This study tests whether an AI tool (ChatGPT-5) can help doctors in the intensive care unit (ICU) make better decisions. About 1,000 critically ill adults will be randomly assigned to standard care or AI-assisted care. The AI will analyze patient data and suggest diagnoses and treatments, but doctors can choose to follow or ignore the advice. The main goal is to see if AI reduces medical errors, like missed diagnoses or wrong treatments.
Disclaimer
Read more
Show less
This is a summary of
the original study
.
Summaries may miss details or leave out important information. Before applying or accepting participation, make sure you have read and understood the full study. Curemydisease.com takes no responsibility whatsoever for anything missed, misunderstood, or acted upon as a result of our summary — we know it does not capture everything.
This is a summary of the original study . Summaries may miss details or leave out important information. Before applying or accepting participation, make sure you have read and understood the full study. Curemydisease.com takes no responsibility whatsoever for anything missed, misunderstood, or acted upon as a result of our summary — we know it does not capture everything.
Get updates
Get notified about this study
Sign up to get updates when this study changes or when new studies for ACUTE KIDNEY INJURY are added.
Genom att skicka in godkänner du våra Användarvillkor
Contacts and locations
Show contact details
Enter your email to view the contact information for this study.
Genom att skicka in godkänner du våra Användarvillkor
Study contacts
-
Contact
Phone: •••-•••-•••• Email: •••••@•••••
Locations
-
Framingham Union Hospital/MetroWest Medical Center
Framingham, Massachusetts, 01702, United States
Contact Email: •••••@•••••
Contact Phone: •••-•••-•••• Email: •••••@•••••
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.