AI doctor in the ICU: can ChatGPT-5 save lives?

NCT ID NCT07293078

First seen Jun 26, 2026 · Last updated Jun 27, 2026 · Updated 1 time

Summary

This study tests whether an AI model (ChatGPT-5) can help doctors make better decisions for critically ill patients in the intensive care unit (ICU). About 1000 adults admitted to the ICU will be randomly assigned to standard care or care where the AI provides diagnostic and treatment suggestions. The goal is to see if the AI reduces medical errors and improves outcomes like survival and hospital stay length.

What this could mean

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

Active substance
ChatGPT-5 (a large language model used for decision support)
What this could lead to
If successful, this could show that AI helps reduce medical errors in the ICU, potentially leading to safer care for critically ill patients.
What could go wrong
This is an early-phase trial (Phase 1/2) with 1000 patients, so results may not apply broadly. The AI's recommendations might not always be accurate or helpful, and there is a risk of over-reliance on technology.

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 ACUTE KIDNEY INJURY are added.

Our safety recommendation!

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

  • Framingham Union Hospital/MetroWest Medical Center

    Framingham, Massachusetts, 01702, United States

More trials for these conditions

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