AI could predict patient crashes before they happen

NCT ID NCT06574906

Ongoing Knowledge-focused Sponsor: Kepler University Hospital Source: ClinicalTrials.gov ↗

First seen Jun 26, 2026 · Last updated Jun 26, 2026

Summary

This study tests whether machine learning can predict changes in early warning scores—vital signs that show if a patient is getting worse—in general hospital wards. Researchers will analyze data from 3,000 patients to see if AI can spot trouble earlier than current spot-check methods. The goal is to give nurses and doctors a heads-up before a patient's condition becomes critical.

What this could mean

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

What this could lead to: If successful, this could lead to an AI system that alerts hospital staff to patient deterioration before it becomes life-threatening, potentially saving lives.
What could go wrong: This is an observational study using existing data, so it won't directly test a treatment. The AI predictions may not work perfectly in real-world settings or for all patients.

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 PATIENT SAFETY 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.

PATIENT SAFETY

Contacts and locations

Locations

Johannes Kepler University, Kepler University Hospital

Linz, Upper Austria, 4020, Austria

More trials for these conditions

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