AI takes on heart risk: GPT-4o and claude face off against doctors in chest pain study
NCT ID NCT07626060
First seen Jun 27, 2026 · Last updated Jun 27, 2026
Summary
This study will enroll 690 adults who come to the emergency room with chest pain (not from injury). Researchers will test whether two AI models, GPT-4o and Claude, can correctly calculate a heart risk score (HEART score) from patient notes and predict if a serious heart event will happen within 30 days. The AI's performance will be compared to a consensus score from three emergency medicine doctors. The goal is to see if AI can help speed up and improve heart risk assessment in busy ERs.
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 ARTIFICIAL INTELLIGENCE (AI) 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
-
Marmara University Pendik Training and Research Hospital
RECRUITINGIstanbul, Istanbul, 34870, Turkey (Türkiye)
More trials for these conditions
Other studies related to the condition(s) this trial covers.
- Can AI-Perfect faces fuel surgery anxiety?
- AI vs. Doctor's intuition: which leads to better diagnoses?
- Can AI learn to grade endoscopy quality from video?
- AI tutors take on nursing education: can they sharpen clinical skills?
- Can AI help nurses learn to diagnose better?
- AI assistant could spot hidden liver and pancreas cancers earlier