Heart score calculator test using GPT-4o and Claude in chest pain patients

Is this trial a fit for you?

A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.

What this trial studies

In this prospective observational study, researchers will apply GPT-4o and Claude to anonymized, unstructured patient notes to generate HEART scores and forecast 30-day major adverse cardiac events. Each patient’s data (free-text history, ECG report text, troponin, and age) are processed independently by both models with fixed, deterministic settings. The model-derived HEART scores are compared against a three-expert consensus HEART score as the reference standard, with majority voting used for component-level scoring and a fourth adjudicator for any complete disagreement. The study plans to enroll 600 adult patients presenting with non-traumatic chest pain at a Turkish emergency department, with strict blinding between LLM outputs and the reference and outcome assessments.

Why it matters

Who can join: the full rules

INCLUSION CRITERIA:

* Age \>=18 years
* Chief complaint of non-traumatic chest pain at the emergency department
* Written informed consent obtained from the patient or legally authorized representative
* Availability for 30-day follow-up (reachable by telephone and/or actively registered in the e-Nabiz national health database)

EXCLUSION CRITERIA:

* Traumatic chest pain etiology
* ST-elevation myocardial infarction (STEMI) at presentation requiring immediate reperfusion protocol
* Refusal or subsequent withdrawal of informed consent
* Inability to complete the mandatory 30-day follow-up period

WITHDRAWAL CRITERIA:

* Patient or representative requests data withdrawal after initial consent
* Administrative identification of retrospective data entry after enrollment

Where it's running

• Marmara University Pendik Training and Research Hospital
  Istanbul, Istanbul, Turkey (Türkiye) Recruiting

Study contacts

• Study coordinator: Emir Unal, Assistant Professor
• Email: emirunal@gmail.com
• Phone: +905327766010

Similar studies

Other studies for the same condition or treatment. Recruiting studies are listed first.

• Does AI-based cephalometric tracing match digital manual tracing for orthodontic measurements?

  This study tests whether AI-powered cephalometric analysis can produce measurements similar to traditional digital tracing in 100 patient radiographs.

  Recruiting University of Pavia · Pavia, Italy · NCT07664488

• Multi-center artificial intelligence-based quantitative echocardiography evaluation

  This project will test whether AI can automatically and accurately measure heart chamber sizes, volumes, and function from echocardiograms in adults with common cardiovascular conditions.

  Recruiting at 37 sites First Hospital of China Medical University · Huainan, Anhui and 36 other locations · NCT07133516

• Deep-learning ECG to detect pulmonary hypertension

  This trial tests whether an AI-powered ECG can spot high blood pressure in the lungs (pulmonary hypertension) in adults aged 50–85 who have had a recent ECG.

  Recruiting National Defense Medical Center, Taiwan · Taipei · NCT07079592

• AI-assisted whole-course management for safe medicine use in advanced solid tumors

  A real-world study compares a smartphone-based digital management system with usual care to see if it reduces drug-related problems and healthcare needs for adults with advanced solid tumors receiving cancer therapy.

  Recruiting at 2 sites Tianjin Medical University Second Hospital · Tianjin, Tianjin Municipality and 1 other locations · NCT07917351

• AI support in emergency medicine helps doctors make differential diagnoses

  This study tests whether a generative AI tool can help emergency doctors arrive at more accurate differential diagnoses for adult patients at Karolinska University Hospital.

  Recruiting Region Stockholm · Stockholm, Huddinge · NCT07766863

• AI-assisted and traditional workflows for admission diagnosis and management planning

  This trial tests whether an AI-agent workflow helps doctors make better admission diagnoses and care plans on simulated cases, compared with plain AI-assisted and traditional workflows.

  Recruiting Second Affiliated Hospital, Zhejiang University, School of Medicine · Hangzhou, Zhejiang · NCT07760051

How to take part

1. Review the eligibility criteria above with your treating physician.
2. Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
3. Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.