AI-assisted interpretation of chest pain CT in the emergency department
Official title: Evaluation of the Impact of AI-Based Cardiac CT Interpretation Tool on Emergency Physicians' Decision-Making
Run by Yonsei University · NCT07235657 · Data updated 2026-11-12
A pragmatic randomized trial tests whether an AI tool (Angiomics) helps emergency physicians interpret coronary CT angiography in adults with acute chest pain.
Quick facts
| Study type | Interventional |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 620 (estimated) |
| Sponsor | Yonsei University Academic / other |
| Drugs / interventions | radiation |
| Locations | 1 site (Seoul) |
| Status | Recruiting |
| Started | December 29, 2025 |
| Main results expected | June 2027 |
| Study ends | August 2027 |
| Registry record updated | November 5, 2026 |
| Trial ID | NCT07235657 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults 18+ with acute chest pain or chest discomfort, intermediate risk (HEART score 4-6), for whom CCTA is ordered.
✕Probably not a fit
Patients with non-ACS etiologies, prior revascularization, intracardiac devices, or contraindications to contrast may not benefit.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This prospective study compares AI-assisted CCTA interpretation to standard interpretation without AI in emergency department patients with acute chest pain and intermediate risk. It aims to measure diagnostic performance, physician confidence, and decision-making impact. The trial uses real-world ED workflow to assess how AI support influences speed and accuracy of ACS assessment. Eligible adults are 18 years or older with chest pain, intermediate HEART score, and a CCTA ordered by their clinician. Outcomes include diagnostic accuracy, confidence levels, and changes in clinical management.
Why it matters
Potential benefit: If successful, AI-assisted interpretation could improve diagnostic accuracy and speed, and help ED physicians make better treatment decisions.
How similar studies have gone: AI-assisted imaging tools have shown promise in improving interpretation accuracy in some emergency imaging studies, but real-world ED effectiveness requires further validation.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: Adults aged 18 years or older Patients presenting to the emergency department with acute chest pain or chest discomfort Patients assessed as intermediate risk (Heart Score 4-6) Patients for whom CCTA was ordered by the treating physician as part of routine clinical care Exclusion Criteria: Prior history of coronary revascularization (coronary artery bypass graft surgery or stent placement) Presence of intracardiac metallic devices such as pacemaker or prosthetic heart valves Contraindications to contrast media (e.g., contrast allergy, severe renal impairment with eGFR \< 30 mL/min/1.73 m²) Patients unable to cooperate (e.g., severe anxiety, non-cooperation) Non-diagnostic CCTA images are identified after image acquisition and handled according to the protocol-defined analysis exclusions.
Where it's running
-
Yonsei University College of Medicine, Yonsei University Severance Hospital
Seoul, South Korea Recruiting
Study contacts
- Study coordinator: arom choi, MD
- Email: aromchoi@yuhs.ac
- Phone: +82-2-2228-2465
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Freesolve resorbable magnesium scaffold vs. Xience stent for up to two new heart artery lesions
This trial tests whether the Freesolve resorbable magnesium scaffold works as well as the Xience drug-eluting stent for treating up to two new coronary artery lesions in adults.
-
AI-driven Medipixel fractional flow reserve to guide PCI
This test checks whether an AI-based, angiography-derived Medipixel FFR method can guide PCI as safely and effectively as standard invasive pressure-wire FFR in adults with coronary artery disease.
-
Comparing heart imaging techniques for coronary artery disease
This study is testing if a new heart imaging method can better identify problems in patients suspected of having coronary artery disease compared to a traditional imaging technique.
-
Comparing two types of drug-coated stents for patients at high bleeding risk
This study is testing if a new type of drug-coated stent is just as good and safe as a standard one for people with coronary artery disease who are at high risk of bleeding.
-
Single versus dual antiplatelet therapy after drug-coated balloon angioplasty in elderly or high-bleeding-risk patients
This study tests whether taking one antiplatelet medicine is as safe and causes less bleeding than taking two medicines for people aged 75 or older, or adults at high bleeding risk, after drug-coated balloon angioplasty for coronary artery disease.
-
Heart registry for patients after coronary interventions in South East Netherlands
This study is creating a registry to help doctors better understand and treat patients in South East Netherlands who have had heart procedures, aiming to reduce their risk of future heart problems.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.