Using cardiac MRI and AI to predict outcomes after STEMI
Official title: Prognostic Value of Cardiac Magnetic Resonance Parameters in Patients With ST-Segment Elevation Myocardial Infarction
Run by Chinese PLA General Hospital · NCT07072858 · Data updated 2026-11-12
This project will try to use routine cardiac MRI scans plus AI to see if imaging features can predict long-term outcomes in people who had a STEMI treated with primary PCI.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years to 80 Years |
| Sex | All |
| Enrollment | 1000 (estimated) |
| Sponsor | Chinese PLA General Hospital Academic / other |
| Locations | 1 site (Beijing) |
| Status | Recruiting |
| Started | January 1, 2014 |
| Main results expected | December 30, 2025 |
| Study ends | December 30, 2025 |
| Registry record updated | July 18, 2025 |
| Trial ID | NCT07072858 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults aged 18–80 who had a confirmed ST-elevation myocardial infarction, were treated with primary PCI, can undergo CMR within seven days post-PCI, and can give informed consent are ideal candidates.
✕Probably not a fit
Patients with contraindications to MRI (incompatible implants or severe claustrophobia), recent revascularization within six months, severe valvular disease or known cardiomyopathy, marked conduction blocks that interfere with imaging, very low kidney function when contrast is anticipated, or who are pregnant or breastfeeding are unlikely to be eligible or to benefit from participation.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This is a prospective, multicenter observational study enrolling adults with ST-elevation myocardial infarction who undergo primary percutaneous coronary intervention. Participants receive comprehensive cardiac magnetic resonance (CMR) scanning—including cine and strain sequences—typically within seven days after PCI, and images are analyzed centrally. Advanced AI and radiomics/machine-learning methods extract high-dimensional features from multiple CMR sequences to identify imaging biomarkers reflecting myocardial structure, function, and deformation. Identified features will be tested for independent and incremental association with long-term clinical cardiovascular outcomes.
Why it matters
Potential benefit: If successful, the approach could help clinicians better identify patients at higher risk after STEMI so follow-up and treatments can be more precisely targeted.
How similar studies have gone: Conventional CMR markers such as infarct size, LVEF, and microvascular obstruction are established prognosticators, and emerging small-to-moderate studies using strain imaging and AI/radiomics have shown promising but not yet widely validated predictive performance.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Age between 18 and 80 years Diagnosed with ST-segment elevation myocardial infarction (STEMI), defined as chest pain with ST-segment elevation on ECG and elevated cardiac troponin levels Underwent primary percutaneous coronary intervention (PCI) Able to undergo cardiac magnetic resonance (CMR) imaging within 7 days post-PCI Provided written informed consent Exclusion Criteria: * Contraindications to CMR (e.g., severe claustrophobia, implanted cardiac defibrillators or non-compatible pacemakers) History of revascularization therapy (PCI or CABG) within the previous 6 months Severe valvular heart disease or known cardiomyopathy Presence of bundle branch block or fascicular block that interferes with image interpretation Known allergy to gadolinium-based contrast agents (for those undergoing contrast-enhanced sequences) Estimated glomerular filtration rate (eGFR) \<30 mL/min/1.73m² (if contrast use is anticipated) Pregnant or breastfeeding women
Where it's running
- Beijing, China Recruiting
Study contacts
- Study coordinator: XIN A, PhD
- Email: a2013346@hotmail.com
- Phone: +8613126526196
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
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.
-
Risk of malignant arrhythmias after acute coronary syndrome
This study tracks how often dangerous heart rhythms occur in adults admitted for ACS and looks for patterns that might predict them.
-
Smartphone AI help for prehospital ECG readings
This study tests whether using a smartphone AI (GPT-4o) to help prehospital providers read 12-lead ECGs improves accuracy in diagnosing acute coronary syndromes and related conditions.
-
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.
-
Optimal timing of staged complete revascularization in STEMI with multivessel disease
This trial tests whether performing staged complete revascularization during the hospital stay or after discharge is best for STEMI patients with multivessel disease.
-
Prediction score for death or lung transplant in emphysema caused by alpha-1 antitrypsin deficiency
This study tests a new prediction tool to identify people with emphysema due to alpha-1-antitrypsin deficiency who are at high risk of death or needing a lung transplant.
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.