Development and Validation of a Cardiac Magnetic Resonance-Based Multimodal Deep Learning Model for Long-Term Outcome Prediction in ST-Segment Elevation Myocardial Infarction
For patients and families
In plain language
An automatic summary of structured registry data. It is an orientation aid, not a substitute for the official protocol or a physician assessment.
- What is being studied
- This is an observational study: the protocol does not assign a study treatment.
- Who it may be relevant to
- Registry conditions: ST Elevation (STEMI) Myocardial Infarction. Basic parameters: from 18 years · All.
- What needs checking
- Age, condition and sex are only basic indicators. Prior treatment, laboratory values and other mandatory requirements appear in the eligibility criteria below.
- Where it takes place
- China
- Next step
- Save the trial, show it to the treating physician, and confirm current recruitment with the study center. Costs, documents and travel →
Unsure about the terms? Read our patient guide →
Overview
Objective: This study aims to develop and test a novel artificial intelligence-based prediction model. This model will integrate cardiac magnetic resonance imaging and clinical data to predict the long-term risk of major adverse cardiovascular events in patients who have undergone emergency percutaneous coronary intervention for ST-segment elevation myocardial infarction. Description: This study plans to enroll patients with STEMI who have received primary PCI. Approximately one week after the procedure, patients will undergo a cardiac magnetic resonance scan. Concurrently, we will collect patients' basic information, blood test results during treatment, and procedural records. Thereafter, patients will be followed up regularly (every six months) to record the occurrence of any major adverse cardiac events, such as cardiovascular death, recurrent myocardial infarction, hospitalization for heart failure, or unplanned repeat revascularization.All collected data, including clinical data and analyzed cardiac MR images, will be used to construct a multimodal deep learning model. The model will learn to identify features associated with future cardiac problems. The accuracy of the model will be tested and validated in different patient groups. Potential Impact: If successful, this prediction tool could assist physicians in identifying high-risk patients earlier and more accurately, enabling closer monitoring and more timely interventions, ultimately improving the long-term prognosis for these patients.
Primary outcome measures
- major adverse cardiac events [Time frame: 2024-2026]
Eligibility criteria
Inclusion criteria
(1)diagnosis of STEMI , elevated cardiac biomarkers (troponin) above the 99th percentile upper reference limit together with at least one of the following: chest pain lasting >30 minutes; ST-segment elevation ≥0.1 mV in two or more contiguous limb leads or ≥0.2 mV in two or more contiguous precordial leads on a 12-lead ECG; (2) age >18 years, first episode of STEMI treated with primary PCI; (3)diagnostic and therapeutic management consistent with current clinical standards and guideline recommendations; (4) Killip class≤III at presentation; (5) provided informed consent for CMR imaging and clinical follow-up.
Exclusion criteria
(1) contraindications to CMR (e.g., cardiac pacemakers, severe claustrophobia, known allergy to gadolinium-based contrast agents, or impaired renal function defined as eGFR<30mL/min/1.73m²). (2) structural heart disease (e.g., significant valvular or congenital disease); (3) documented history of prior myocardial infarction, PCI, or coronary artery bypass grafting (CABG)； (4) comorbidities severely compromising overall prognosis or the ability to undergo the study procedures, such as serious hematological disorders, active systemic infections, or active malignancy; (5) cognitive impairment or psychiatric conditions precluding adequate cooperation with the CMR examination or clinical follow-up; (6) Poor-quality CMR images or missing essential sequences precluding accurate quantitative analysis.
Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.
Healthy volunteers: No
Study design
- Observational model
- Cohort
Study locations
China · 1 center
- Chinese PLA General Hospital — Beijing
Identifiers
NCT: NCT07277400 · CMR-DL