Acute Myocardial Infarction Prediction Using Artificial Intelligence Applied to Electrocardiogram Images

Condition(s) studied

Investigational drug(s) / intervention(s)

Deep learning approach of ECG for AMI detection: AMIdECG was trained to perform AMI detection in a supervised manner as a classification task. And the classification labels of AMI subtypes (" STEMI "or" NSTEMI ") or non-AMI states used during the training phase are real-world diagnostic results

Study summary

The goal of this observational study is to develop and validate an artificial intelligence(AI)-based prediction model for new-onset acute myocardial infarction(AMI) using electrocardiogram(ECG) data. The main question it aims to answer is whether the AI-based ECG accurately forecast new-onset AMI by previous ECG data with 'normal' diagnosis?

Eligibility

Primary outcome measure(s)

• Acute myocardial infarction (AMI) — From June 2025 to April 2026
  AMI was defined as STEMI, NSTEMI using ICD-10.

Trial sites (1)

More Guangdong Provincial People's Hospital trials in China

Other trials for the same condition