This multicenter retrospective study aims to develop, validate, and clinically apply an artificial intelligence (AI)-powered electrocardiography (ECG) algorithm for the diagnosis and prognostic prediction of cardiovascular diseases, including coronary artery disease and heart failure. By utilizing encrypted raw 12-lead ECG text data and deep neural network models, the study evaluates the effectiveness of AI-enhanced ECG in detecting cardiac abnormalities and predicting clinical outcomes.
Patients aged 18 years or older diagnosed with cardiovascular diseases, including coronary artery disease and heart failure.
Patients with 12-lead electrocardiogram (ECG) records extractable as text (XML
None
Patients visiting the participating tertiary hospitals with extractable electrocardiogram records and diagnosed with cardiovascular diseases.
Cohort
Other
Retrospective ECG Data Analysis
Other interventionAnalysis of de-identified 12-lead electrocardiogram raw data using deep learning models for cardiovascular disease diagnosis and prognosis.
Diagnostic Performance (AUC-ROC) of AI-ECG Models
To evaluate the area under the receiver operating characteristic curve (AUC-ROC) of the deep neural network-based 12-lead ECG model for diagnosing cardiovascular diseases compared to reference clinical standards.
Sensitivity and Specificity of AI-ECG Models
To evaluate the association between AI-ECG risk scores and long-term clinical outcomes, including all-cause mortality and heart failure-related hospitalizations.
Click on the lead sponsor to view all of their trials.
