Artificial intelligence-enhanced electrocardiography analysis as a promising tool for predicting obstructive coronary
Jiesuck Park1,2, Joonghee Kim3,4, Si-Hyuck Kang1,2
1Department of Cardiology, Seoul National University Bundang Hospital, Gumi-ro 173beon-gil, Bundang-gu, Seongnam-si, Gyeonggi-do 13620, Republic of Korea.
Insights
Artificial intelligence (AI) analysis of electrocardiograms (ECGs) can predict obstructive coronary artery disease (CAD) in patients with stable angina. This AI tool shows feasibility and clinical utility for diagnosing CAD using ECG data.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Imaging
Background:
- Clinical feasibility of AI-based ECG analysis for obstructive coronary artery disease (CAD) lacks validation in large stable angina cohorts.
- Accurate prediction of obstructive CAD is crucial for timely intervention and improved patient outcomes.
Purpose of the Study:
- To validate the clinical feasibility of an AI-based quantitative ECG (QCG) analysis for predicting obstructive and extensive CAD in patients with stable angina.
- To assess the predictive performance of QCG risk scores against established clinical risk factors.
Main Methods:
- A deep learning framework was developed for QCG analysis, trained on over 50,000 ECGs from 21,000+ patients.
- Internal and external validation cohorts of stable angina patients (n=4517) underwent coronary imaging for obstructive CAD assessment.
- QCG risk scores (QCGObstCAD and QCGExtCAD) were derived and compared with invasive/CT angiography findings and clinical risk factors.
Main Results:
- QCG scores significantly correlated with the presence and severity of obstructive and extensive CAD (P < 0.001).
- QCGObstCAD demonstrated good predictive ability for obstructive CAD (AUCs 0.731-0.781) and severe obstructive CAD (AUCs 0.780-0.786).
- QCG scores provided independent and incremental predictive value for CAD beyond traditional risk factors.
Conclusions:
- AI-based QCG analysis is clinically feasible for predicting obstructive CAD in stable angina patients.
- The QCG tool demonstrates robust performance in identifying obstructive and extensive CAD, including severe stenosis and multivessel disease.
- QCG analysis offers a promising, non-invasive approach to enhance CAD risk stratification.
Aims:
The clinical feasibility of artificial intelligence (AI)-based electrocardiography (ECG) analysis for predicting obstructive coronary artery disease (CAD) has not been sufficiently validated in patients with stable angina, especially in large sample sizes.
Methods And Results:
A deep learning framework for the quantitative ECG (QCG) analysis was trained and internally tested to derive the risk scores (0-100) for obstructive CAD (QCGObstCAD) and extensive CAD (QCGExtCAD) using 50 756 ECG images from 21 866 patients who underwent coronary artery evaluation for chest pain (invasive coronary or computed tomography angiography). External validation was performed in 4517 patients with stable angina who underwent coronary imaging to identify obstructive CAD. The QCGObstCAD and QCGExtCAD scores were significantly increased in the presence of obstructive and extensive CAD (all P < 0.001) and with increasing degrees of stenosis and disease burden, respectively (all P trend < 0.001). In the internal and external tests, QCGObstCAD exhibited a good predictive ability for obstructive CAD [area under the curve (AUC), 0.781 and 0.731, respectively] and severe obstructive CAD (AUC, 0.780 and 0.786, respectively), and QCGExtCAD exhibited a good predictive ability for extensive CAD (AUC, 0.689 and 0.784). In the external test, the QCGObstCAD and QCGExtCAD scores demonstrated independent and incremental predictive values for obstructive and extensive CAD, respectively, over that with conventional clinical risk factors. The QCG scores demonstrated significant associations with lesion characteristics, such as the fractional flow reserve, coronary calcification score, and total plaque volume.
Conclusion:
The AI-based QCG analysis for predicting obstructive CAD in patients with stable angina, including those with severe stenosis and multivessel disease, is feasible.
