Development of Clinically Validated Artificial Intelligence Model for Detecting ST-segment Elevation Myocardial
Sang-Hyup Lee1, Kyu Lee Jeon2, Yong-Joon Lee1
1Division of Cardiology, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea.
Insights
An artificial intelligence (AI) model accurately diagnoses ST-segment elevation myocardial infarction (STEMI) using electrocardiogram (ECG) data. This AI tool aids in timely cardiac catheterization laboratory activation, improving patient care for STEMI.
Area of Science:
- Cardiology
- Artificial Intelligence
- Medical Diagnostics
Background:
- Primary percutaneous coronary intervention is crucial for ST-segment elevation myocardial infarction (STEMI).
- Cardiac catheterization laboratory activation for STEMI is often suboptimal.
- Accurate and timely diagnosis is essential for effective STEMI treatment.
Purpose of the Study:
- To develop a precise artificial intelligence (AI) model for diagnosing STEMI.
- To improve the accuracy of cardiac catheterization laboratory activation for STEMI patients.
Main Methods:
- Utilized electrocardiogram (ECG) waveform data from a Korean percutaneous coronary intervention registry.
- Developed a deep ensemble model combining 5 convolutional neural networks.
- Validated the AI model using clinical data, physician comparisons, and external datasets.
Main Results:
- The AI model achieved 92.1% accuracy, 95.4% sensitivity, and 91.8% specificity on 18,697 ECGs.
- Demonstrated outstanding and balanced performance across clinical validation, physician comparison, and external validation.
- The AI model exhibited reasonable explainability via gradient-weighted class activation mapping.
Conclusions:
- The deep ensemble AI model demonstrates robust performance in diagnosing STEMI.
- The AI model shows potential for improving cardiac catheterization laboratory activation efficiency.
- Further prospective validation is recommended to confirm clinical benefits in real-world settings.
Study Objective:
Although the importance of primary percutaneous coronary intervention has been emphasized for ST-segment elevation myocardial infarction (STEMI), the appropriateness of the cardiac catheterization laboratory activation remains suboptimal. This study aimed to develop a precise artificial intelligence (AI) model for the diagnosis of STEMI and accurate cardiac catheterization laboratory activation.
Methods:
We used electrocardiography (ECG) waveform data from a prospective percutaneous coronary intervention registry in Korea in this study. Two independent board-certified cardiologists established a criterion standard (STEMI or Not STEMI) for each ECG based on corresponding coronary angiography data. We developed a deep ensemble model by combining 5 convolutional neural networks. In addition, we performed clinical validation based on a symptom-based ECG data set, comparisons with clinical physicians, and external validation.
Results:
We used 18,697 ECGs for the model development data set, and 1,745 (9.3%) were STEMI. The AI model achieved an accuracy of 92.1%, sensitivity of 95.4%, and specificity of 91.8 %. The performances of the AI model were well balanced and outstanding in the clinical validation, comparison with clinical physicians, and the external validation.
Conclusion:
The deep ensemble AI model showed a well-balanced and outstanding performance. As visualized with gradient-weighted class activation mapping, the AI model has a reasonable explainability. Further studies with prospective validation regarding clinical benefit in a real-world setting should be warranted.
