The CNN-LSTM deep learning model achieved an AUC of 1.00 for STEMI detection, surpassing the AUC of experienced doctors (0.94) in identifying STEMI cases.
Case-Control (n=883)
No
Does a deep learning model based on 12-lead ECG accurately detect STEMI and identify the culprit vessel compared to experienced doctors?
A deep learning model using raw 12-lead ECG data can detect STEMI and identify the culprit vessel with high accuracy, potentially outperforming or matching experienced physicians.
Effect estimate: AUC 0.99 for CNN-LSTM
Early diagnosis of acute ST-segment elevation myocardial infarction (STEMI) and early determination of the culprit vessel are associated with a better clinical outcome. We developed three deep learning (DL) models for detecting STEMIs and culprit vessels based on 12-lead electrocardiography (ECG) and compared them with conclusions of experienced doctors, including cardiologists, emergency physicians, and internists. After screening the coronary angiography (CAG) results, 883 cases (506 control and 377 STEMI) from internal and external datasets were enrolled for testing DL models. Convolutional neural network-long short-term memory (CNN-LSTM) (AUC: 0.99) performed better than CNN, LSTM, and doctors in detecting STEMI. Deep learning models (AUC: 0.96) performed similarly to experienced cardiologists and emergency physicians in discriminating the left anterior descending (LAD) artery. Regarding distinguishing RCA from LCX, DL models were comparable to doctors (AUC: 0.81). In summary, we developed ECG-based DL diagnosis systems to detect STEMI and predict culprit vessel occlusion, thus enhancing the accuracy and effectiveness of STEMI diagnosis.
Wu et al. (Thu,) conducted a case-control in ST-segment elevation myocardial infarction (STEMI) (n=883). Deep Learning (DL) models for STEMI detection vs. Conclusions of experienced doctors (cardiologists, emergency physicians, and internists) was evaluated on Detection of STEMI (AUC 0.99 for CNN-LSTM). The CNN-LSTM deep learning model achieved an AUC of 1.00 for STEMI detection, surpassing the AUC of experienced doctors (0.94) in identifying STEMI cases.