Deep Learning Networks Accurately Detect ST-Segment Elevation Myocardial Infarction and Culprit Vessel

Frontiers in Cardiovascular Medicine

article

Lin Wu¹  Guifang Huang³  Xianguan Yu¹  Minzhong Ye⁴  Lu Liu⁵  Yesheng Ling¹  Xiangyu Liu⁶  Dinghui Liu¹  Bin Zhou¹  Yong Liu¹  Jianrui Zheng¹  Suzhen Liang¹  Rui Pu¹  Xuemin He²  Yanming Chen²  Lanqing Han³  Xiaoxian Qian¹ 

[1] Department of Cardiology, The Third Affiliated Hospital, Sun Yat-sen University;Department of Endocrine and Metabolic Diseases, The Third Affiliated Hospital, Sun Yat-sen University;Center for Artificial Intelligence, Research Institute of Tsinghua;Novelty-Checking Center, Guangdong Institute of Scientific and Technical Information;Department of Anesthesiology, The Third Affiliated Hospital, Sun Yat-sen University;School of Computer Science and Engineering, Sun Yat-sen University

关键词: ST-segment elevation myocardial infarction (STEMI);    electrocardiogram (ECG);    convolutional neural network (CNN);    long short-term memory (LSTM);    CNN-LSTM;    deep learning (DL);    culprit vessel;   

DOI  :  10.3389/fcvm.2022.797207

学科分类：地球科学(综合)

来源: Frontiers

【 摘 要 】

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.

【 授权许可】

CC BY