1. A Deep Learning–Enabled Electrocardiogram Model for the Identification of a Rare Inherited Arrhythmia: Brugada Syndrome
- Author
-
Chin-Yu Lin, Ting-Yung Chang, Chih Min Liu, Tze-Fan Chao, Fa Po Chung, Kai-Wen Hu, Ta-Chuan Tuan, Jo-Nan Liao, Cathy S.J. Fann, Satoshi Higa, Chien-Liang Liu, Yenn Jiang Lin, Yu-Feng Hu, Vincent S. Tseng, Li-Wei Lo, Shih Lin Chang, Nobumori Yagi, and Shih Ann Chen
- Subjects
Adult ,Male ,medicine.medical_specialty ,Adolescent ,Taiwan ,Sudden cardiac death ,Electrocardiography ,Young Adult ,Deep Learning ,Rare Diseases ,Cohen's kappa ,Internal medicine ,medicine ,Humans ,Diagnosis, Computer-Assisted ,cardiovascular diseases ,Medical diagnosis ,Brugada Syndrome ,Retrospective Studies ,Brugada syndrome ,business.industry ,Incidence ,Deep learning ,Middle Aged ,Right bundle branch block ,medicine.disease ,Feature (computer vision) ,Cohort ,Cardiology ,Female ,Artificial intelligence ,Cardiology and Cardiovascular Medicine ,business ,Follow-Up Studies - Abstract
Background Brugada syndrome is a major cause of sudden cardiac death in young people with a distinctive electrocardiogram (ECG) feature. We aimed to develop a deep learning-enabled ECG model for automatic screening Brugada syndrome to identify these patients at an early time, thus allowing for life-saving therapy. Methods A total of 276 ECGs with a type 1 Brugada ECG pattern (276 type 1 Brugada ECGs and another randomly retrieved 276 non-Brugada type ECGs for one to one allocation) were extracted from the hospital-based ECG database for a two-stage analysis with a deep learning model. After trained network for identifying right bundle branch block pattern, we transferred the first-stage learning to the second task to diagnose the type 1 Brugada ECG pattern. The diagnostic performance of the deep learning model was compared to that of board-certified practicing cardiologists. The model was further validated in the independent ECG dataset, collected from the hospitals in Taiwan and Japan. Results The diagnoses by the deep learning model (AUC: 0.96, sensitivity: 88.4%, specificity: 89.1%) were highly consistent with the standard diagnoses (Kappa coefficient: 0.78). However, the diagnoses by the cardiologists were significantly different from the standard diagnoses, with only moderate consistency (Kappa coefficient: 0.63). In the independent ECG cohort, the deep learning model still reached a satisfactory diagnostic performance (AUC 0.89, sensitivity: 86.0%, specificity: 90.0%). Conclusions We presented the first deep learning-enabled ECG model for diagnosing Brugada syndrome, which appears to be a robust screening tool with a diagnostic potential rivaling trained physicians.
- Published
- 2022