SAR model for accurate detection of multi-label arrhythmias from electrocardiograms
Liuyang Yang,
Yaqing Zheng,
Zhimin Liu,
Rui Tang,
Libing Ma,
Yu Chen,
Ting Zhang,
Wei Li
Affiliations
Liuyang Yang
The Affiliated Hospital of Kunming University of Science and Technology. The First People's Hospital of Yunnan Province, Kunming, Yunnan, China; Department of Management Science and Information System, Faculty of Management and Economics, Kunming University of Science and Technology, Kunming, Yunnan, China; School of Population Medicine and Public Health, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
Yaqing Zheng
The Affiliated Hospital of Kunming University of Science and Technology. The First People's Hospital of Yunnan Province, Kunming, Yunnan, China
Zhimin Liu
The Third Affiliated Hospital of Kunming Medical University, Yunnan Cancer Hospital, Kunming, Yunnan,China
Rui Tang
Department of Management Science and Information System, Faculty of Management and Economics, Kunming University of Science and Technology, Kunming, Yunnan, China
Libing Ma
School of Population Medicine and Public Health, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Department of Respiratory and Critical Care Medicine, the Affiliated Hospital of Guilin Medical University, Guilin, Guangxi, China
Yu Chen
Department of Management Science and Information System, Faculty of Management and Economics, Kunming University of Science and Technology, Kunming, Yunnan, China
Ting Zhang
School of Population Medicine and Public Health, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; Corresponding author.
Wei Li
The Affiliated Hospital of Kunming University of Science and Technology. The First People's Hospital of Yunnan Province, Kunming, Yunnan, China; Corresponding author.
Objective: Arrhythmias are prevalent symptoms of cardiovascular disease, necessitating accurate and timely detection to mitigate associated risks. Detecting arrhythmias from ECGs quickly and accurately holds great significance in preventing heart disease and reducing mortality. This research endeavors to outperform previous studies by developing a scientific neural network model capable of training and predicting ECG signals for 11 categories of arrhythmias, accounting for up to 5 co-existing labels. Methods: In this study, we initially address the issue of imbalanced datasets by employing Borderline SMOTE and Cluster Centroids techniques during preprocessing. Subsequently, we propose a novel SAR model that combines attention and resnet mechanisms. The dataset is subjected to a 10-fold validation process to train and evaluate the model. Finally, several metrics such as HammingLoss, RankingLoss, F1-score, AUC and Coverage are used to evaluate the model. Results: By evaluating the results of the tests, the average Hamming Loss is 1.12 %, the average Ranking Loss is 1.17 %, the average Micro F1-score is 98.46 %, the average Micro AUC is 98.76 %, and the average Coverage is 3.2762. The results show that the SAR model outperforms previous related studies on the task of classifying arrhythmia signals with multiple categories and labels. Conclusion: The SAR model demonstrated excellent performance in accurately classifying multi-category and multi-label arrhythmia signals, affirming its scientific validity. Compared with previous studies, the model achieves a certain improvement in performance, which can help cardiologists to achieve scientific and accurate diagnosis of arrhythmia diseases.
