Research Article
Sudden Cardiac Arrest Detection Using Deep Learning and Principal Component Analysis
@INPROCEEDINGS{10.1007/978-3-031-47359-3_16, author={Van-Su Pham and Hang Duy Thi Nguyen and Hai-Chau Le and Minh Tuan Nguyen}, title={Sudden Cardiac Arrest Detection Using Deep Learning and Principal Component Analysis}, proceedings={Industrial Networks and Intelligent Systems. 9th EAI International Conference, INISCOM 2023, Ho Chi Minh City, Vietnam, August 2-3, 2023, Proceedings}, proceedings_a={INISCOM}, year={2023}, month={10}, keywords={Sudden cardiac arrest (SCA) Principal component analysis (PCA) Deep learning (DL) Automated External Defibrillators (AED) Electrocardiogram (ECG)}, doi={10.1007/978-3-031-47359-3_16} }- Van-Su Pham
Hang Duy Thi Nguyen
Hai-Chau Le
Minh Tuan Nguyen
Year: 2023
Sudden Cardiac Arrest Detection Using Deep Learning and Principal Component Analysis
INISCOM
Springer
DOI: 10.1007/978-3-031-47359-3_16
Abstract
Sudden cardiac arrest (SCA) is mainly caused by ventricular fibrillation and ventricular tachycardia, which are known as shockable rhythms and can be effectively treated with automated external defibrillators (AED). In this study, we propose a novel algorithm with high performance for detecting SCA on electrocardiogram (ECG) signals for use in the shock advice algorithm (SAA) applied in the AED. The algorithm utilizes a combination of principal component analysis (PCA) and convolutional neural network (CNN) model, using 5-fold cross-validation (CV). The PCA algorithm transforms 20 features extracted from ECG signals into 20 component features in different spaces where they are uncorrelated. Our proposed SAA algorithm achieves an accuracy of 99.0 %, a sensitivity of 94.7%, a specificity of 99.4%, and a balanced error rate of 2.9%.
