Robust Arrhythmia Classification Based on QRS Detection and a Compact 1D-CNN for Wearable ECG Devices

• Published in: IEEE journal of biomedical and health informatics 2022-12, Vol.26 (12), p.5918-5929
• Main Authors: Sabor, Nabil, Gendy, Garas, Mohammed, Hazem, Wang, Guoxing, Lian, Yong
• Format: Article
• Language: English
• Subjects: Algorithms; and wearable devices; Arrhythmia; Arrhythmias, Cardiac - diagnosis; Cardiac arrhythmia; Cardiovascular diseases; Classification; Classification algorithms; compact CNN; EKG; Electrocardiography; Electrocardiography - methods; Heart diseases; Humans; Microcontrollers; nonlinear energy operator; QRS Complexes; Robustness; Sensitivity; Signal Processing, Computer-Assisted; Wearable computers; Wearable Electronic Devices; Wearable technology
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2022.3207456

Embedded arrhythmia classification is the first step towards heart diseases prevention in wearable applications. In this paper, a robust arrhythmia classification algorithm, NEO-CCNN, for wearables that can be implemented on a simple microcontroller is proposed. The NEO-CCNN algorithm not only detects QRS complex but also accurately locates R-peak with the help of the proposed adaptive time-dependent thresholding technique, improving the accuracy and sensitivity in arrhythmia classification. An optimized compact 1D-CNN network (CCNN) with 9,701 parameters is used for classification. A QRS complex augmentation method is introduced in the training process to cater for R-peak location error (RLE). A nested k 1 k 2 -fold cross-validation method is utilized to evaluate the robustness of the proposed algorithm. Simulation results show that the proposed algorithm has the ability to detect more than 99.79% of R peaks with an RLE of 7.94 ms for the MIT-BIH database. Implemented on the STM32F407 microcontroller, NEO-CNN attains a classification accuracy of 97.83% and sensitivity of 96.46% using only 8s window size.