Key result
Tiny matched filter-based CNN achieves ~98% accuracy for ECG classification with sub-millisecond inference.
Why the study?
Deploying machine learning algorithms for ECG monitoring at the edge addresses cloud-related availability and privacy concerns, but faces challenges from high computational demands and edge device constraints.
Does a tiny matched filter-based CNN classifier improve real-time ECG arrhythmia detection at the edge compared to state-of-the-art classifiers?
Does a tiny matched filter-based CNN classifier improve real-time ECG arrhythmia detection at the edge compared to state-of-the-art classifiers?
A novel, lightweight CNN classifier enables highly accurate, real-time ECG arrhythmia detection on resource-constrained edge devices.
Automated electrocardiogram (ECG) classification using machine learning (ML) is extensively utilized for arrhythmia detection. Contemporary ML algorithms are typically deployed on the cloud, which may not always meet the availability and privacy requirements of ECG monitoring. Edge inference is an emerging alternative that overcomes the concerns of cloud inference; however, it poses new challenges due to the demanding computational requirements of modern ML algorithms and the tight constraints of edge devices. In this work, we propose a tiny convolutional neural network (CNN) classifier for real-time monitoring of ECG at the edge with the aid of the matched filter (MF) theory. The MIT-BIH dataset with inter-patient division is used for model training and testing. The model generalization capability is validated on the INCART, QT, and PTB diagnostic databases, and the model performance in the presence of noise is experimentally analyzed. The proposed classifier can achieve average accuracy, sensitivity, and F1 scores of 98.18%, 91.90%, and 92.17%, respectively. The sensitivity of detecting supraventricular and ventricular ectopic beats (SVEB and VEB) is 85.3% and 96.34%, respectively. The model is 15 KB in size, with an average inference time of less than 1 ms. The proposed model achieves superior classification and real-time performance results compared to the state-of-the-art ECG classifiers while minimizing the model complexity. The proposed classifier can be readily deployed on a wide range of resource-constrained edge devices for arrhythmia monitoring, which can save millions of cardiovascular disease patients.
No takes yet. Share an insight, caveat, or question.
Mohammed M. Farag (2023) studied Arrhythmia. Tiny matched filter-based convolutional neural network (CNN) classifier vs. State-of-the-art ECG classifiers was evaluated on Average accuracy for ECG classification and arrhythmia detection. A tiny matched filter-based CNN classifier achieved an average accuracy of 98.18% and sensitivity of 91.90% for ECG classification, with a model size of 15 KB and inference time under 1 ms.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: