Automated arrhythmia detection with homeomorphically irreducible tree technique using more than 10,000 individual subject ECG records

Abstract

Background and objective: Arrhythmia constitute a common clinical problem in cardiology. The diagnosis is often made using electrocardiographic (ECG) signals but manual ECG interpretation by experts is expensive and time-consuming. In this work, we developed and validated an arrhythmia classification model based on handcrafted features, which was more computationally efficient than traditional deep learning models. Material and method: The classification model comprised (i) a specific feature extraction function based on the homeomorphically irreducible tree (HIT) graph pattern, (ii) multi-level feature generation based on maximum absolute pooling, (iii) Chi2 feature selector, and (iv) standard support vector machine classifier. We trained and validated the model on a large dataset comprising 12-leads ECGs acquired from more than 10,000 subjects. Performance metrics were reported for seven- (Case 1) and four-class (Case 2) arrhythmia diagnosis. Results: High classification accuracy rates of 92.95% and 97.18% were attained for Case 1 and Case 2, respectively, that were comparable with those of deep learning on the same ECG dataset. Conclusion: The model achieved excellent classification results at low computational cost, which underscores the potential for real world application of the proposed HIT-based ECG classification model. (C) 2021 Elsevier Inc. All rights reserved.