Key result
Time-domain features and optimized support vector machines achieve 100% accuracy for ECG arrhythmia classification.
Why the study?
Automatic classification of arrhythmias faces challenges from the substantial volume of clinical ECG data and distinguishing features, where the inclusion of irrelevant features can cause inaccurate classification results.
Does time-domain feature extraction combined with TLO and SVM improve the accuracy of ECG arrhythmia classification compared to other feature extraction techniques?
Does time-domain feature extraction combined with TLO and SVM improve the accuracy of ECG arrhythmia classification compared to other feature extraction techniques?
A machine learning model utilizing time-domain feature extraction and teaching learning-based optimization achieved perfect classification accuracy for various arrhythmias in a dataset of 185 ECG records.
May warrant further ML exploration in arrhythmia detection; leaves open prospective validation before any clinical use.
BACKGROUND: Automatic classification of arrhythmias based on electrocardiography (ECG) data faces several significant challenges, particularly due to the substantial volume of clinical data involved in ECG signal analysis. The volume of clinical data has increased considerably, especially with the emergence of new clinical symptoms and signs in various arrhythmia conditions. These symptoms and signs, which serve as distinguishing features, can number in the tens of thousands. However, the inclusion of irrelevant features can lead to inaccurate classification results. METHOD: To identify the most relevant and optimal features for ECG arrhythmia classification, common feature extraction techniques have been applied to ECG signals, specifically shallow and deep feature extraction. Additionally, a feature selection technique based on a metaheuristic optimization algorithm is utilized following the ECG feature extraction process. RESULTS: Our findings indicate that shallow feature extraction based on the time-domain analysis, combined with feature selection using a metaheuristic optimization algorithm, outperformed other ECG feature extraction and selection techniques. Among eight features of time-domain anaylsis, the selected feature is one to three features from RR-interval assesment, achieving 100% accuracy, sensitivity, specificity, and precision for ECG arrhythmia classification. CONCLUSION: The proposed end-to-end architecture for ECG arrhythmia classification demonstrates simplicity in parameters and low complexity, making it highly effective for practical applications.
No takes yet. Share an insight, caveat, or question.
Darmawahyuni et al. (2024) studied Arrhythmia (n=185). Time-domain feature extraction with teaching learning-based optimization (TLO) and support vector machines (SVM) vs. Other feature extraction and selection techniques (deep features, frequency-domain, time-frequency domain) was evaluated on Classification accuracy, sensitivity, specificity, and precision. Time-domain feature extraction combined with teaching learning-based optimization and support vector machines achieved 100% accuracy, sensitivity, specificity, and precision for ECG arrhythmia classification.