Abstract
Atrial Fibrillation (AF) is the most common type of cardiac arrhythmia. Early diagnosis of AF helps to improve therapy and prognosis. Machine Learning (ML) has been successfully applied to improve the effectiveness of Computer-Aided Diagnosis (CADx) systems for AF detection. Presenting an explanation for the decision made by an ML model is considerable from the cardiologists' point of view, which decreases the complexity of the ML model and can provide tangible information in their diagnosis. In this paper, a range of explanation techniques is applied to hand-crafted features based ML models for heart rhythm classification. We validate the impact of the techniques by applying feature selection and classification to the 2017 CinC/PhysioNet challenge dataset. The results show the effectiveness and efficiency of SHapley Additive exPlanations (SHAP) technique along with Random Forest (RF) for the classification of the Electrocardiogram (ECG) signals for AF detection with a mean F-score of 0.746 compared to 0.706 for a technique based on the same features based on a cascaded SVM approach. The study also highlights how this interpretable hand-crafted feature-based model can provide cardiologists with a more compact set of features and tangible information in their diagnosis.
Highlights
Atrial Fibrillation (AF) is the most common cardiac arrhythmia with an increased prevalence with aging (Chugh et al, 2014)
In a Computer-Aided Diagnosis (CADx) system for heart rhythm classification, features are extracted from an ECG signal and are a representation of the corresponding signal, which are fed into a Machine Learning (ML) model
We present a range of interpretability techniques applied to hand-crafted features based machine learning models for heart rhythm classification
Summary
Atrial Fibrillation (AF) is the most common cardiac arrhythmia with an increased prevalence with aging (Chugh et al, 2014). It can lead to the formation of clots, heart failure, and other heart-related abnormalities (Wolf et al, 1991), and is associated with a five-fold increased risk of stroke (Wolf et al, 1978). The Electrocardiogram (ECG) has been extensively investigated for the diagnosis of many cardiac diseases. In a Computer-Aided Diagnosis (CADx) system for heart rhythm classification, features are extracted from an ECG signal and are a (compact) representation of the corresponding signal, which are fed into a Machine Learning (ML) model. ML models automatically learn useful patterns from training data (including the extracted features from the ECG signals) for which the diagnosis is already known and aim at extracting knowledge into their structures and parameters. The development of automated AF detection has attracted an increased level of attention, since
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
