Detection and Classification of Cardiac Arrhythmias by Machine Learning: a Systematic Review

Abstract

Machine learning (ML) techniques can perform as better as humans at key healthcare tasks. Recent advances make it possible to perform, using ML, automatic high-level feature extraction and classification of cardiac arrhythmia. In this work, we aimed through a systematic literature review to identify the principal methods, databases, and contributions of ML on cardiac arrhythmias classification. Electronic database including PubMed, Science Direct, IEEE, Scielo, Scopus, and Web of Science were searched, from 2014 to 2019, by combining the following keywords “ECG”, “heart signals”, “ar-rhythmia”, “classification” and “machine learning”. 28 studies were selected as eligible. Classifications classes ranged from 2 to 17, with prevalence of 2 classes (71.4% of the studies). The most frequent applied methods were Artificial Neural Network (13 articles), followed by Support Vector Machines and Mixed techniques (5 articles respectively). MIT-BIH Arrhythmia Database was used in 15 studies (54%), whereas 8 (28.5%) utilized their own data. The approach basis for evaluating the results is the confusion matrix, where up to 82% of the studies used accuracy, 67.8% precision, and 46% sensitivity/specificity. Classification of cardiac arrhythmias through ECG is of increasing interest from the research groups, and ML classification is showing rising levels of performance. It would benefit both patients and clinicians.