Classification of congestive heart failure with different New York Heart Association functional classes based on heart rate variability indices and machine learning

This study aims to evaluate the effect of heart rate variability (HRV) indices on the New York Heart Association (NYHA) classification of patients with congestive heart failure and to test the effectiveness of different machine learning algorithms. Twenty-nine long-term RR interval recordings from subjects (aged 34 to 79) with congestive heart failure (NYHA classes I, II, and III) in MIT-BIH Database were studied. We firstly removed the unreasonable RR intervals and segment the RR recordings with a 300-RR interval length window. Then the multiple HRV indexes were calculated for each RR segment. Support vector machine (SVM) and classification and regression tree (CART) methods were then separately used to distinguish patients with different NYHA classes based on the selected HRV indices. Receiver operating characteristic curve analysis was finally employed as the evaluation indicator to compare the performance of the two classifiers. The SVM classifier achieved accuracy, sensitivity, and specificity of 84.0%, 71.2%, and 83.4%, respectively, whereas the CART classifier achieved 81.4%, 66.5%, and 81.6%, respectively. The area under the curve of receiver operating characteristic for the two classifiers was 86.4% and 84.7%, respectively. It is possible for accurately classifying the NYHA functional classes I, II, and III when using the combination of HRV indices and machine learning algorithms. The SVM classifier performed better in classification than the CART classifier using the same HRV indices.