An efficient detection of congestive heart failure using frequency localized filter banks for the diagnosis with ECG signals

Congestive heart failure (CHF) refers to the condition in which the heart is unable to maintain the required blood flow under normal heart pressure. CHF is one of the major causes of death worldwide and is commonly caused by coronary artery disease, diabetes and high blood pressure. It typically affects the elderly population. The diagnosis of CHF is mostly based on clinical assessment of symptoms, signs, imaging findings, and invasive intracardiac pressure measurement. The electrocardiogram (ECG) is neither sensitive nor specific for diagnosis of CHF, and the analysis of the ECG signal for the possible presence of CHF is manually intensive and requires adequate skills and expertise for discerning subtle abnormalities in the electrical activity of the heart that may be associated with CHF. We hypothesized that this task of recognizing the multiparametric patterns of ECG signal aberrations that might occur in CHF could be expedited and optimized using machine learning. In this paper, we present an automated approach for the diagnosis of CHF using ECG signals. The proposed approach was tested on four different sets of normal and CHF ECG signals obtained from established public databases. The experiments were performed using short (2 second (s)) ECG segments. Five different features (fuzzy entropy, Renyi entropy, Higuchi's fractal dimension, Kraskov entropy and energy) were extracted from the wavelet decomposition of ECG segments using frequency localized filter banks. For training and classification, we employed quadratic support vector machine (QSVM). A 10-fold cross-validation technique was used for evaluation. Accuracy >= 99.66%, sensitivity >= 99.82%, and specificity >= 99.28%, were obtained across all four data sets used. The system can be deployed in hospitals to facilitate the diagnosis of CHF. The proposed system can reduce the time requirement and error rate associated with manual reading of large ECG signals. (C) 2018 Elsevier B.V. All rights reserved.