Using Heart Rate Fragmentation and Heart Rate Asymmetry to Discriminate Congestive Heart

Heart Rate Asymmetry (HRA) quantifies the imbalance of heart rate acceleration and deceleration.Furthermore, Heart Rate Fragmentation (HRF) refers to a pattern of irregular heart rate variability characterized by frequent, short-lived accelerations or decelerations in heart rate while analyzing beat-to-beat intervals.This paper uses HRA and HRF features to distinguish Congestive Heart Failure (CHF) from Normal Sinus Rhythm (NSR).We have used 29 ECG recordings of subjects with CHF from the Physionet Congestive Heart Failure database and 54 ECG recordings of subjects in normal sinus rhythm from the Physionet Normal Sinus Rhythm database.Using 3000 RR intervals, three common HRA indexes and four HRF indexes were calculated.K-Nearest Neighbors (KNN) was trained on 70% of the data as a training set, and the accuracy was evaluated on 30% as a test set.The first case is when all seven extracted features are used in the classifier.Only four HRF parameters are considered in the second case, and in the third case, only three HRA parameters are included.The result shows that the extracted descriptors of the HRF are 100% accurate compared to the HRA, which obtained an accuracy of 81%.The results showed that although both HRF and HRA have promising results in diagnosing CHF, the parameters extracted from HRF alone can obtain promising results.