Improved cross sample entropy with error-metric based cardiac variability time series evaluation

Abstract

The cardiac rate variability analysis is a tool used to diagnose pathological and physiological variations in subjects in the premature stages. The cross-sample entropy (CSE) measure is used to analyze cardiac variability to diagnose cardiovascular diseases. In the proposed work, CSE is evaluated to detect arrhythmia subjects. It has been observed that CSE is restricted by a fixed threshold and any distance measure for cardiac disorder detection. In the proposed work, a new measure, named the error-metric cross sample entropy (E-metricCSE), is introduced to detect various cardiac disorders by using dynamic threshold and an error metric, root mean square error (RMSE). It signifies that the use of the RMSE makes the proposed algorithm most convenient for noise free data when compared to a distance metric. Different sets of MIX (Q) processes are executed on both real and simulated data to test the effectiveness of the proposed method. It is further noticed that the proposed algorithm is more consistent and more effective to quantify pathological and physiological subjects than the original CSE. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.