Automated Prediction of Sudden Cardiac Death Risk Using Kolmogorov Complexity and Recurrence Quantification Analysis Features Extracted from HRV Signals

Abstract

Sudden Cardiac Death (SCD) is an unexpected sudden death of a person followed by Ventricular Fibrillation (VF) or Ventricular Tachycardia (VT) which is usually diagnosed using Electrocardiogram (ECG). Prediction of developing SCD is important for expeditious treatment and thus reducing the mortality rate. In our previous paper, we have developed the Sudden Cardiac Death Index (SCDI) to predict the SCD four minutes prior to its onset using nonlinear features extracted from Discrete Wavelet Transform (DWT) coefficients using ECG signals. In this present paper, we are proposing an automated prediction of SCD using Recurrence Quantification Analysis (RQA) and Kolmogorov complexity parameters extracted from Heart Rate Variability (HRV) signals. The extracted features ranked using t-test are subjected to k-Nearest Neighbor (k-NN), Decision Tree (DT), Support Vector Machine (SVM) and Probabilistic Neural Network (PNN) classifiers for automated classification of normal and SCD classes for of 1min, 2min, 3min and 4 min before SCD durations. Our results show that, we are able to predict the SCD four minutes before its onset with an average accuracy of 86.8%, sensitivity of 80%, and specificity of 94.4% using k-NN classifier and average accuracy of 86.8%, sensitivity of 85%, specificity of 88.8% using PNN classifier. The performance of the proposed system can be improved further by adding more features and more robust classifiers.