The Performance of Short-Term Heart Rate Variability in the Detection of Congestive Heart Failure

Abstract

Congestive heart failure (CHF) is a cardiac disease associated with the decreasing capacity of the cardiac output. It has been shown that the CHF is the main cause of the cardiac death around the world. Some works proposed to discriminate CHF subjects from healthy subjects using either electrocardiogram (ECG) or heart rate variability (HRV) from long-term recordings. In this work, we propose an alternative framework to discriminate CHF from healthy subjects by using HRV short-term intervals based on 256 RR continuous samples. Our framework uses a matching pursuit algorithm based on Gabor functions. From the selected Gabor functions, we derived a set of features that are inputted into a hybrid framework which uses a genetic algorithm and k-nearest neighbour classifier to select a subset of features that has the best classification performance. The performance of the framework is analyzed using both Fantasia and CHF database from Physionet archives which are, respectively, composed of 40 healthy volunteers and 29 subjects. From a set of nonstandard 16 features, the proposed framework reaches an overall accuracy of 100% with five features. Our results suggest that the application of hybrid frameworks whose classifier algorithms are based on genetic algorithms has outperformed well-known classifier methods.

Figure 1

Example. Heart rate variability (zero mean) and its joint time and frequency domain. Each “circle” (b and d) represents a Gabor function chosen by the MP algorithm. Normal sinus rhythm (a and b) and congestive heart failure signal (c and d). Both time-frequency planes are normalized to have the same energy levels (scale omitted for better visualization).

Figure 2

Energy decay ratio. The residual energy after each MP iteration for CHF (dash line) and NSR (solid line). Slow decays suggest that the decomposition was carried out by noncoherent structures (NSR) in opposition to coherent structures (CHF).

Figure 3

Example of the frequency distribution measurement pattern. Number of Gabor functions (distribution) organized by their center frequency (Hz). (a) Normal sinus rhythm. (b) Congestive heart failure.

Figure 4

System overview flowchart. Preprocessing stage (white boxes). Processing stage: matching pursuit decomposition and feature extraction (dark gray boxes), KNN/GA algorithm optimization (light gray boxes), and final classification results based on KNN classifier (black boxes).

Figure 5

Box plot of features computed for NSR and CHF heartbeat intervals. The central mark represents the median for 40 volunteers (NSR) and 29 subjects (CHF); the edges of the box are the 25th and 75th percentiles. While outliers are plotted individually (+), the whiskers are considered not outliers.