A new algorithm for wavelet-based heart rate variability analysis

TL;DR

This paper introduces a novel wavelet-based algorithm for HRV spectral analysis using MODWPT, implemented in the open-source RHRV toolkit, enabling better analysis of non-stationary heart rate signals.

Contribution

The paper presents the first implementation of wavelet-based spectral analysis in an HRV toolkit, improving non-stationary signal analysis with an optimized algorithm.

Findings

Algorithm accurately calculates spectral power in specified bands.

Implementation in RHRV makes wavelet analysis accessible for HRV researchers.

Optimized computation reduces processing time for wavelet-based HRV analysis.

Abstract

One of the most promising non-invasive markers of the activity of the autonomic nervous system is Heart Rate Variability (HRV). HRV analysis toolkits often provide spectral analysis techniques using the Fourier transform, which assumes that the heart rate series is stationary. To overcome this issue, the Short Time Fourier Transform is often used (STFT). However, the wavelet transform is thought to be a more suitable tool for analyzing non-stationary signals than the STFT. Given the lack of support for wavelet-based analysis in HRV toolkits, such analysis must be implemented by the researcher. This has made this technique underutilized. This paper presents a new algorithm to perform HRV power spectrum analysis based on the Maximal Overlap Discrete Wavelet Packet Transform (MODWPT). The algorithm calculates the power in any spectral band with a given tolerance for the band's boundaries. The MODWPT decomposition tree is pruned to avoid calculating unnecessary wavelet coefficients, thereby optimizing execution time. The center of energy shift correction is applied to achieve optimum alignment of the wavelet coefficients. This algorithm has been implemented in RHRV, an open-source package for HRV analysis. To the best of our knowledge, RHRV is the first HRV toolkit with support for wavelet-based spectral analysis.