Robust heartbeat detection using multimodal recordings and ECG quality assessment with signal amplitudes dispersion

TL;DR

This paper presents a robust method for heartbeat detection that combines ECG quality assessment with multimodal signal analysis, improving noise discrimination and beat detection accuracy.

Contribution

It introduces a novel approach using amplitude dispersion and signal compatibility to enhance ECG heartbeat detection amidst noise and integrates multimodal data fusion strategies.

Findings

Effective noise segmentation of ECG signals.

Improved heartbeat detection accuracy.

Enhanced robustness with multimodal data fusion.

Abstract

Method: In this study, a new method is introduced for distinguishing noise-free segments of ECG from noisy segments that use sample amplitude dispersion with an adoptive threshold for variance of samples amplitude and a method which uses compatibility of detected beats in ECG and some of the other signals which are related to the heart activity such as BP, arterial pressure (ART) and pulmonary artery pressure (PAP). A prioritization is applied in other pulsatile signals based on the amplitude and clarity of the peaks on them, and a fusion strategy is employed for segments on which ECG is noisy and other available signals in the data, which contain peaks corresponding to R peak of the ECG, are scored in three steps scoring function.