Robustness of electrocardiogram signal quality indices. Issue 189 (13th April 2022)

• Record Type: Journal Article
• Authors: Rahman, Saifur; Karmakar, Chandan; Natgunanathan, Iynkaran; Yearwood, John; Palaniswami, Marimuthu
• Is Part Of: Journal of the Royal Society interface. Volume 19:Issue 189(2022)
• Publication Date: 2022-04-13
• Subjects: electrocardiogram -- signal quality indices -- SQA -- statistical signal quality indices -- threshold‌ -- cardiovascular diseases; Physical sciences -- Research -- Periodicals; Life sciences -- Research -- Periodicals; Interdisciplinary research -- Periodicals; 570.5
• DOI: 10.1098/rsif.2022.0012
• Languages: English
• ISSNs: 1742-5689

Abstract

Abstract : Electrocardiogram (ECG) signal quality indices (SQIs) are essential for improving diagnostic accuracy and reliability of ECG analysis systems. In various practical applications, the ECG signals are corrupted by different types of noise. These corrupted ECG signals often provide insufficient and incorrect information regarding a patient's health. To solve this problem, signal quality measurements should be made before an ECG signal is used for decision-making. This paper investigates the robustness of existing popular statistical signal quality indices (SSQIs): relative power of QRS complex (SQI p ), skewness (SQIskew ), signal-to-noise ratio (SQIsnr ), higher order statistics SQI (SQIhos ) and peakedness of kurtosis (SQIkur ). We analysed the robustness of these SSQIs against different window sizes across diverse datasets. Results showed that the performance of SSQIs considerably fluctuates against varying datasets, whereas the impact of varying window sizes was minimal. This fluctuation occurred due to the use of a static threshold value for classifying noise-free ECG signals from the raw ECG signals. Another drawback of these SSQIs is the bias towards noise-free ECG signals, that limits their usefulness in clinical settings. In summary, the fixed threshold-based SSQIs cannot be used as a robust noise detection system. In order to solve this fixed threshold problem, other techniques can be developed using adaptive thresholds and machine-learning mechanisms.