Towards Continuous Skin Sympathetic Nerve Activity Monitoring: Removing Muscle Noise

TL;DR

This paper presents a deep learning method using CNNs to detect and remove muscle noise from non-invasive skin sympathetic nerve activity recordings, improving accuracy for real-world applications.

Contribution

It introduces a CNN-based approach to effectively identify and eliminate muscle noise artifacts in SKNA data, enhancing non-invasive sympathetic nervous system monitoring.

Findings

CNN achieved 89.85% accuracy in classifying noise and signals

Muscle noise significantly interferes within the 500-1000 Hz frequency band

Addressing muscle noise improves SKNA monitoring accuracy

Abstract

Continuous monitoring of non-invasive skin sympathetic nerve activity (SKNA) holds promise for understanding the sympathetic nervous system (SNS) dynamics in various physiological and pathological conditions. However, muscle noise artifacts present a challenge in accurate SKNA analysis, particularly in real-life scenarios. This study proposes a deep convolutional neural network (CNN) approach to detect and remove muscle noise from SKNA recordings obtained via ECG electrodes. Twelve healthy participants underwent controlled experimental protocols involving cognitive stress induction and voluntary muscle movements, while collecting SKNA data. Power spectral analysis revealed significant muscle noise interference within the SKNA frequency band (500-1000 Hz). A 2D CNN model was trained on the spectrograms of the data segments to classify them into baseline, stress-induced SKNA, and muscle noise-contaminated periods, achieving an average accuracy of 89.85% across all subjects. Our findings underscore the importance of addressing muscle noise for accurate SKNA monitoring, advancing towards wearable SKNA sensors for real-world applications.