Wearable ECG Quality Assessment: A Deep Learning and Ambulatory Context-Awareness Approach

2026-09-24

AI Summary

This study addresses the challenge of automatic signal quality assessment for ambulatory electrocardiogram (ECG) recordings, which are highly susceptible to noise interference. Leveraging the CACHET-CADB database, this work proposes a deep learning model that integrates physical and patient-reported contextual data to enable automated ambulatory ECG signal quality evaluation. The primary contribution lies in introducing context-aware techniques into ambulatory ECG modeling for the first time, thereby extending existing signal quality assessment paradigms. The cross-domain robustness of the proposed model is validated on the MIT-BIH and PhysioNet/Computing in Cardiology Challenge 2021 datasets. Experimental results demonstrate its effectiveness in resolving complex noise patterns, offering a reliable solution for wearable ECG monitoring applications.

Abstract

This paper presents and evaluates a Deep Learning-based (DL-based) Signal Quality Assessment (SQA) model to distinguish between clean and noisy ambulatory Electrocardiograms (ECG). The model is trained on Copenhagen Center for Health Technology-Contextualized Arrhythmia Database (CACHET-CADB), which, to the best of our knowledge, is the first ambulatory ECG database with both physical and patient-reported contextual data. The model shows stable performance on different databases such as MIT-databases and the latest PyhsioNet/Cinc Challenge 2021 databases. Subsequently, the paper demonstrates how complicated ECG noise can be investigated by the SQA model and the physical contextual data.

Problem

• Wearable ECG
• Signal Quality Assessment
• Ambulatory ECG
• Noise Detection

Innovation

• Deep Learning
• Signal Quality Assessment
• Ambulatory ECG
• Context-Awareness
• Wearable