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

Xiaopeng Mao; Marike Weisbjerg; Sadasivan Puthusserypady · 2026

Paper

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.

Analysis

Paper intelligence

Summary

This paper presents a Deep Learning-based Signal Quality Assessment model for distinguishing clean from noisy ambulatory ECGs, utilizing contextual data for enhanced analysis.

Key findings

A DL-based SQA model effectively differentiates clean from noisy ambulatory ECGs.
The model exhibits consistent performance across diverse ECG databases.
Contextual data aids in understanding and investigating complex ECG noise.

Methods

Deep Learning-based Signal Quality Assessment (SQA) model
Training on CACHET-CADB database
Evaluation on MIT-databases and PhysioNet/CinC Challenge 2021 databases

Limitations

The study relies on a specific ambulatory ECG database (CACHET-CADB).
Performance may vary on databases not included in the evaluation.
The full capabilities of contextual data in noise investigation require further exploration.

Applications

Ambulatory ECG monitoring
Remote patient monitoring
Clinical decision support systems

Confidence95%

Source record

Publication metadata

Authors: Xiaopeng Mao; Marike Weisbjerg; Sadasivan Puthusserypady
Published: Sep 24, 2026
Paper type: preprint
Source: Arxiv

arXiv