What does this research mean for the field?

A deep compressed sensing framework that directly classifies adaptively compressed ECG signals without requiring complex reconstruction achieves over 98% accuracy at a 0.2 compression ratio, outperforming existing models. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

April 4, 2023PLoS ONEOpen Access

ECG signal classification in wearable devices based on compressed domain

View Full Paper

Ask AI

Bookmark

Why the study?

Wearable ECG monitoring generates large amounts of data affecting detection speed, and while deep compressed sensing optimizes this, signal reconstruction remains complex and expensive.

Structured PICO

Population

ECG signals from the MIT-BIH Arrhythmia Database and Ali Cloud Tianchi ECG signal Database

Intervention

Improved classification scheme for deep compressed sensing models (pre-processing, compression, and classification directly from compressed data)

Comparator

Other models

Outcome

Accuracy, Precision, Sensitivity, and F1-score of ECG signal classificationsurrogate

An improved deep compressed sensing model for wearable devices accurately classifies ECG signals directly from compressed data, achieving over 98% accuracy.

Implication

May support compressed ECG classification on wearables; leaves open prospective clinical validation.

Abstract

Wearable devices are often used to diagnose arrhythmia, but the electrocardiogram (ECG) monitoring process generates a large amount of data, which will affect the detection speed and accuracy. In order to solve this problem, many studies have applied deep compressed sensing (DCS) technology to ECG monitoring, which can under-sampling and reconstruct ECG signals, greatly optimizing the diagnosis process, but the reconstruction process is complex and expensive. In this paper, we propose an improved classification scheme for deep compressed sensing models. The framework is comprised of four modules: pre-processing; compression; and classification. Firstly, the normalized ECG signals are compressed adaptively in the three convolutional layers, and then the compressed data is directly put into the classification network to obtain the results of four kinds of ECG signals. We conducted our experiments on the MIT-BIH Arrhythmia Database and Ali Cloud Tianchi ECG signal Database to validate the robustness of our model, adopting Accuracy, Precision, Sensitivity and F1-score as the evaluation metrics. When the compression ratio (CR) is 0.2, our model has 98.16% accuracy, 98.28% average accuracy, 98.09% Sensitivity and 98.06% F1-score, all of which are better than other models.