Dataset Information

Automatic Detection of Arrhythmia Based on Multi-Resolution Representation of ECG Signal.

ABSTRACT: Automatic detection of arrhythmia is of great significance for early prevention and diagnosis of cardiovascular disease. Traditional feature engineering methods based on expert knowledge lack multidimensional and multi-view information abstraction and data representation ability, so the traditional research on pattern recognition of arrhythmia detection cannot achieve satisfactory results. Recently, with the increase of deep learning technology, automatic feature extraction of ECG data based on deep neural networks has been widely discussed. In order to utilize the complementary strength between different schemes, in this paper, we propose an arrhythmia detection method based on the multi-resolution representation (MRR) of ECG signals. This method utilizes four different up to date deep neural networks as four channel models for ECG vector representations learning. The deep learning based representations, together with hand-crafted features of ECG, forms the MRR, which is the input of the downstream classification strategy. The experimental results of big ECG dataset multi-label classification confirm that the F1 score of the proposed method is 0.9238, which is 1.31%, 0.62%, 1.18% and 0.6% higher than that of each channel model. From the perspective of architecture, this proposed method is highly scalable and can be employed as an example for arrhythmia recognition.

SUBMITTER: Wang D

PROVIDER: S-EPMC7175329 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic Detection of Arrhythmia Based on Multi-Resolution Representation of ECG Signal.

Wang Dongqi D Meng Qinghua Q Chen Dongming D Zhang Hupo H Xu Lisheng L

Sensors (Basel, Switzerland) 20200312 6

Automatic detection of arrhythmia is of great significance for early prevention and diagnosis of cardiovascular disease. Traditional feature engineering methods based on expert knowledge lack multidimensional and multi-view information abstraction and data representation ability, so the traditional research on pattern recognition of arrhythmia detection cannot achieve satisfactory results. Recently, with the increase of deep learning technology, automatic feature extraction of ECG data based on ...[more]

PMID: 32178296

Similar Datasets

Project description:BackgroundCardiac arrhythmias in exercising horses are the focus of much interest, both in terms of what is considered normal and potential associations with poor performance and sudden cardiac death. One barrier to performing large-scale studies is the lack of an easily applicable device, to allow recording of large numbers of high-quality exercising electrocardiograms (ECGs). The EquimetreTM is a new wearable device which records a single lead ECG, amongst other parameters. Validation of such wearable devices is essential before further studies are undertaken.ObjectivesTo evaluate the quality of ECG using the EquimetreTM and compare arrhythmia detection during exercise with the reference TelevetTM system.Study designProspective blinded clinical study.MethodsSimultaneous ECGs were recorded with both systems in 49 healthy horses during exercise. High intensity exercise (>40km/h) was performed by 29 racehorses, and lower intensity exercise for the remainder of the racehorses and show jumpers. Tracings were excluded if >10% artefact was present (duration of artefact relative to duration of exercise). For included ECGs, the duration of artefact was recorded and compared. ECGs were evaluated using Kubios premium software. Arrhythmia detection (yes/no) and arrhythmia classification (sinus arrhythmia, narrow complex of similar morphology to the sinus complexes or wide complex with a different morphology) were compared using Cohen's Kappa coefficient.ResultsNine TelevetTM ECGs and 3 EquimetreTM ECGs were excluded due to artefact >10%. TelevetTM ECGs included significantly more artefact during exercise than EquimetreTM ECGs (5% vs. 0.25% p<0.001). Arrhythmia analysis was performed on 38 horses' paired ECGs. The Kappa coefficient was excellent for arrhythmia detection (K=0.97) and arrhythmia classification (K=0.93).Main limitationsRelatively low numbers of horses with arrhythmias (n=21) were included. The ECG recordings only provided one lead, making arrhythmia classification challenging in some cases.ConclusionsThe Equimetre device provides a reliable ECG for arrhythmia detection during exercise. This system may be useful clinically and for future large-scale investigations into the occurrence and significance of exercising arrhythmias.

Dataset Information

Automatic Detection of Arrhythmia Based on Multi-Resolution Representation of ECG Signal.

Publications

Automatic Detection of Arrhythmia Based on Multi-Resolution Representation of ECG Signal.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets