Tags

Type your tag names separated by a space and hit enter

[Heartbeat-based end-to-end classification of arrhythmias].
Nan Fang Yi Ke Da Xue Xue Bao 2019; 39(9):1071-1077NF

Abstract

OBJECTIVE

We propose a heartbeat-based end-to-end classification of arrhythmias to improve the classification performance for supraventricular ectopic beat (SVEB) and ventricular ectopic beat (VEB).

METHODS

The ECG signals were preprocessed by heartbeat segmentation and heartbeat alignment. An arrhythmia classifier was constructed based on convolutional neural network, and the proposed loss function was used to train the classifier.

RESULTS

The proposed algorithm was verified on MIT-BIH arrhythmia database. The AUC of the proposed loss function for SVEB and VEB reached 0.77 and 0.98, respectively. With the first 5 min segment as the local data, the diagnostic sensitivities for SVEB and VEB were 78.28% and 98.88%, respectively; when 0, 50, 100, and 150 samples were used as the local data, the diagnostic sensitivities for SVEB and VEB reached 82.25% and 93.23%, respectively.

CONCLUSIONS

The proposed method effectively reduces the negative impact of class-imbalance and improves the diagnostic sensitivities for SVEB and VEB, and thus provides a new solution for automatic arrhythmia classification.

Authors+Show Affiliations

School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China.School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China.

Pub Type(s)

Journal Article

Language

chi

PubMed ID

31640959

Citation

Deng, Li, and Rong Fu. "[Heartbeat-based End-to-end Classification of Arrhythmias]." Nan Fang Yi Ke Da Xue Xue Bao = Journal of Southern Medical University, vol. 39, no. 9, 2019, pp. 1071-1077.
Deng L, Fu R. [Heartbeat-based end-to-end classification of arrhythmias]. Nan Fang Yi Ke Da Xue Xue Bao. 2019;39(9):1071-1077.
Deng, L., & Fu, R. (2019). [Heartbeat-based end-to-end classification of arrhythmias]. Nan Fang Yi Ke Da Xue Xue Bao = Journal of Southern Medical University, 39(9), pp. 1071-1077. doi:10.12122/j.issn.1673-4254.2019.09.11.
Deng L, Fu R. [Heartbeat-based End-to-end Classification of Arrhythmias]. Nan Fang Yi Ke Da Xue Xue Bao. 2019 Sep 30;39(9):1071-1077. PubMed PMID: 31640959.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - [Heartbeat-based end-to-end classification of arrhythmias]. AU - Deng,Li, AU - Fu,Rong, PY - 2019/10/24/entrez PY - 2019/10/24/pubmed PY - 2019/11/12/medline KW - arrhythmia KW - classification KW - convolution neural network KW - deep learning SP - 1071 EP - 1077 JF - Nan fang yi ke da xue xue bao = Journal of Southern Medical University JO - Nan Fang Yi Ke Da Xue Xue Bao VL - 39 IS - 9 N2 - OBJECTIVE: We propose a heartbeat-based end-to-end classification of arrhythmias to improve the classification performance for supraventricular ectopic beat (SVEB) and ventricular ectopic beat (VEB). METHODS: The ECG signals were preprocessed by heartbeat segmentation and heartbeat alignment. An arrhythmia classifier was constructed based on convolutional neural network, and the proposed loss function was used to train the classifier. RESULTS: The proposed algorithm was verified on MIT-BIH arrhythmia database. The AUC of the proposed loss function for SVEB and VEB reached 0.77 and 0.98, respectively. With the first 5 min segment as the local data, the diagnostic sensitivities for SVEB and VEB were 78.28% and 98.88%, respectively; when 0, 50, 100, and 150 samples were used as the local data, the diagnostic sensitivities for SVEB and VEB reached 82.25% and 93.23%, respectively. CONCLUSIONS: The proposed method effectively reduces the negative impact of class-imbalance and improves the diagnostic sensitivities for SVEB and VEB, and thus provides a new solution for automatic arrhythmia classification. SN - 1673-4254 UR - https://www.unboundmedicine.com/medline/citation/31640959/[Heartbeat-based_end-to-end_classification_of_arrhythmias] L2 - https://medlineplus.gov/arrhythmia.html DB - PRIME DP - Unbound Medicine ER -