Preliminary abnormal electrocardiogram segment screening method for Holter data based on long short-term memory networks

doi:10.1088/1674-1056/ab6d52

Abstract Holter usually monitors electrocardiogram (ECG) signals for more than 24 hours to capture short-lived cardiac abnormalities. In view of the large amount of Holter data and the fact that the normal part accounts for the majority, it is reasonable to design an algorithm that can automatically eliminate normal data segments as much as possible without missing any abnormal data segments, and then take the left segments to the doctors or the computer programs for further diagnosis. In this paper, we propose a preliminary abnormal segment screening method for Holter data. Based on long short-term memory (LSTM) networks, the prediction model is established and trained with the normal data of a monitored object. Then, on the basis of kernel density estimation, we learn the distribution law of prediction errors after applying the trained LSTM model to the regular data. Based on these, the preliminary abnormal ECG segment screening analysis is carried out without R wave detection. Experiments on the MIT-BIH arrhythmia database show that, under the condition of ensuring that no abnormal point is missed, 53.89% of normal segments can be effectively obviated. This work can greatly reduce the workload of subsequent further processing.

Keywords: electrocardiogram long short-term memory network kernel density estimation MIT-BIH arrhythmia database

Received: 23 December 2019
Revised: 13 January 2020
Accepted manuscript online:

PACS:	07.05.Mh	(Neural networks, fuzzy logic, artificial intelligence)
	02.50.Cw	(Probability theory)
	07.05.Kf	(Data analysis: algorithms and implementation; data management)

Corresponding Authors: Siying Chen, Hongxing Liu
E-mail: njhxliu@nju.edu.cn;siying_chen22@163.com,495777679@qq.com

Cite this article:

Siying Chen(陈偲颖), Hongxing Liu(刘红星) Preliminary abnormal electrocardiogram segment screening method for Holter data based on long short-term memory networks 2020 Chin. Phys. B 29 040701

[1]	de Albuquerque V H C, Nunes T M, Pereira D R, Luz E J D S, Menotti D, Papa J P and Tavares J M R 2018 Neural Comput. Appl. 29 679
[2]	Lin C C and Yang C M 2014 International Symposium on Computer, Consumer and Control (IS3C), June 10-12, 2014, Taichung, Taiwan, China, pp. 650-653
[3]	Ye C, Coimbra M T and Kumar B V K V 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, August 31-September 4, 2010, Buenos Aires, Argentina, p. 1918
[4]	Goldberger A L, Amaral L A N, Glass L, Hausdorff J M, Ivanov P C, Mark R G, Mietus J E, Moody G B, Peng C K and Stanley H E 2000 Circulation 101 e215
[5]	Acharya U R, Oh S L, Hagiwara Y, Tan J H, Adam M, Gertych A and Tan R S 2017 Comput. Biol. & Med. 89 389
[6]	Chuah M C and Fu F 2007 Frontiers of High Performance Computing and Networking ISPA, 2007 Workshops, August 28-September 1, 2007, Niagara Falls, Canada, pp. 123-135
[7]	Acharya U R, Fujita H, Lih O S, Hagiwara Y, Tan J H and Adam M 2017 Inf. Sci. 405 81
[8]	Chauhan S and Vig L 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA), October 9-21, 2015, Paris, France, p. 1
[9]	Hochreiter S and Schmidhuber J 1997 Neural Comput. 9 1735
[10]	Krizhevsky A, Sutskever I and Hinton G E 2012 Proceedings of the 25th International Conference on Neu ral Information Processing Systems, December 3-6, 2012, Lake Tahoe, Nevada, p. 1097
[11]	Hinton G E, Srivastava N, Krizhevsky A, Sutskever I and Salakhutdinov R R 2012 arXiv preprint arXiv:1207.0580.
[12]	Srivastava N, Hinton G, Krizhevsky A, Sutskever I and Salakhutdinov R 2014 J. Mach. Learn. Res. 15 1929
[13]	Khosrow D 1986 Technometrics 29 495
[14]	EC57 A A 1998 ANSI/AAMI EC57: 2012 Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms
[15]	Singh B N and Tiwari 2006 Digital Signal Process. 16 275
[16]	Nair V and Hinton G E 2010 Proceedings of the 27th international conference on machine learning, June 21-24, 2010, Haifa, Israel, pp. 807-814

[1]	Traffic flow prediction based on BILSTM model and data denoising scheme Zhong-Yu Li(李中昱), Hong-Xia Ge(葛红霞), and Rong-Jun Cheng(程荣军). Chin. Phys. B, 2022, 31(4): 040502.
[2]	Position difference regularity of corresponding R-wave peaks for maternal ECG components from different abdominal points Zhang Jie-Min (张洁敏), Guan Qun (管群), Tang Li-Ming (汤黎明), Liu Tie-Bing (刘铁兵), Liu Hong-Xing (刘红星), Huang Xiao-Lin (黄晓林), Si Jun-Feng (司峻峰). Chin. Phys. B, 2014, 23(1): 018701.
[3]	Multiscale entropy based study of the pathological time series Wang Jun (王俊), Ma Qian-Li (马千里). Chin. Phys. B, 2008, 17(12): 4424-4427.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Metrics
Related Articles

Preliminary abnormal electrocardiogram segment screening method for Holter data based on long short-term memory networks

Cite this article:

Online attention