ECG Signal Classification with Deep Learning for Heart Disease Identification

Wenbo Zhang; Limin Yu; Lishan Ye; Weifen Zhuang; Fei Ma

doi:10.1109/BDAI.2018.8546681

ECG Signal Classification with Deep Learning for Heart Disease Identification

Wenbo Zhang, Limin Yu, Lishan Ye, Weifen Zhuang, Fei Ma

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

32 Citations (Scopus)

Abstract

Electrocardiogram (ECG) signal is widely used in medical diagnosis of heart diseases. Automatic extraction of relevant and reliable information from ECG signals has not been an easy task for computerized system. This study proposes to use 12-layer 1-d CNN to classify 1 lead individual heartbeat signal into five classes of heart diseases. The proposed method was tested on MIT/BIH arrhythmia database and results were measured using positive predictive value, sensitivity and F1 score. Our proposed method obtained a positive predictive value of 0.977, sensitivity of 0.976, and F1 score of 0.976. Comparing with the results obtained by other four methods on the same database, our method was found superior on all three measures.

Original language	English
Title of host publication	International Conference on Big Data and Artificial Intelligence, BDAI 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	47-51
Number of pages	5
ISBN (Electronic)	9781538661369
DOIs	https://doi.org/10.1109/BDAI.2018.8546681
Publication status	Published - 26 Nov 2018
Event	2018 International Conference on Big Data and Artificial Intelligence, BDAI 2018 - Beijing, China Duration: 22 Jun 2018 → 24 Jun 2018

Publication series

Name	International Conference on Big Data and Artificial Intelligence, BDAI 2018

Conference

Conference	2018 International Conference on Big Data and Artificial Intelligence, BDAI 2018
Country/Territory	China
City	Beijing
Period	22/06/18 → 24/06/18

Keywords

1D Convolutional neural networks (CNNs)
ECG classification
Electrocardiogram
Heart diseases diagnosis

Access to Document

10.1109/BDAI.2018.8546681

Cite this

Zhang, W., Yu, L., Ye, L., Zhuang, W., & Ma, F. (2018). ECG Signal Classification with Deep Learning for Heart Disease Identification. In International Conference on Big Data and Artificial Intelligence, BDAI 2018 (pp. 47-51). Article 8546681 (International Conference on Big Data and Artificial Intelligence, BDAI 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BDAI.2018.8546681

@inproceedings{cefdabd42be54483a23dd1f0377e15da,

title = "ECG Signal Classification with Deep Learning for Heart Disease Identification",

abstract = "Electrocardiogram (ECG) signal is widely used in medical diagnosis of heart diseases. Automatic extraction of relevant and reliable information from ECG signals has not been an easy task for computerized system. This study proposes to use 12-layer 1-d CNN to classify 1 lead individual heartbeat signal into five classes of heart diseases. The proposed method was tested on MIT/BIH arrhythmia database and results were measured using positive predictive value, sensitivity and F1 score. Our proposed method obtained a positive predictive value of 0.977, sensitivity of 0.976, and F1 score of 0.976. Comparing with the results obtained by other four methods on the same database, our method was found superior on all three measures.",

keywords = "1D Convolutional neural networks (CNNs), ECG classification, Electrocardiogram, Heart diseases diagnosis",

author = "Wenbo Zhang and Limin Yu and Lishan Ye and Weifen Zhuang and Fei Ma",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 International Conference on Big Data and Artificial Intelligence, BDAI 2018 ; Conference date: 22-06-2018 Through 24-06-2018",

year = "2018",

month = nov,

day = "26",

doi = "10.1109/BDAI.2018.8546681",

language = "English",

series = "International Conference on Big Data and Artificial Intelligence, BDAI 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "47--51",

booktitle = "International Conference on Big Data and Artificial Intelligence, BDAI 2018",

}

Zhang, W, Yu, L, Ye, L, Zhuang, W & Ma, F 2018, ECG Signal Classification with Deep Learning for Heart Disease Identification. in International Conference on Big Data and Artificial Intelligence, BDAI 2018., 8546681, International Conference on Big Data and Artificial Intelligence, BDAI 2018, Institute of Electrical and Electronics Engineers Inc., pp. 47-51, 2018 International Conference on Big Data and Artificial Intelligence, BDAI 2018, Beijing, China, 22/06/18. https://doi.org/10.1109/BDAI.2018.8546681

ECG Signal Classification with Deep Learning for Heart Disease Identification. / Zhang, Wenbo; Yu, Limin; Ye, Lishan et al.
International Conference on Big Data and Artificial Intelligence, BDAI 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 47-51 8546681 (International Conference on Big Data and Artificial Intelligence, BDAI 2018).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - ECG Signal Classification with Deep Learning for Heart Disease Identification

AU - Zhang, Wenbo

AU - Yu, Limin

AU - Ye, Lishan

AU - Zhuang, Weifen

AU - Ma, Fei

PY - 2018/11/26

Y1 - 2018/11/26

N2 - Electrocardiogram (ECG) signal is widely used in medical diagnosis of heart diseases. Automatic extraction of relevant and reliable information from ECG signals has not been an easy task for computerized system. This study proposes to use 12-layer 1-d CNN to classify 1 lead individual heartbeat signal into five classes of heart diseases. The proposed method was tested on MIT/BIH arrhythmia database and results were measured using positive predictive value, sensitivity and F1 score. Our proposed method obtained a positive predictive value of 0.977, sensitivity of 0.976, and F1 score of 0.976. Comparing with the results obtained by other four methods on the same database, our method was found superior on all three measures.

AB - Electrocardiogram (ECG) signal is widely used in medical diagnosis of heart diseases. Automatic extraction of relevant and reliable information from ECG signals has not been an easy task for computerized system. This study proposes to use 12-layer 1-d CNN to classify 1 lead individual heartbeat signal into five classes of heart diseases. The proposed method was tested on MIT/BIH arrhythmia database and results were measured using positive predictive value, sensitivity and F1 score. Our proposed method obtained a positive predictive value of 0.977, sensitivity of 0.976, and F1 score of 0.976. Comparing with the results obtained by other four methods on the same database, our method was found superior on all three measures.

KW - 1D Convolutional neural networks (CNNs)

KW - ECG classification

KW - Electrocardiogram

KW - Heart diseases diagnosis

UR - http://www.scopus.com/inward/record.url?scp=85059945556&partnerID=8YFLogxK

U2 - 10.1109/BDAI.2018.8546681

DO - 10.1109/BDAI.2018.8546681

M3 - Conference Proceeding

AN - SCOPUS:85059945556

T3 - International Conference on Big Data and Artificial Intelligence, BDAI 2018

SP - 47

EP - 51

BT - International Conference on Big Data and Artificial Intelligence, BDAI 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 International Conference on Big Data and Artificial Intelligence, BDAI 2018

Y2 - 22 June 2018 through 24 June 2018

ER -

Zhang W, Yu L, Ye L, Zhuang W, Ma F. ECG Signal Classification with Deep Learning for Heart Disease Identification. In International Conference on Big Data and Artificial Intelligence, BDAI 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 47-51. 8546681. (International Conference on Big Data and Artificial Intelligence, BDAI 2018). doi: 10.1109/BDAI.2018.8546681

ECG Signal Classification with Deep Learning for Heart Disease Identification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this