Early abnormal heartbeat multistage classification by using decision tree and K-nearest neighbor

Mohamad Sabri Bin Sinal, Eiji Kamioka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Heart diseases contribute to the highest cause of death around the world particularly for middle aged and elderly people. There are various types of heart disease symptoms. One of the most common types is Arrhythmia which is considered as a dangerous heart condition since the symptom itself may initiate more chronic heart diseases and result in death if it is not treated earlier. However, the detection of Arrhythmia by humans is regarded as a challenging task because the natures of the symptom appear at random times. Therefore, an automatic detection method of abnormal heartbeat in ECG (electrocardiogram) data is needed to overcome the issue. In this paper, a novel multistage classification approach using K-Nearest Neighbor and decision tree of the 3 segments in the ECG cycle is proposed to detect Arrhythmia heartbeat from the early minute of ECG data. Specific attributes based on feature extraction in each heartbeat are used to classify the Normal Sinus Rhythm and Arrhythmia. The experimental result shows that the proposed multistage classification approach is able to detect the Arrhythmia heartbeat with 90.6% accuracy for the P and the Q peak segments, 91.1% accuracy for the Q, R and S peak segments and lastly, 97.7% accuracy for the S and the T peak segments, outperforming the other data mining techniques.

Original languageEnglish
Title of host publicationAICCC 2018 - Proceedings of 2018 Artificial Intelligence and Cloud Computing Conference
PublisherAssociation for Computing Machinery
Pages29-34
Number of pages6
ISBN (Electronic)9781450366236
DOIs
Publication statusPublished - 2018 Dec 21
Event2018 International Conference on Artificial Intelligence and Cloud Computing, AICCC 2018 - Tokyo, Japan
Duration: 2018 Dec 212018 Dec 23

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2018 International Conference on Artificial Intelligence and Cloud Computing, AICCC 2018
CountryJapan
CityTokyo
Period18/12/2118/12/23

Fingerprint

Decision trees
Electrocardiography
Data mining
Feature extraction

Keywords

  • Computational Intelligence
  • Data Mining
  • Heart Disease
  • Heart Disease Classification
  • Heartbeat Classification
  • Machine Learning

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Bin Sinal, M. S., & Kamioka, E. (2018). Early abnormal heartbeat multistage classification by using decision tree and K-nearest neighbor. In AICCC 2018 - Proceedings of 2018 Artificial Intelligence and Cloud Computing Conference (pp. 29-34). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3299819.3299848

Early abnormal heartbeat multistage classification by using decision tree and K-nearest neighbor. / Bin Sinal, Mohamad Sabri; Kamioka, Eiji.

AICCC 2018 - Proceedings of 2018 Artificial Intelligence and Cloud Computing Conference. Association for Computing Machinery, 2018. p. 29-34 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bin Sinal, MS & Kamioka, E 2018, Early abnormal heartbeat multistage classification by using decision tree and K-nearest neighbor. in AICCC 2018 - Proceedings of 2018 Artificial Intelligence and Cloud Computing Conference. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 29-34, 2018 International Conference on Artificial Intelligence and Cloud Computing, AICCC 2018, Tokyo, Japan, 18/12/21. https://doi.org/10.1145/3299819.3299848
Bin Sinal MS, Kamioka E. Early abnormal heartbeat multistage classification by using decision tree and K-nearest neighbor. In AICCC 2018 - Proceedings of 2018 Artificial Intelligence and Cloud Computing Conference. Association for Computing Machinery. 2018. p. 29-34. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3299819.3299848
Bin Sinal, Mohamad Sabri ; Kamioka, Eiji. / Early abnormal heartbeat multistage classification by using decision tree and K-nearest neighbor. AICCC 2018 - Proceedings of 2018 Artificial Intelligence and Cloud Computing Conference. Association for Computing Machinery, 2018. pp. 29-34 (ACM International Conference Proceeding Series).
@inproceedings{aed115316daa4299bee7ba31dd87b1b6,
title = "Early abnormal heartbeat multistage classification by using decision tree and K-nearest neighbor",
abstract = "Heart diseases contribute to the highest cause of death around the world particularly for middle aged and elderly people. There are various types of heart disease symptoms. One of the most common types is Arrhythmia which is considered as a dangerous heart condition since the symptom itself may initiate more chronic heart diseases and result in death if it is not treated earlier. However, the detection of Arrhythmia by humans is regarded as a challenging task because the natures of the symptom appear at random times. Therefore, an automatic detection method of abnormal heartbeat in ECG (electrocardiogram) data is needed to overcome the issue. In this paper, a novel multistage classification approach using K-Nearest Neighbor and decision tree of the 3 segments in the ECG cycle is proposed to detect Arrhythmia heartbeat from the early minute of ECG data. Specific attributes based on feature extraction in each heartbeat are used to classify the Normal Sinus Rhythm and Arrhythmia. The experimental result shows that the proposed multistage classification approach is able to detect the Arrhythmia heartbeat with 90.6{\%} accuracy for the P and the Q peak segments, 91.1{\%} accuracy for the Q, R and S peak segments and lastly, 97.7{\%} accuracy for the S and the T peak segments, outperforming the other data mining techniques.",
keywords = "Computational Intelligence, Data Mining, Heart Disease, Heart Disease Classification, Heartbeat Classification, Machine Learning",
author = "{Bin Sinal}, {Mohamad Sabri} and Eiji Kamioka",
year = "2018",
month = "12",
day = "21",
doi = "10.1145/3299819.3299848",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "29--34",
booktitle = "AICCC 2018 - Proceedings of 2018 Artificial Intelligence and Cloud Computing Conference",

}

TY - GEN

T1 - Early abnormal heartbeat multistage classification by using decision tree and K-nearest neighbor

AU - Bin Sinal, Mohamad Sabri

AU - Kamioka, Eiji

PY - 2018/12/21

Y1 - 2018/12/21

N2 - Heart diseases contribute to the highest cause of death around the world particularly for middle aged and elderly people. There are various types of heart disease symptoms. One of the most common types is Arrhythmia which is considered as a dangerous heart condition since the symptom itself may initiate more chronic heart diseases and result in death if it is not treated earlier. However, the detection of Arrhythmia by humans is regarded as a challenging task because the natures of the symptom appear at random times. Therefore, an automatic detection method of abnormal heartbeat in ECG (electrocardiogram) data is needed to overcome the issue. In this paper, a novel multistage classification approach using K-Nearest Neighbor and decision tree of the 3 segments in the ECG cycle is proposed to detect Arrhythmia heartbeat from the early minute of ECG data. Specific attributes based on feature extraction in each heartbeat are used to classify the Normal Sinus Rhythm and Arrhythmia. The experimental result shows that the proposed multistage classification approach is able to detect the Arrhythmia heartbeat with 90.6% accuracy for the P and the Q peak segments, 91.1% accuracy for the Q, R and S peak segments and lastly, 97.7% accuracy for the S and the T peak segments, outperforming the other data mining techniques.

AB - Heart diseases contribute to the highest cause of death around the world particularly for middle aged and elderly people. There are various types of heart disease symptoms. One of the most common types is Arrhythmia which is considered as a dangerous heart condition since the symptom itself may initiate more chronic heart diseases and result in death if it is not treated earlier. However, the detection of Arrhythmia by humans is regarded as a challenging task because the natures of the symptom appear at random times. Therefore, an automatic detection method of abnormal heartbeat in ECG (electrocardiogram) data is needed to overcome the issue. In this paper, a novel multistage classification approach using K-Nearest Neighbor and decision tree of the 3 segments in the ECG cycle is proposed to detect Arrhythmia heartbeat from the early minute of ECG data. Specific attributes based on feature extraction in each heartbeat are used to classify the Normal Sinus Rhythm and Arrhythmia. The experimental result shows that the proposed multistage classification approach is able to detect the Arrhythmia heartbeat with 90.6% accuracy for the P and the Q peak segments, 91.1% accuracy for the Q, R and S peak segments and lastly, 97.7% accuracy for the S and the T peak segments, outperforming the other data mining techniques.

KW - Computational Intelligence

KW - Data Mining

KW - Heart Disease

KW - Heart Disease Classification

KW - Heartbeat Classification

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85063004798&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063004798&partnerID=8YFLogxK

U2 - 10.1145/3299819.3299848

DO - 10.1145/3299819.3299848

M3 - Conference contribution

AN - SCOPUS:85063004798

T3 - ACM International Conference Proceeding Series

SP - 29

EP - 34

BT - AICCC 2018 - Proceedings of 2018 Artificial Intelligence and Cloud Computing Conference

PB - Association for Computing Machinery

ER -