Meta Learning Ensemble Technique for Diagnosis of Cardiac Autonomic Neuropathy Based on Heart Rate Variability Features

Ahmad Shaker Abdalrada; Jemal Abawajy; Morshed Chowdhury; Sutharshan Rajasegarar; Tahsien Al-Quraishi; Herbert Jelinek

Meta Learning Ensemble Technique for Diagnosis of Cardiac Autonomic Neuropathy Based on Heart Rate Variability Features

Ahmad Shaker Abdalrada, Jemal Abawajy, Morshed Chowdhury, Sutharshan Rajasegarar, Tahsien Al-Quraishi, Herbert Jelinek

Deakin University

Research output: Book chapter/Published conference paper › Conference paper › peer-review

5 Citations (Scopus)

Abstract

Heart Rate Variability (HRV) attributes form an important set of tests, usually collected for patients with different kinds of pathology such as diabetes, kidney disease and cardiovascular disease. The aim of this study was to examine the role of HRV attributes for improving the diagnosis of Cardiac Autonomic Neuropathy (CAN). We investigated the performance of various base classifiers for the most essential features for CAN combined with the HRV attributes. To get the optimal subset of features, we used a feature selection method based on mean decrease accuracy (MDA), which is implemented in the Random Forest classifier. Random Forest consistently outperformed all other base classifiers. A number of ensemble classifiers have also been investigated using Random Forest to enhance the diagnosis of CAN when Ewing battery tests were combined with HRV attributes. The results improved classification accuracy compared to existing classifiers with the best results obtained by AdaBoostM and MultBoost ensembles.

Original language	English
Title of host publication	Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017)
Editors	Gongzhu Hu, Takaaki Goto
Place of Publication	New York, USA
Publisher	International Society for Computers and Their Applications (ISCA)
Pages	169-176
Number of pages	7
ISBN (Print)	9781510847835
Publication status	Published - 2017
Event	30th International Conference on Computer Applications in Industry and Engineering: CAINE 2017 - Hilton San Diego/Harbor Island, San Diego, United States Duration: 02 Oct 2017 → 04 Oct 2017 http://www.caine-conf.org/2017/

Conference

Conference	30th International Conference on Computer Applications in Industry and Engineering
Country/Territory	United States
City	San Diego
Period	02/10/17 → 04/10/17
Internet address	http://www.caine-conf.org/2017/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

Abdalrada, A. S., Abawajy, J., Chowdhury, M., Rajasegarar, S., Al-Quraishi, T., & Jelinek, H. (2017). Meta Learning Ensemble Technique for Diagnosis of Cardiac Autonomic Neuropathy Based on Heart Rate Variability Features. In G. Hu, & T. Goto (Eds.), Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017) (pp. 169-176). International Society for Computers and Their Applications (ISCA).

Abdalrada, Ahmad Shaker ; Abawajy, Jemal ; Chowdhury, Morshed et al. / Meta Learning Ensemble Technique for Diagnosis of Cardiac Autonomic Neuropathy Based on Heart Rate Variability Features. Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017) . editor / Gongzhu Hu ; Takaaki Goto. New York, USA : International Society for Computers and Their Applications (ISCA), 2017. pp. 169-176

@inproceedings{c9515bbb189e4d38b6a72cd975c6ba05,

title = "Meta Learning Ensemble Technique for Diagnosis of Cardiac Autonomic Neuropathy Based on Heart Rate Variability Features",

abstract = "Heart Rate Variability (HRV) attributes form an important set of tests, usually collected for patients with different kinds of pathology such as diabetes, kidney disease and cardiovascular disease. The aim of this study was to examine the role of HRV attributes for improving the diagnosis of Cardiac Autonomic Neuropathy (CAN). We investigated the performance of various base classifiers for the most essential features for CAN combined with the HRV attributes. To get the optimal subset of features, we used a feature selection method based on mean decrease accuracy (MDA), which is implemented in the Random Forest classifier. Random Forest consistently outperformed all other base classifiers. A number of ensemble classifiers have also been investigated using Random Forest to enhance the diagnosis of CAN when Ewing battery tests were combined with HRV attributes. The results improved classification accuracy compared to existing classifiers with the best results obtained by AdaBoostM and MultBoost ensembles.",

keywords = "Heart rate variability, Cardiac autonomic neuropathy, Meta ensemble technique, Metaclassifiers",

author = "Abdalrada, {Ahmad Shaker} and Jemal Abawajy and Morshed Chowdhury and Sutharshan Rajasegarar and Tahsien Al-Quraishi and Herbert Jelinek",

year = "2017",

language = "English",

isbn = "9781510847835",

pages = "169--176",

editor = "Gongzhu Hu and Takaaki Goto",

booktitle = "Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017)",

publisher = "International Society for Computers and Their Applications (ISCA)",

address = "United States",

note = "30th International Conference on Computer Applications in Industry and Engineering : CAINE 2017 ; Conference date: 02-10-2017 Through 04-10-2017",

url = "http://www.caine-conf.org/2017/",

}

Abdalrada, AS, Abawajy, J, Chowdhury, M, Rajasegarar, S, Al-Quraishi, T & Jelinek, H 2017, Meta Learning Ensemble Technique for Diagnosis of Cardiac Autonomic Neuropathy Based on Heart Rate Variability Features. in G Hu & T Goto (eds), Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017) . International Society for Computers and Their Applications (ISCA), New York, USA, pp. 169-176, 30th International Conference on Computer Applications in Industry and Engineering, San Diego, California, United States, 02/10/17.

Meta Learning Ensemble Technique for Diagnosis of Cardiac Autonomic Neuropathy Based on Heart Rate Variability Features. / Abdalrada, Ahmad Shaker; Abawajy, Jemal; Chowdhury, Morshed et al.
Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017) . ed. / Gongzhu Hu; Takaaki Goto. New York, USA: International Society for Computers and Their Applications (ISCA), 2017. p. 169-176.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Meta Learning Ensemble Technique for Diagnosis of Cardiac Autonomic Neuropathy Based on Heart Rate Variability Features

AU - Abdalrada, Ahmad Shaker

AU - Abawajy, Jemal

AU - Chowdhury, Morshed

AU - Rajasegarar, Sutharshan

AU - Al-Quraishi, Tahsien

AU - Jelinek, Herbert

PY - 2017

Y1 - 2017

N2 - Heart Rate Variability (HRV) attributes form an important set of tests, usually collected for patients with different kinds of pathology such as diabetes, kidney disease and cardiovascular disease. The aim of this study was to examine the role of HRV attributes for improving the diagnosis of Cardiac Autonomic Neuropathy (CAN). We investigated the performance of various base classifiers for the most essential features for CAN combined with the HRV attributes. To get the optimal subset of features, we used a feature selection method based on mean decrease accuracy (MDA), which is implemented in the Random Forest classifier. Random Forest consistently outperformed all other base classifiers. A number of ensemble classifiers have also been investigated using Random Forest to enhance the diagnosis of CAN when Ewing battery tests were combined with HRV attributes. The results improved classification accuracy compared to existing classifiers with the best results obtained by AdaBoostM and MultBoost ensembles.

AB - Heart Rate Variability (HRV) attributes form an important set of tests, usually collected for patients with different kinds of pathology such as diabetes, kidney disease and cardiovascular disease. The aim of this study was to examine the role of HRV attributes for improving the diagnosis of Cardiac Autonomic Neuropathy (CAN). We investigated the performance of various base classifiers for the most essential features for CAN combined with the HRV attributes. To get the optimal subset of features, we used a feature selection method based on mean decrease accuracy (MDA), which is implemented in the Random Forest classifier. Random Forest consistently outperformed all other base classifiers. A number of ensemble classifiers have also been investigated using Random Forest to enhance the diagnosis of CAN when Ewing battery tests were combined with HRV attributes. The results improved classification accuracy compared to existing classifiers with the best results obtained by AdaBoostM and MultBoost ensembles.

KW - Heart rate variability

KW - Cardiac autonomic neuropathy

KW - Meta ensemble technique

KW - Metaclassifiers

UR - http://www.caine-conf.org/2017/wp-content/uploads/2017/09/CAINE2017-Program.pdf

UR - http://www.caine-conf.org/2017/

M3 - Conference paper

SN - 9781510847835

SP - 169

EP - 176

BT - Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017)

A2 - Hu, Gongzhu

A2 - Goto, Takaaki

PB - International Society for Computers and Their Applications (ISCA)

CY - New York, USA

T2 - 30th International Conference on Computer Applications in Industry and Engineering

Y2 - 2 October 2017 through 4 October 2017

ER -

Abdalrada AS, Abawajy J, Chowdhury M, Rajasegarar S, Al-Quraishi T, Jelinek H. Meta Learning Ensemble Technique for Diagnosis of Cardiac Autonomic Neuropathy Based on Heart Rate Variability Features. In Hu G, Goto T, editors, Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017) . New York, USA: International Society for Computers and Their Applications (ISCA). 2017. p. 169-176

Meta Learning Ensemble Technique for Diagnosis of Cardiac Autonomic Neuropathy Based on Heart Rate Variability Features

Abstract

Conference

UN SDGs

Other files and links

Fingerprint

Cite this