Minimal ensemble based on subset selection using ECG to diagnose categories of CAN

Jemal Abawajy; Andrei Kelarev; Xun Yi; Herbert F Jelinek

doi:10.1016/j.cmpb.2018.01.019

Minimal ensemble based on subset selection using ECG to diagnose categories of CAN

Comput Methods Programs Biomed. 2018 Jul:160:85-94. doi: 10.1016/j.cmpb.2018.01.019. Epub 2018 Mar 1.

Authors

Jemal Abawajy¹, Andrei Kelarev², Xun Yi³, Herbert F Jelinek⁴

Affiliations

¹ School of Information Technology, Deakin University, 221 Burwood Hwy, Victoria 3125, Australia. Electronic address: jemal.abawajy@deakin.edu.au.
² School of Information Technology, Deakin University, 221 Burwood Hwy, Victoria 3125, Australia; School of Science, RMIT University, GPO Box 2476, Melbourne, VIC 3001, Australia. Electronic address: andrei.kelare@gmail.com.
³ School of Science, RMIT University, GPO Box 2476, Melbourne, VIC 3001, Australia. Electronic address: xun.yi@rmit.edu.au.
⁴ School of Community Health, Charles Sturt University, PO Box 789, Albury, NSW 2640, Australia. Electronic address: hjelinek@csu.edu.au.

PMID: 29728250
DOI: 10.1016/j.cmpb.2018.01.019

Abstract

Background and objective: Early diagnosis of cardiac autonomic neuropathy (CAN) is critical for reversing or decreasing its progression and prevent complications. Diagnostic accuracy or precision is one of the core requirements of CAN detection. As the standard Ewing battery tests suffer from a number of shortcomings, research in automating and improving the early detection of CAN has recently received serious attention in identifying additional clinical variables and designing advanced ensembles of classifiers to improve the accuracy or precision of CAN diagnostics. Although large ensembles are commonly proposed for the automated diagnosis of CAN, large ensembles are characterized by slow processing speed and computational complexity. This paper applies ECG features and proposes a new ensemble-based approach for diagnosis of CAN progression.

Methods: We introduce a Minimal Ensemble Based On Subset Selection (MEBOSS) for the diagnosis of all categories of CAN including early, definite and atypical CAN. MEBOSS is based on a novel multi-tier architecture applying classifier subset selection as well as the training subset selection during several steps of its operation. Our experiments determined the diagnostic accuracy or precision obtained in 5 × 2 cross-validation for various options employed in MEBOSS and other classification systems.

Results: The experiments demonstrate the operation of the MEBOSS procedure invoking the most effective classifiers available in the open source software environment SageMath. The results of our experiments show that for the large DiabHealth database of CAN related parameters MEBOSS outperformed other classification systems available in SageMath and achieved 94% to 97% precision in 5 × 2 cross-validation correctly distinguishing any two CAN categories to a maximum of five categorizations including control, early, definite, severe and atypical CAN.

Conclusions: These results show that MEBOSS architecture is effective and can be recommended for practical implementations in systems for the diagnosis of CAN progression.

Keywords: Automated diagnosis; Cardiac autonomic neuropathy; Cross validation; Diabetes complications; Ensemble classifiers; Multi-tier system.

Publication types

Validation Study

MeSH terms

Algorithms*
Arrhythmias, Cardiac / diagnosis
Autonomic Nervous System Diseases / classification*
Autonomic Nervous System Diseases / diagnosis*
Diabetic Neuropathies / classification*
Diabetic Neuropathies / diagnosis*
Diagnosis, Computer-Assisted / methods*
Diagnosis, Computer-Assisted / statistics & numerical data
Electrocardiography / statistics & numerical data*
Heart Diseases / classification*
Heart Diseases / diagnosis*
Humans
Support Vector Machine