SORA

Advancing, promoting and sharing knowledge of health through excellence in teaching, clinical practice and research into the prevention and treatment of illness

Using multiple classifiers for predicting the risk of endovascular aortic aneurysm repair re-intervention through hybrid feature selection.

Attallah, O; Karthikesalingam, A; Holt, PJ; Thompson, MM; Sayers, R; Bown, MJ; Choke, EC; Ma, X (2017) Using multiple classifiers for predicting the risk of endovascular aortic aneurysm repair re-intervention through hybrid feature selection. Proc Inst Mech Eng H, 231 (11). pp. 1048-1063. ISSN 2041-3033 https://doi.org/10.1177/0954411917731592
SGUL Authors: Holt, Peter James Edward

[img]
Preview
PDF Accepted Version
Available under License ["licenses_description_publisher" not defined].

Download (961kB) | Preview

Abstract

Feature selection is essential in medical area; however, its process becomes complicated with the presence of censoring which is the unique character of survival analysis. Most survival feature selection methods are based on Cox's proportional hazard model, though machine learning classifiers are preferred. They are less employed in survival analysis due to censoring which prevents them from directly being used to survival data. Among the few work that employed machine learning classifiers, partial logistic artificial neural network with auto-relevance determination is a well-known method that deals with censoring and perform feature selection for survival data. However, it depends on data replication to handle censoring which leads to unbalanced and biased prediction results especially in highly censored data. Other methods cannot deal with high censoring. Therefore, in this article, a new hybrid feature selection method is proposed which presents a solution to high level censoring. It combines support vector machine, neural network, and K-nearest neighbor classifiers using simple majority voting and a new weighted majority voting method based on survival metric to construct a multiple classifier system. The new hybrid feature selection process uses multiple classifier system as a wrapper method and merges it with iterated feature ranking filter method to further reduce features. Two endovascular aortic repair datasets containing 91% censored patients collected from two centers were used to construct a multicenter study to evaluate the performance of the proposed approach. The results showed the proposed technique outperformed individual classifiers and variable selection methods based on Cox's model such as Akaike and Bayesian information criterions and least absolute shrinkage and selector operator in p values of the log-rank test, sensitivity, and concordance index. This indicates that the proposed classifier is more powerful in correctly predicting the risk of re-intervention enabling doctor in selecting patients' future follow-up plan.

Item Type: Article
Additional Information: Attallah, O; Karthikesalingam, A; Holt, PJ; Thompson, MM; Sayers, R; Bown, MJ; Choke, EC; Ma, X, Using multiple classifiers for predicting the risk of endovascular aortic aneurysm repair re-intervention through hybrid feature selection, Proc Inst Mech Eng H (Volume: 231 issue: 11) pp. 1048-1063. Copyright © 2017 (IMechE 2017). DOI: 10.1177/0954411917731592
Keywords: Cox’s proportional hazard model, Multiple classifier system, censoring, endovascular aortic repair, hybrid feature selection, survival analysis, Aortic Aneurysm, Endovascular Procedures, Humans, Kaplan-Meier Estimate, Neural Networks (Computer), Risk Assessment, Support Vector Machine, Humans, Aortic Aneurysm, Risk Assessment, Neural Networks (Computer), Kaplan-Meier Estimate, Endovascular Procedures, Support Vector Machine, Multiple classifier system, hybrid feature selection, survival analysis, censoring, Cox's proportional hazard model, endovascular aortic repair, Cox’s proportional hazard model, Multiple classifier system, censoring, endovascular aortic repair, hybrid feature selection, survival analysis, 0903 Biomedical Engineering, 0913 Mechanical Engineering
SGUL Research Institute / Research Centre: Academic Structure > Molecular and Clinical Sciences Research Institute (MCS)
Academic Structure > Molecular and Clinical Sciences Research Institute (MCS) > Vascular & Cardiac Surgery (INCCVC)
Journal or Publication Title: Proc Inst Mech Eng H
ISSN: 2041-3033
Language: eng
Dates:
DateEvent
November 2017Published
19 September 2017Published Online
22 August 2017Accepted
Projects:
Project IDFunderFunder ID
NIHR-CS-011-008Department of HealthUNSPECIFIED
PubMed ID: 28925817
Web of Science ID: WOS:000418182400005
Go to PubMed abstract
URI: http://openaccess.sgul.ac.uk/id/eprint/110597
Publisher's version: https://doi.org/10.1177/0954411917731592

Actions (login required)

Edit Item Edit Item