A decision analytic approach to predicting quality of life for lung transplant recipients: A hybrid genetic algorithms-based methodology

Asil Oztekin, Lina Al-Ebbini, Zulal Sevkli, Dursun Delen

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Feature selection, a critical pre-processing step for data mining, is aimed at determining representative variables/predictors from a large and feature-rich dataset for development of an effective prediction model. The purpose of this paper is to develop a hybrid methodology for feature selection using genetic algorithms to identify such representative features (input variables) and thereby to ensure the development of the best possible analytic model to predict and explain the target variable, quality of life (QoL), for patients undergoing a lung transplant overseen by the United Network for Organ Sharing (UNOS). The evaluation of three classification models, GA-kNN, GA-SVM, and GA-ANN, demonstrated that performance of the lung transplantation process has significantly improved via the GA-SVM approach, although the other two models have also yielded considerably high prediction accuracies. This study is unique in that it proposes a hybrid GA-based feature selection methodology along with design and development of several highly accurate classification algorithms to identify the most important features in the large and feature rich UNOS transplant dataset for lung transplantation.

Original languageEnglish
Pages (from-to)639-651
Number of pages13
JournalEuropean Journal of Operational Research
Volume266
Issue number2
DOIs
StatePublished - 16 Apr 2018
Externally publishedYes

Fingerprint

Transplants
Hybrid Genetic Algorithm
Quality of Life
Lung
Genetic algorithms
Feature extraction
Methodology
Feature Selection
Transplantation
Transplantation (surgical)
Sharing
Data mining
Classification Algorithm
Prediction Model
Preprocessing
Predictors
Data Mining
Gas
Quality of life
Hybrid genetic algorithm

Keywords

  • Feature selection
  • Genetic algorithms
  • OR in medicine
  • Quality of life
  • UNOS lung allocation

Cite this

@article{8d5dc421e45146ed9f90b3d0da0e6e24,
title = "A decision analytic approach to predicting quality of life for lung transplant recipients: A hybrid genetic algorithms-based methodology",
abstract = "Feature selection, a critical pre-processing step for data mining, is aimed at determining representative variables/predictors from a large and feature-rich dataset for development of an effective prediction model. The purpose of this paper is to develop a hybrid methodology for feature selection using genetic algorithms to identify such representative features (input variables) and thereby to ensure the development of the best possible analytic model to predict and explain the target variable, quality of life (QoL), for patients undergoing a lung transplant overseen by the United Network for Organ Sharing (UNOS). The evaluation of three classification models, GA-kNN, GA-SVM, and GA-ANN, demonstrated that performance of the lung transplantation process has significantly improved via the GA-SVM approach, although the other two models have also yielded considerably high prediction accuracies. This study is unique in that it proposes a hybrid GA-based feature selection methodology along with design and development of several highly accurate classification algorithms to identify the most important features in the large and feature rich UNOS transplant dataset for lung transplantation.",
keywords = "Feature selection, Genetic algorithms, OR in medicine, Quality of life, UNOS lung allocation",
author = "Asil Oztekin and Lina Al-Ebbini and Zulal Sevkli and Dursun Delen",
year = "2018",
month = "4",
day = "16",
doi = "10.1016/j.ejor.2017.09.034",
language = "English",
volume = "266",
pages = "639--651",
journal = "European Journal of Operational Research",
issn = "0377-2217",
publisher = "Elsevier",
number = "2",

}

A decision analytic approach to predicting quality of life for lung transplant recipients : A hybrid genetic algorithms-based methodology. / Oztekin, Asil; Al-Ebbini, Lina; Sevkli, Zulal; Delen, Dursun.

In: European Journal of Operational Research, Vol. 266, No. 2, 16.04.2018, p. 639-651.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A decision analytic approach to predicting quality of life for lung transplant recipients

T2 - A hybrid genetic algorithms-based methodology

AU - Oztekin, Asil

AU - Al-Ebbini, Lina

AU - Sevkli, Zulal

AU - Delen, Dursun

PY - 2018/4/16

Y1 - 2018/4/16

N2 - Feature selection, a critical pre-processing step for data mining, is aimed at determining representative variables/predictors from a large and feature-rich dataset for development of an effective prediction model. The purpose of this paper is to develop a hybrid methodology for feature selection using genetic algorithms to identify such representative features (input variables) and thereby to ensure the development of the best possible analytic model to predict and explain the target variable, quality of life (QoL), for patients undergoing a lung transplant overseen by the United Network for Organ Sharing (UNOS). The evaluation of three classification models, GA-kNN, GA-SVM, and GA-ANN, demonstrated that performance of the lung transplantation process has significantly improved via the GA-SVM approach, although the other two models have also yielded considerably high prediction accuracies. This study is unique in that it proposes a hybrid GA-based feature selection methodology along with design and development of several highly accurate classification algorithms to identify the most important features in the large and feature rich UNOS transplant dataset for lung transplantation.

AB - Feature selection, a critical pre-processing step for data mining, is aimed at determining representative variables/predictors from a large and feature-rich dataset for development of an effective prediction model. The purpose of this paper is to develop a hybrid methodology for feature selection using genetic algorithms to identify such representative features (input variables) and thereby to ensure the development of the best possible analytic model to predict and explain the target variable, quality of life (QoL), for patients undergoing a lung transplant overseen by the United Network for Organ Sharing (UNOS). The evaluation of three classification models, GA-kNN, GA-SVM, and GA-ANN, demonstrated that performance of the lung transplantation process has significantly improved via the GA-SVM approach, although the other two models have also yielded considerably high prediction accuracies. This study is unique in that it proposes a hybrid GA-based feature selection methodology along with design and development of several highly accurate classification algorithms to identify the most important features in the large and feature rich UNOS transplant dataset for lung transplantation.

KW - Feature selection

KW - Genetic algorithms

KW - OR in medicine

KW - Quality of life

KW - UNOS lung allocation

UR - http://www.scopus.com/inward/record.url?scp=85032949841&partnerID=8YFLogxK

U2 - 10.1016/j.ejor.2017.09.034

DO - 10.1016/j.ejor.2017.09.034

M3 - Article

AN - SCOPUS:85032949841

VL - 266

SP - 639

EP - 651

JO - European Journal of Operational Research

JF - European Journal of Operational Research

SN - 0377-2217

IS - 2

ER -