Research in disease diagnosis is a challenging task due to inconsistent, class imbalance, conflicting and high dimensionality nature of medical data sets. The excellent features of each such data set play an important role in improving performance of classifiers that may follow either iterative or non-iterative approach. In the present study, a comparative study is carried out to show the performance of iterative and non-iterative classifiers in combination with genetic algorithm (GA) based feature selection approach over some widely used medical data sets. The experiment assists to identify the clinical data sets for which feature reduction is necessary for improving performance of classifiers. For iterative approaches, two popular classifiers namely C4.5 and RIPPER are chosen, whereas -NN and Naïve Bayes are taken as non-iterative learners. In total, 14 real world medical domain data sets are selected from the University of California, Irvine (UCI repository) for conducting experiments over the learners. From experiments using GA-based feature selection or its absence, it is observed that the naive Bayes provides the best results on most datasets; however, it shows comparatively better performance when features are filtered out.
AzarATEI-MetwallySM. Decision tree classifiers for automated medical diagnosis. Neural Computing and Applications2013; 23(7-8): 2387-2403.
2.
BlakeCKoeghEMertzCJ. Repository of machine learning. University of California at Irvine, 1999. URL: http://www.mlearn.ics.uci.edu/MLRepository.html.
3.
BurroniMCoronaRDell’EvaGSeraFBonoRPudduPPerottiRNobileFAndreassiLRubegniP. Melanoma computer-aided diagnosis reliability and feasibility Study. Clinical Cancer Research2004; 10(6): 1881-1886.
4.
BhanuBLeeSMingJ. Adaptive image segmentation using a genetic algorithm. IEEE Transactions on Systems, Man and Cybernetics1995; 25(12): 1543-1567.
5.
BonchiFGiannottiFMancoGRensoCNanniMPedreschiDRuggieriS. Data mining for intelligent web caching. Proceeding of International Conference on Information Technology: Coding and Computing, IEEE, 2001; 599-603.
6.
BremermannHJRogsonMSalaffS. Global properties of evolution processes. Natural Automata and Useful Simulations1966; 3-41.
7.
BrownDE. Introduction to data mining for medical informatics: Clinics in laboratory medicine. Clinical Data Mining and Warehousing2008; 28: 9-35.
8.
ChenHTanC. Prediction of type-2 diabetes based on several element levels in blood and chemometrics. Biological Trace Element Research2012; 147(1-3): 67-74.
9.
ChenYLiZNieLHuXWangXChuaTSZhangX. A semi-supervised bayesian network model for microblog topic classification. In Coling2012; 561-576.
10.
ChenMZhengAXLloydJJordanMIBrewerE. Failure diagnosis using decision trees. Proceedings of International Conference in Autonomic Computing, IEEE, 2004; 36-43.
11.
CohenWW. Fast effective rule induction. Proceedings of Twelfth International Conference on Machine Learning, Lake Tahoe, California, 1995.
12.
DeekshatuluBLChandraP. Classification of heart disease using k-nearest neighbor and genetic algorithm. Procedia Technology2013; 10: 85-94.
13.
DumaMTwalaBMarwalaT. Improving the performance of the ripper in insurance risk classification: A Comparative Study using feature selection. Proceedings of 8th International Conference on Informatics in Control, Automation and Robotics, Netherland 2011; 1: 203-210.
14.
EmmanouilidisCHunterAMaclntyreJCoxC. Multiple-criteria genetic algorithms for feature selection in neuro-fuzzy modeling. International Joint Conference on Neural Networks (IJCNN’99), IEEE1999; 6: 4387-4392.
15.
EstevezPACaballeroRE. A niching genetic algorithm for selecting features for neural classifiers. Proceedings of 8th International Conference on Artificial Neural Networks (ICANN, 98), Springer London, 1998; 311-316.
16.
FurnkranzJWidmerG. Incremental reduced error pruning. Proceedings of the 11th International Conference on Machine Learning (ML-94)1994; 70-77.
17.
GargAXAdhikariNKMcDonaldHRosas-ArellanoMPDevereauxPJBeyeneJSamJHaynesRB. Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: A systematic review. JAMA2005; 293(10): 1223-1238.
18.
Garcıa-LaencinaPJSancho-GomezJLFigueiras-VidalAR. Pattern classification with missing data: A review. Neural Computing & Applications2010; 19(2): 263-282.
19.
GoldbergDE. Genetic algorithms in search, optimization, and machine learning. Addison-Wesley Professional, Reading, Massachusetts, US, 1989.
20.
GonzalezJPOzgunerU. Lane detection using histogram-based segmentation and decision trees. Proceedings of Intelligent Transportation Systems, IEEE2000; 346-351.
21.
GrossDPZhangJSteenstraIBarnsleySHawsCAmellTMcIntoshGCooperJZaianeO. Development of a computer-based clinical decision support tool for selecting appropriate rehabilitation interventions for injured workers. Journal of Occupational Rehabilitation2013; 23(4): 597-609.
22.
HallMA. Correlation-based feature selection for discrete and numeric class machine learning. In Proceedings of Seventeenth International Conference on Machine Learning2000; 359-366.
23.
HickeySJ. Naive Bayes classification of public health data with greedy feature selection. Communications of the IIMA2013; 13(2): 87-97.
24.
HollandJH. Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence. University of Michigan Press, 1975.
25.
KazmierskaJMalickiJ. Application of the Naïve Bayesian classifier to optimize treatment decisions. Radiotherapy and Oncology2008; 86(2): 211-216.
26.
KahramanliHAllahverdiN. Design of a hybrid system for diabetes and heart diseases. Expert Systems with Applications2008; 35(1): 82-89.
27.
KalaiselviCNasiraGM. A new approach for the diagnosis of diabetes and prediction of cancer using ANFIS. World Congress on Computing and Communication Technologies, (WCCCT), IEEE2014; 188-190.
28.
KarlikBOztoprakE. Personalized cancer treatment by using Naïve Bayes Classifier. International Journal of Machine Learning and Computing2012; 2(3): 339-344.
29.
KawamotoKHoulihanCABalasEALobachDF. Improving clinical practice using clinical decision support systems: A systematic review of trials to identify features critical to success. Bmj (Clinical Research Ed.)2005; 330(7494): 765.
30.
LeeCSWangMH. A fuzzy expert system for diabetes decision support application. IEEE Transactions on Systems, Man and Cybernetics2011; 41(1): 139-153.
31.
LiuXLuRMaJChenLQinB. Privacy-preserving patient centric clinical decision support system on naïve Bayesian classification. IEEE Journal of Biomedical and Health Informatics2016; 20(2): 655-668.
32.
MatsuiKSuganamiYKosugiY. Feature selection by genetic algorithm for MRI segmentation. Systems and Computers in Japan1999; 30(7): 69-78.
33.
MacArthurSDBrodleyCEKakACBroderickLS. Interactive content-based image retrieval using relevance feedback. Computer Vision and Image Understanding2002; 88(2): 55-75.
34.
MaulikU. Medical image segmentation using genetic algorithms. IEEE Transactions on Information Technology in BioMedicine2009; 13(2): 166-173.
35.
MurakamiYMizuguchiK. Applying the Naïve Bayes classifier with kernel density estimation to the prediction of protein-protein interaction sites. Bioinformatics2009; 26(15): 1841-1848.
36.
OteroFEFreitasAAJohnsonCG. A new sequential covering strategy for inducing classification rules with ant colony algorithms. IEEE transactions on Evolutionary Computation2013; 17(1): 64-76.
37.
PanWLinJLeCT. A mixture model approach to detecting differentially expressed genes with microarray data. Functional and Integrative Genomics2003; 3(3): 117-124.
38.
ParedesRVidalE. A class-dependent weighted dissimilarity measure for nearest neighbor classification problems. Pattern Recognition Letters2000; 21(12): 1027-1036.
39.
ParkIKLeeKMLeeSU. Perceptual grouping of 3D features in aerial image using decision tree classifier. International Conference on Image Processing, IEEE1999; 1: 31-35.
40.
QuinlanJR. Introduction of decision trees. Machine Learning1986; 1(1): 81-106.
41.
RajavigneshRTholkappiaAGVidivelliS. Agent based decision support system using improved k-NN classifier for effective diagnosis of heart disease. Australian Journal of Basic & Applied Sciences2014; 8(17): 160.
42.
TanwaniAKFarooqM. The role of biomedical dataset in classification. In Conference on Artificial Intelligence in Medicine in Europe, Springer, Berlin, Heidelberg2009; 370-374.
43.
SeeraMLimCP. A hybrid intelligent system for medical data classification. Expert Systems with Applications2014; 41(5): 2239-2249.
44.
SeeratBQamarU. Rule induction using enhanced RIPPER algorithm for clinical decision support system. Sixth International Conference on Intelligent Control and Information Processing, IEEE, 2015; 83-91.
45.
SelvakuberanKKayathiriDHariniBDeviMI. An efficient feature selection method for classification in Health care Systems using Machine Learning Techniques. Third International Conference on Electronics Computer Technology (ICECT) IEEE, 2011; 4: 223-226.
46.
SarkarBKSanaSSChaudhuriKS. Selecting informative rules with parallel genetic algorithm in classification problem. Applied Mathematics and Computation2011; 218(7): 3247-3264.
StasisACLoukisENPavlopoulosSAKoutsourisD. Using decision tree algorithms as a basis for a heart sound diagnosis decision support system. Proceedings of the 4th Annual IEEE Conference on Information Technology Applications in Biomedicine, 2003; 354-357.
49.
QuinlanJR. C4.5: Programming for Machine Learning. Morgan Kaufmann, 1992; 38.
50.
De JongKASpearsWM. Using genetic algorithms to solve NP-complete problems. Proceedings of the Third International Conference on Genetic Algorithms, Morgan Kaufmarm, 1989; 124-132.
51.
JohnGHKohaviRPflegerK. Irrelevant features and the subset selection problem. In Proceedings of ML-94, Morgan Kaufmann, 1994; 121-129.
52.
NaghibiTHoffmannSPfisterB. Convex approximation of the NP-hard search problem in feature subset selection. International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE, 2013; 3273-3277.
