A NOVEL HYBRID CLASSIFICATION METHOD WITH PARTICLE SWARM OPTIMIZATION AND K-NEAREST NEIGHBOR ALGORITHM FOR DIAGNOSIS OF CORONARY ARTERY DISEASE USING EXERCISE STRESS TEST DATA

Babaoglu, IsmailFindik, OguzUlker, ErkanAygul, Nazif2020-03-262020-03-2620121349-41981349-418Xhttps://hdl.handle.net/20.500.12395/27688The aim of this study is to investigate the effectiveness of a novel hybrid method, particle swarm optimization with k-nearest neighbor classifier (PSOkNN), on determination of coronary artery disease (CAD) existence upon exercise stress testing (EST) data. The PSOkNN method is composed of two steps. At the first step, one particle which demonstrates the whole samples optimally in training dataset is generated for both healthy and unhealthy patients. Then, at the second one, the class of the test sample is determined according to the distance of the test sample to the generated particles utilizing k-nearest neighbor algorithm. To demonstrate the effectiveness of this novel method, the results of PSOkNN are compared with the classification results of the artificial immune recognition system and k-nearest neighbor algorithm. Besides, reliability of the proposed method on determination of CAD existence upon EST data is examined by using classification accuracy, k-fold cross-validation method and Cohen's kappa coefficient.eninfo:eu-repo/semantics/closedAccessCoronary artery diseaseExercise stress testingParticle swarm optimizationArtificial immune recognition systemA NOVEL HYBRID CLASSIFICATION METHOD WITH PARTICLE SWARM OPTIMIZATION AND K-NEAREST NEIGHBOR ALGORITHM FOR DIAGNOSIS OF CORONARY ARTERY DISEASE USING EXERCISE STRESS TEST DATAArticle85B34673475Q3WOS:000305169200003N/A