Recursive Particle Swarm Optimization (RPSO) schemed Support Vector Machine (SVM) Implementation for Microarray Data Analysis on Chronic Kidney Disease (CKD)

9th Annual Basic Science International Conference 2019

自然科学（总论）

Rustam, Zuherman^1 ; Syarifah, Mas Andam^1 ; Siswantining, Titin^1

Departemen of Mathematics, Faculty of Mathematics and Natural Sciences (FMIPA), Universitas Indonesia, Depok

16424, Indonesia^1

关键词: Chronic kidney disease;    Haemodialysis;    Heart disease;    Microarray data;    Microarray data analysis;    Particle swarm optimization algorithm;    SVM-RFE;    Treatment costs;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/546/5/052077/pdf
DOI  :  10.1088/1757-899X/546/5/052077

学科分类：自然科学（综合）

来源: IOP

【 摘 要 】

Chronic Kidney Disease is the second chronical and catastrophic disease after heart disease in terms of treatment cost. This is because CKD symptoms occurs on final stages, that is fourth and fifth, in which it is too late for treatment. Therefore, final stage patient must receive continuous medication, such as haemodialysis. So early detection on a patient CKD is necessary to prevent patient to be chronic. Studies of gene genes are used to classify microarray data with global CKD decisions or not. So to get accurate results in this study using SVM-RFE with the addition of the Particle Swarm Optimization algorithm as a gene selector to be more optimal and it consideration of the fixed gene in its condition which is important information of the CKD gene itself. This research is then expected to be able to classify globally with CKD output or not CKD. As a result, for the CKD microarray data accuracy using RPSO schemed SVM highest than only using SVM-RFE.