A novel SVM-ID3 Hybrid Feature Selection Method to Build a Disease Model for Melanoma using Integrated Genotyping and Phenotype Data from dbGaP

Son, Yesim AydinYucebas, Sait Can2025-01-272025-01-272014978-1-61499-432-9978-1-61499-431-20926-96301879-8365https://doi.org/10.3233/978-1-61499-432-9-501https://hdl.handle.net/20.500.12428/2330925th European Medical Informatics Conference (MIE) -- AUG 31-SEP 03, 2014 -- Istanbul, TURKEYThe relations between Single Nucleotide Polymorphism (SNP) and complex diseases are likely to be non-linear and require analysis of the high dimensional data. Previous studies in the field mostly focus on genotyping and effects of various phenotypes are not considered. To fill this gap a hybrid feature selection model of support vector machine and decision tree has been designed. The designed method is tested on melanoma. We were able to select phenotypic features such as moles and dysplastic nevi, and SNPs those maps to specific genes such as CAMK1D. The performance results of the proposed hybrid model, on melanoma dataset are 79.07% of sensitivity and 0.81 of area under ROC curve.eninfo:eu-repo/semantics/closedAccessGenome Wide Association Studies (GWAS)Single Nucleotide Polymorphism (SNP)Data MiningSupport Vector Machines (SVM)Decision TreesHybrid ModelsA novel SVM-ID3 Hybrid Feature Selection Method to Build a Disease Model for Melanoma using Integrated Genotyping and Phenotype Data from dbGaPConference Object20550150510.3233/978-1-61499-432-9-501N/AWOS:0004542261000992-s2.0-8492951839925160235Q3