A novel SVM-ID3 Hybrid Feature Selection Method to Build a Disease Model for Melanoma using Integrated Genotyping and Phenotype Data from dbGaP
[ X ]
Tarih
2014
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Ios Press
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
The 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.
Açıklama
25th European Medical Informatics Conference (MIE) -- AUG 31-SEP 03, 2014 -- Istanbul, TURKEY
Anahtar Kelimeler
Genome Wide Association Studies (GWAS), Single Nucleotide Polymorphism (SNP), Data Mining, Support Vector Machines (SVM), Decision Trees, Hybrid Models
Kaynak
E-Health - For Continuity of Care
WoS Q Değeri
N/A
Scopus Q Değeri
Q3
Cilt
205
