Research Information System
Thesis Type: Doctorate
Institution Of The Thesis: Orta Doğu Teknik Üniversitesi, Graduate School of Informatics, Medical Informatics, Turkey
Approval Date: 2014
Student: HÜSAMETTİN GÜL
Supervisor: YEŞİM AYDIN SON
Abstract:Despite the rise in type 2 diabetes (T2D) prevalence worldwide, we do not have a method for early T2D risk prediction. Phenotype variables only contribute to risk prediction near the onset or after the development of T2D. The predictive ability of genetic models has been found to be little or negligible so far. T2D has mostly genetic background but the genetic loci identified so far account for only a small fraction (10%) of the overall heritable risk. In this study, we used data from The Nurses' Health Study and Health Professionals' Follow-up Study cohorts to develop a better and early risk prediction method for T2D by using binary logistic regression. Phenotypic variables yielded 70.7% overall correctness and an area under curve (AUC) of 0.77. With regard to genotype, 798 single nucleotide polymorphisms (SNPs) with P values lower than 1.0E-3, yielded 90.0% correctness and an AUC of 0.965. This is the highest score in literature, even including the scores obtained with phenotypic variables. The additive contributions of phenotype and genotype increased the overall correctness to 92.9%, and AUC to 0.980. Our results showed that the genotype could be used to obtain a higher score, which could enable early risk prediction. These findings present new possibilities for genome-wide association study (GWAS) analysis in terms of discovering missing heritability. Changes in diet and lifestyle due to early risk prediction using genotype could result in a healthier population. These results should be confirmed by follow-up studies.