Using the optimal receiver operating characteristic curve to design a predictive genetic test, exemplified with type 2 diabetes

Abstract

Current extensive genetic research into common complex diseases, especially with the completion of genome-wide association studies, is bringing to light many novel genetic risk loci. These new discoveries, along with previously known genetic risk variants, offer an important opportunity for researchers to improve health care. We describe a method of quick evaluation of these new findings for potential clinical practice by designing a new predictive genetic test, estimating its classification accuracy, and determining the sample size required for the verification of this accuracy. The proposed predictive test is asymptotically more powerful than tests built on any other existing method and can be extended to scenarios where loci are linked or interact. We illustrate the approach for the case of type 2 diabetes. We incorporate recently discovered risk factors into the proposed test and find a potentially better predictive genetic test. The area under the receiver operating characteristic (ROC) curve (AUC) of the proposed test is estimated to be higher (AUC = 0.671) than for the existing test (AUC = 0.580).

Figure 1

ROC Curves for Type 2 Diabetes The three lines in the plot from bottom to top correspond to the ROC curves of three type 2 diabetes predictive tests: the rebuilt existing predictive genetic test based on three SNPs, the new predictive test combing the previously associated SNPs, four environmental factors, and four novel risk SNPs from the confirmatory stage of the genome-wide association study, and the improved new predictive test with five additional novel risk SNPs discovered in the second genome-wide association study of type 2 diabetes. The estimated AUC values of these three tests are 0.580, 0.657, and 0.671, respectively.