Decision Tree–Based Modeling of Androgen Pathway Genes and Prostate Cancer Risk

Abstract

Inherited variability in genes that influence androgen metabolism has been associated with risk of prostate cancer. The objective of this analysis was to evaluate interactions for prostate cancer risk by using classification and regression tree (CART) models (i.e., decision trees), and to evaluate whether these interactive effects add information about prostate cancer risk prediction beyond that of "traditional" risk factors. We compared CART models with traditional logistic regression (LR) models for associations of factors with prostate cancer risk using 1,084 prostate cancer cases and 941 controls. All analyses were stratified by race. We used unconditional LR to complement and compare with the race-stratified CART results using the area under curve (AUC) for the receiver operating characteristic curves. The CART modeling of prostate cancer risk showed different interaction profiles by race. For European Americans, interactions among CYP3A43 genotype, history of benign prostate hypertrophy, family history of prostate cancer, and age at consent revealed a distinct hierarchy of gene-environment and gene-gene interactions, whereas for African Americans, interactions among family history of prostate cancer, individual proportion of European ancestry, number of GGC androgen receptor repeats, and CYP3A4/CYP3A5 haplotype revealed distinct interaction effects from those found in European Americans. For European Americans, the CART model had the highest AUC whereas for African Americans, the LR model with the CART discovered factors had the largest AUC. These results provide new insight into underlying prostate cancer biology for European Americans and African Americans.