An application of CART algorithms for detection of an association between VDR polymorphisms and reduced bone density in individuals with type 2 diabetes: a population-based cross-sectional study

Introduction: An important part of preventing major common diseases is identifying genetic factors that contribute to their occurrence. For the first time in our knowledge, we investigated association between five polymorphisms vitamin D receptor (VDR) gene (ApaI, BsmI, FokI, EcoRV, and TaqI) low bone density/osteopenia/osteoporosis individuals with type 2 diabetes using classification regression tree (CART) algorithms.
 Methods: Data from 158 participants T2D were used develop CART analysis. The binary output variable was "bone state" or normal values. Age BMI (continuous variables), deficiency (yes/no), gender (binary as well studied polymorphism VDR (categorical variables) all played a role explanatory model. A 5-fold cross-validation process for model validation.
 Results: Participants divided into three groups: men, women, both sexes. In groups, age factor predicting state final obtained second most significant predictor each sexes (accuracy:75.30% ± 2.80%, AUC: 0.740 0.064), EcoRV women (accuracy: 80.79% 6.58%, AUC:0.785 0.063), TaqI men 76.36% 3.05%, AUC:0.706 0.125).
 Conclusion: Model validation models demonstrated use algorithms could be an acceptable technique risk osteoporosis among T2D. Our recommendation conduct more population-based studies. We hope this study will serve basis future research.