Machine Learning Approaches for Diabetes Risk Factor Detection

Abstract

Diabetes is a deficiency in the body's ability to convert glucose (sugar) to energy. Glucose is the main source of fuel for our body. When food is digested it is changed into fats, protein, or carbohydrates. Foods that affect blood sugars are called carbohydrates. The hypertriglyceridemic waist (HW) is strongly associated with type 2 diabetes Phenotype; however, to date, no study has assessed the predictive power of phenotypes based on individual triglyceride and anthropometric measurements. The aims of the study were to assess the association between the HW phenotype and type 2 diabetes in Korean adults and to evaluate the predictive power of dissimilar phenotypes consisting of combinations of individual anthropometric measurements and Triglyceride levels. Study measured fasting plasma glucose and TG levels and performed anthropometric measurements. We employed binary logistic regression (LR) to examine statistically significant differences between normal subjects and those with type 2 diabetes using Hypertriglyceridemic waist and individual anthropometric measurements. For more reliable prediction results, two machine learning algorithms, naive Bayes and LR, were used to evaluate the predictive power of various phenotypes.