Risk prediction of type II diabetes based on random forest model

Authors:
Publisher website
Google Scholar
Abstract
In recent years, type II diabetes has become a serious disease that threaten the health and mind of human. Efficient predictive modeling is required for medical researchers and practitioners. This study proposes a type II diabetes prediction model based on random forest which aims at analyzing some readily available indicators (age, weight, waist, hip, etc.) effects on diabetes and discovering some rules on given data. The method can significantly reduce the risk of disease through digging out a clear and understandable model for type II diabetes from a medical database. Random forest algorithm uses multiple decision trees to train the samples, and integrates weight of each tree to get the final results. The validation results at school of medicine, University of Virginia shows that the random forest algorithm can greatly reduce the problem of over-fitting of the single decision tree, and it can effectively predict the impact of these readily available indicators on the risk of diabetes. Additionally, we get a better prediction accuracy using random forest than using the naive Bayes algorithm, ID3 algorithm and AdaBoost algorithm.

This publication has 14 references indexed in Scilit: