Open AccessMCMC impute missing values and Bayesian variable selection for logistic regression model to predict Pima Indian Diabetes
Author(s) -
Gongli Li,
Yueze Liu,
Han Li,
Ruikuan Yao,
Chenyang Li
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1865/4/042087
Subject(s) - logistic regression , frequentist inference , feature selection , missing data , bayesian probability , markov chain monte carlo , diabetes mellitus , statistics , model selection , computer science , econometrics , artificial intelligence , bayesian inference , machine learning , medicine , mathematics , endocrinology
Diabetes mellitus is a metabolic disease that causes high blood sugar. The risk factor of diabetes can be reduced significantly by early precise prediction. Lots of literatures published for diabetes prediction, but nearly all of them proposed frequentist Machine learning algorithm to classify and build models. Besides, their data pre-processing methods are not professional. In this literature, we are proposing MCMC filling missing values and Bayesian variable selection for logistic regression model to classify diabetes patients. It shows great performance (AUC = 0.884, sensitivity = 0.805, specificity = 0.875).