Single Nucleotide Polymorphism relevance learning with Random Forests for Type 2 diabetes risk prediction

作者：

Highlights：

• Type 2 diabetes (T2D) prognosis using Random Forests (RF) on 677-subject database.

• T2D prognosis using Single Nucleotide Polymorphisms (SNPs).

• Detection of SNP and SNP value relevance using RF.

• Prognosis comparison on RF with linear regression and Support Vector Machines.

摘要

•Type 2 diabetes (T2D) prognosis using Random Forests (RF) on 677-subject database.•T2D prognosis using Single Nucleotide Polymorphisms (SNPs).•Detection of SNP and SNP value relevance using RF.•Prognosis comparison on RF with linear regression and Support Vector Machines.

论文关键词：Type 2 diabetes,Random Forest,Feature learning,Predictive model,Gini importance

论文评审过程：Received 10 February 2017, Revised 4 September 2017, Available online 22 September 2017, Version of Record 16 March 2018.

论文官网地址：https://doi.org/10.1016/j.artmed.2017.09.005