Early temporal prediction of Type 2 Diabetes Risk Condition from a General Practitioner Electronic Health Record: A Multiple Instance Boosting Approach
作者：
Highlights：
• MIL-Boost is applied to predict insulin resistance worsening.
• MIL-Boost is applied to temporal EHR data stored by a general practitioner.
• MIL-Boost overcomes other competitors (Recall from 0.70 and up to 0.83).
• MIL-Boost identifies also non-conventional insulin resistance biomarkers.
• MIL-Boost may represent the main core of a clinical decision support system.
摘要
•MIL-Boost is applied to predict insulin resistance worsening.•MIL-Boost is applied to temporal EHR data stored by a general practitioner.•MIL-Boost overcomes other competitors (Recall from 0.70 and up to 0.83).•MIL-Boost identifies also non-conventional insulin resistance biomarkers.•MIL-Boost may represent the main core of a clinical decision support system.
论文关键词：Type 2 Diabetes,Machine Learning,Predictive Medicine,Temporal Analysis,Electronic Health Record,Clinical Decision Support System
论文评审过程：Received 29 July 2019, Revised 12 February 2020, Accepted 20 March 2020, Available online 6 May 2020, Version of Record 16 May 2020.
论文官网地址：https://doi.org/10.1016/j.artmed.2020.101847
