Interpretable risk models for Sleep Apnea and Coronary diseases from structured and non-structured data

作者：

Highlights：

• Novel method for risk prediction of diseases with accurate and explainable prediction.

• Embedding and weak supervision method to extract knowledge from EHR unstructured data

• Empirical evidence that the join of EHR unstructured data improves the risk model.

摘要

•Novel method for risk prediction of diseases with accurate and explainable prediction.•Embedding and weak supervision method to extract knowledge from EHR unstructured data•Empirical evidence that the join of EHR unstructured data improves the risk model.

论文关键词：Coronary diseases,Sleep Apnea,Text embedding,Weak supervision,EHR data,SHAP

论文评审过程：Received 1 August 2021, Revised 10 January 2022, Accepted 19 March 2022, Available online 1 April 2022, Version of Record 5 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116955