Mixed-integer optimization approach to learning association rules for unplanned ICU transfer
作者：
Highlights：
• Early identifying unplanned transfer to intensive care unit from emergency department due to unexpected clinical deteriorations is formulated as a supervised learning problem.
• A new rule-based analytic method using optimization and data mining is developed.
• Significant association rules of key risk factors resulting in high-risk, unplanned transfers are formed.
• The developed method provides easy-to-interpret results beneficial for supporting clinical decisions.
摘要
•Early identifying unplanned transfer to intensive care unit from emergency department due to unexpected clinical deteriorations is formulated as a supervised learning problem.•A new rule-based analytic method using optimization and data mining is developed.•Significant association rules of key risk factors resulting in high-risk, unplanned transfers are formed.•The developed method provides easy-to-interpret results beneficial for supporting clinical decisions.
论文关键词：Emergency department,Critical care,Unplanned ICU transfer,Association rule,Mixed-integer optimization
论文评审过程：Received 20 March 2019, Revised 9 January 2020, Accepted 13 January 2020, Available online 30 January 2020, Version of Record 6 February 2020.
论文官网地址：https://doi.org/10.1016/j.artmed.2020.101806
