Insights from a machine learning model for predicting the hospital Length of Stay (LOS) at the time of admission

作者：

Highlights：

• A Cubist model for hospital Length of Stay (LOS) is proposed.

• The groups of cases covered by the Cubist rules differ in their characteristics.

• The LOS primarily depends on historical variables such as number of admissions.

• Applying CARMA algorithm allows discovery of important relations among variables.

• A method to separate the cases by their level of Cubist error.

摘要

•A Cubist model for hospital Length of Stay (LOS) is proposed.•The groups of cases covered by the Cubist rules differ in their characteristics.•The LOS primarily depends on historical variables such as number of admissions.•Applying CARMA algorithm allows discovery of important relations among variables.•A method to separate the cases by their level of Cubist error.

论文关键词：Cubist decision tree,Continuous association rule mining algorithm (CARMA),Support vector machine (SVM),Decision function,Error distribution,Length of Stay (LOS)

论文评审过程：Received 10 August 2016, Revised 22 January 2017, Accepted 12 February 2017, Available online 16 February 2017, Version of Record 25 February 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.02.023