Predicting hospital associated disability from imbalanced data using supervised learning

作者:

Highlights:

• Hospitalization of elderly patients can lead to serious adverse effects on their functional capability.

• We study the outcome of hospitalization of elderly patients as a supervised learning task.

• We use a rich set of features characterizing the medical and social situation of elderly patient and show that the need for help and supervision are the most important features predicting whether these patients will return home.

• Our random forest model outperforms current models used to predict hospital associated disability.

• Our findings can help to improve hospitalization and rehabilitation of elderly patients.

摘要

•Hospitalization of elderly patients can lead to serious adverse effects on their functional capability.•We study the outcome of hospitalization of elderly patients as a supervised learning task.•We use a rich set of features characterizing the medical and social situation of elderly patient and show that the need for help and supervision are the most important features predicting whether these patients will return home.•Our random forest model outperforms current models used to predict hospital associated disability.•Our findings can help to improve hospitalization and rehabilitation of elderly patients.

论文关键词:Hospital associated disability,Machine learning,Random forest

论文评审过程:Received 16 May 2018, Revised 30 July 2018, Accepted 28 September 2018, Available online 3 October 2018, Version of Record 20 March 2019.

论文官网地址:https://doi.org/10.1016/j.artmed.2018.09.004