Building interpretable predictive models for pediatric hospital readmission using Tree-Lasso logistic regression
作者：
Highlights：
• Integration of domain knowledge and learning algorithm led to increased interpretability of predictive models while predictive performance is not affected significantly.
• A quantitative analysis of interpretability is given based on information loss caused by dimensionality reduction.
• The method is evaluated and analysed for hospital readmission prediction for SID pediatric patient data in California.
• Interpretations of models comply with existing medical understanding of pediatric readmission.
摘要
•Integration of domain knowledge and learning algorithm led to increased interpretability of predictive models while predictive performance is not affected significantly.•A quantitative analysis of interpretability is given based on information loss caused by dimensionality reduction.•The method is evaluated and analysed for hospital readmission prediction for SID pediatric patient data in California.•Interpretations of models comply with existing medical understanding of pediatric readmission.
论文关键词：Lasso regression,Tree Lasso regression,Model interpretability,Hospital readmission prediction
论文评审过程：Received 6 November 2015, Revised 23 July 2016, Accepted 25 July 2016, Available online 29 July 2016, Version of Record 7 August 2016.
论文官网地址：https://doi.org/10.1016/j.artmed.2016.07.003
