Using interpretability approaches to update “black-box” clinical prediction models: an external validation study in nephrology

作者：

Highlights：

• There is a dearth of external validation studies, i.e., in a different setting, in clinical predictive modeling.

• Machine learning-based prediction models are especially prone to not generalize well in validation studies.

• The use of interpretability methods helps to shed light on model performance in external validation.

• Using knowledge distilled from interpretability methods helps to perform model update for simpler, potentially more generalizable models.

摘要

•There is a dearth of external validation studies, i.e., in a different setting, in clinical predictive modeling.•Machine learning-based prediction models are especially prone to not generalize well in validation studies.•The use of interpretability methods helps to shed light on model performance in external validation.•Using knowledge distilled from interpretability methods helps to perform model update for simpler, potentially more generalizable models.

论文关键词：Clinical predictive modeling,Nephrology,Validation,Interpretability methods

论文评审过程：Received 20 January 2020, Revised 9 September 2020, Accepted 25 October 2020, Available online 7 November 2020, Version of Record 16 December 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101982