Cross-site transportability of an explainable artificial intelligence model for acute kidney injury prediction.

Cross-site transportability of an explainable artificial intelligence model for acute kidney injury prediction.
复制标题

DOI:
10.1038/s41467-020-19551-w
复制
发表时间:
2020-11-09
影响因子:
16.6
通讯作者:
Liu M
Liu M
中科院分区:
综合性期刊1区
文献类型:
--
作者:
Song X;Yu ASL;Kellum JA;Waitman LR;Matheny ME;Simpson SQ;Hu Y;Liu M

文献摘要

参考文献

被引文献

相似文献

人工智能 (AI) 在预测急性肾损伤 (AKI) 方面表现出了良好的前景,然而,这些模型的临床采用需要可解释性和可移植性。医院之间不可互操作的数据是模型可移植性的主要障碍。在这里,我们利用美国 PCORnet 平台开发 AKI 预测模型,并评估其在六个独立卫生系统中的可移植性。我们的工作表明,跨站点性能可能会恶化,并揭示了不同人群的风险因素的异质性是原因。因此,无论源医院训练的人工智能模型有多准确,目标医院能否采用它仍然是一个悬而未决的问题。为了填补研究空白​​,我们提出了一种预测人工智能模型可移植性的方法,可以加速医院外部人工智能模型的适应过程。人工智能 (AI) 在预测急性肾损伤 (AKI) 方面表现出了良好的前景,然而,这些模型的临床采用需要跨站点的可解释性和可移植性。在这里,作者开发了 AKI 预测模型以及模型在六个独立卫生系统中可移植性的衡量标准。
Artificial intelligence (AI) has demonstrated promise in predicting acute kidney injury (AKI), however, clinical adoption of these models requires interpretability and transportability. Non-interoperable data across hospitals is a major barrier to model transportability. Here, we leverage the US PCORnet platform to develop an AKI prediction model and assess its transportability across six independent health systems. Our work demonstrates that cross-site performance deterioration is likely and reveals heterogeneity of risk factors across populations to be the cause. Therefore, no matter how accurate an AI model is trained at the source hospital, whether it can be adopted at target hospitals is an unanswered question. To fill the research gap, we derive a method to predict the transportability of AI models which can accelerate the adaptation process of external AI models in hospitals. Artificial intelligence (AI) has demonstrated promise in predicting acutekidney injury (AKI), however, clinical adoption of these models requires interpretability and transportability across sites. Here, the authors develop an AKI prediction model and a measure for model transportability across six independent health systems.
DOI: 10.15265/iy-2017-018
发表时间: 2017-08-01
影响因子: --
作者:
Rosenbloom, S T;Carroll, R J;Denny, J C
通讯作者: Denny, J C
DOI: 10.2215/cjn.02430315
发表时间: 2015-10-01
影响因子: 9.8
作者:
Lin, Jennie;Fernandez, Hilda;Wilson, F. Perry
通讯作者: Wilson, F. Perry
DOI: 10.1136/bmjopen-2017-016591
发表时间: 2017-09-27
期刊: BMJ open
影响因子: 2.9
作者:
Hodgson LE;Sarnowski A;Roderick PJ;Dimitrov BD;Venn RM;Forni LG
通讯作者: Forni LG
DOI: 10.1038/s41591-018-0239-8
发表时间: 2019-01-01
期刊: NATURE MEDICINE
影响因子: 82.9
作者:
Ravizza, Stefan;Huschto, Tony;Petrich, Wolfgang
通讯作者: Petrich, Wolfgang
DOI: 10.5334/egems.199
发表时间: 2018-04-13
期刊: EGEMS (Washington, DC)
影响因子: --
作者:
Qualls LG;Phillips TA;Hammill BG;Topping J;Louzao DM;Brown JS;Curtis LH;Marsolo K
通讯作者: Marsolo K