Cross-site transportability of an explainable artificial

Index

Abstract

Artificial intelligence (AI) shows promise in predicting acute kidney injury (AKI), but clinical adoption needs interpretability and transportability. This study uses the US PCORnet platform to develop an AKI prediction model and assess its transportability across six health systems. Results show cross-site performance deterioration, caused by heterogeneity of risk factors. A method to predict AI model transportability is derived, accelerating external AI model adaptation in hospitals.

Publisher

Nature Communications

Published On

Nov 09, 2020

Authors

Xing Song, Alan S. L. Yu, John A. Kellum, Lemuel R. Waitman, Michael E. Matheny, Steven Q. Simpson, Yong Hu, Mei Liu

Related Publications

Explore these studies to deepen your understanding of the subject.

Medicine and Health

Novel Biomarkers for Early Detection of Acute Kidney Injury and Prediction of Long-Term Kidney Function Decline after Partial Nephrectomy

M. Allinovi, F. Sessa, et al.

Business

Understanding continuance intention of artificial intelligence (AI)-enabled mobile banking applications: an extension of AI characteristics to an expectation confirmation model

J. Lee, Y. Tang, et al.

Chemistry

A generative artificial intelligence framework based on a molecular diffusion model for the design of metal-organic frameworks for carbon capture

H. Park, X. Yan, et al.

Medicine and Health

Development and evaluation of an artificial intelligence system for COVID-19 diagnosis

C. Jin, W. Chen, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny