Early prediction of acute kidney injury in critical care setting using clinical notes and structured multivariate physiological measurements
Name
SHTI-264-SHTI190245.pdf
Description
Published version
Size
274.43 KB
Format
Adobe PDF
Checksum (MD5)
78e572f0dc25bb98733e1513b8af005f
Author(s)
Sun, M
Baron, J
Dighe, A
Szolovits, P
Wunderink, RG
Isakova, T
Luo, Y
Date Issued
August 21, 2019
Journal
Studies in Health Technology and Informatics
Version
Final published version
Abstract
© 2019 International Medical Informatics Association (IMIA) and IOS Press. The onset of acute kidney injury (AKI) during an intensive care unit (ICU) admission is associated with increased morbidity and mortality. Developing novel methods to identify early AKI onset is of critical importance in preventing or reducing AKI complications. We built and applied multiple machine learning models to integrate clinical notes and structured physiological measurements and estimate the risk of new AKI onset using the MIMIC-III database. From the clinical notes, we generated clinically meaningful word representations and embeddings. Four supervised learning classifiers and mixed-feature deep learning architecture were used to construct prediction models. The best configurations consistently utilized both structured and unstructured clinical features and yielded competitive AUCs above 0.83. Our work suggests that integrating structured and unstructured clinical features can be effectively applied to assist clinicians in identifying the risk of incident AKI onset in critically-ill patients upon admission to the ICU.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution NonCommercial License 4.0
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3233/SHTI190245
