Predicting intervention onset in the ICU with switching state space models.
Name
2611344.pdf
Description
Accepted version
Size
380.55 KB
Format
Adobe PDF
Checksum (MD5)
03293ae7748ada58c4e0ab6574a42a07
Author(s)
Ghassemi, Marzyeh
Wu, M.
Hughes, M.
Doshi-Velez, F.
Date Issued
March 2017
Journal
AMIA Joint Summit
Publisher
American Medical Informatics Association
Citation
Ghassemi, M., M. Wu, M. Hughes, and F. Doshi-Velez, "Predicting intervention onset in the ICU with switching state space models." AMIA Joint Summit 2017, March 27-30, 2017, San Francisco, California. url https://www.amia.org/jointsummits2017/papers
Version
Author's final manuscript
Abstract
The impact of many intensive care unit interventions has not been fully quantified, especially in heterogeneous patient populations. We train unsupervised switching state autoregressive models on vital signs from the public MIMIC-III database to capture patient movement between physiological states. We compare our learned states to static demographics and raw vital signs in the prediction of five ICU treatments: ventilation, vasopressor administra tion, and three transfusions. We show that our learned states, when combined with demographics and raw vital signs, improve prediction for most interventions even 4 or 8 hours ahead of onset. Our results are competitive with existing work while using a substantially larger and more diverse cohort of 36,050 patients. While custom classifiers can only target a specific clinical event, our model learns physiological states which can help with many interventions. Our robust patient state representations provide a path towards evidence-driven administration of clinical interventions.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://www.amia.org/jointsummits2017/papers
