Open AccessA High-Fidelity Model to Predict Length of Stay in the Neonatal Intensive Care Unit
Author(s) -
Kanix Wang,
Walid Hussain,
John R. Birge,
Michael D. Schreiber,
Daniel C. Adelman
Publication year - 2022
Publication title -
informs journal on computing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.403
H-Index - 80
eISSN - 1526-5528
pISSN - 1091-9856
DOI - 10.1287/ijoc.2021.1062
Subject(s) - fidelity , computer science , health care , predictive power , neonatal intensive care unit , medical emergency , data mining , medicine , pediatrics , telecommunications , economics , economic growth , philosophy , epistemology
Having an interpretable dynamic length-of-stay (LOS) model can help hospital administrators and clinicians make better decisions and improve the quality of care. The widespread implementation of electronic medical record (EMR) systems has enabled hospitals to collect massive amounts of health data. However, how to integrate this deluge of data into healthcare operations remains unclear. We propose a framework grounded in established clinical knowledge to model patients' lengths-of-stay. In particular, we impose expert knowledge when grouping raw clinical data into medically meaningful variables, which summarize patients' health trajectories. We use dynamic predictive models to output patients' remaining lengths-of-stay (RLOS), future discharges, and census probability distributions based on their health trajectories up to the current stay. Evaluated with large-scale EMR data, the dynamic model significantly improves predictive power over the performance of any model in previous literature and remains medically interpretable.