Predicting Inpatient Flow at a Major Hospital Using Interpretable Analytics
Name
2020.05.12.20098848v2.full.pdf
Description
Accepted version
Size
2.69 MB
Format
Adobe PDF
Checksum (MD5)
a6d201b698774aa6bab9be25c1ff1eda
Author(s)
Bertsimas, Dimitris
Pauphilet, Jean
Stevens, Jennifer
Tandon, Manu
Date Issued
2021
Journal
Manufacturing and Service Operations Management
Publisher
Institute for Operations Research and the Management Sciences (INFORMS)
Citation
Bertsimas, Dimitris, Pauphilet, Jean, Stevens, Jennifer and Tandon, Manu. 2021. "Predicting Inpatient Flow at a Major Hospital Using Interpretable Analytics." Manufacturing and Service Operations Management.
Version
Author's final manuscript
Abstract
Problem definition: Translate data from electronic health records (EHR) into accurate predictions on patient flows and inform daily decision making at a major hospital. Academic/practical relevance: In a constrained hospital environment, forecasts on patient demand patterns could help match capacity and demand and improve hospital operations. Methodology: We use data from 63,432 admissions at a large academic hospital (50% female, median age 64 years old, median length of stay 3.12 days). We construct an expertise-driven patient representation on top of their EHR data and apply a broad class of machine learning methods to predict several aspects of patient flows. Results: With a unique patient representation, we estimate short-term discharges, identify long-stay patients, predict discharge destination, and anticipate flows in and out of intensive care units with accuracy in the 80%+ range. More importantly, we implement this machine learning pipeline into the EHR system of the hospital and construct prediction-informed dashboards to support daily bed placement decisions. Managerial implications: Our study demonstrates that interpretable machine learning techniques combined with EHR data can be used to provide visibility on patient flows. Our approach provides an alternative to deep learning techniques that is equally accurate, interpretable, frugal in data and computational power, and production ready.
MIT Department
Massachusetts Institute of Technology. Operations Research Center
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1287/MSOM.2021.0971
