Surgical scheduling via optimization and machine learning with long-tailed data
Name
10729_2023_9649_ReferencePDF.pdf
Size
2.52 MB
Format
Adobe PDF
Checksum (MD5)
0fd22a9d1a3517e055847894baa6230b
Author(s)
Shi, Yuan
Mahdian, Saied
Blanchet, Jose
Glynn, Peter
Shin, Andrew Y.
Scheinker, David
Date Issued
September 4, 2023
Publisher
Springer US
Citation
Shi, Yuan, Mahdian, Saied, Blanchet, Jose, Glynn, Peter, Shin, Andrew Y. et al. 2023. "Surgical scheduling via optimization and machine learning with long-tailed data."
Version
Author's final manuscript
Abstract
Using data from cardiovascular surgery patients with long and highly variable post-surgical lengths of stay (LOS), we develop a modeling framework to reduce recovery unit congestion. We estimate the LOS and its probability distribution using machine learning models, schedule procedures on a rolling basis using a variety of optimization models, and estimate performance with simulation. The machine learning models achieved only modest LOS prediction accuracy, despite access to a very rich set of patient characteristics. Compared to the current paper-based system used in the hospital, most optimization models failed to reduce congestion without increasing wait times for surgery. A conservative stochastic optimization with sufficient sampling to capture the long tail of the LOS distribution outperformed the current manual process and other stochastic and robust optimization approaches. These results highlight the perils of using oversimplified distributional models of LOS for scheduling procedures and the importance of using optimization methods well-suited to dealing with long-tailed behavior.
MIT Department
Massachusetts Institute of Technology. Operations Research Center
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s10729-023-09649-0
