Surgical Scheduling via Optimization and Machine Learning with Long-Tailed Data
This addresses congestion management in hospital surgical scheduling, but the results are incremental as most methods failed to improve over existing practices.
The study tackled reducing recovery unit congestion in cardiovascular surgery by predicting patient length of stay (LOS) with machine learning and scheduling procedures via optimization models, finding that only a conservative stochastic optimization with sufficient sampling to handle long-tailed LOS data outperformed the current manual system.
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.