Handling Overtime Constraints in Mixed Integer Linear Programming for Surgical Scheduling: A Comparison of Neural Network and Classical Linearization Techniques

TL;DR

This paper introduces a neural network-based method to improve surgical scheduling by better handling overtime constraints in MILP models, showing competitive results with classical approaches.

Contribution

It integrates feedforward neural networks into MILP models to approximate surgery durations, enhancing efficiency and accuracy in operating room scheduling under uncertainty.

Findings

FNN approach achieves optimality gap below 2% in all cases.

It yields the highest OR utilization in six of eight cases.

It produces overtime probabilities closest to targets on average.

Abstract

Uncertainty in surgery durations continues to be difficult to account for in operating room scheduling. In particular, it remains complex to accurately incorporate uncertainty in surgical overtime constraints within mixed-integer linear programming (MILP) models. Therefore, we propose a method that integrates feedforward neural networks (FNNs) into MILP models to approximate the total surgery duration in these overtime constraints. The proposed approach is evaluated using real-life hospital data and compared against two classical approaches: scenario-based modelling and piecewise linear function approximations. We demonstrate that with a relatively small FNN, we achieve competitive operating room schedules in terms of both solution quality and computational performance. The FNN-based approach is the most computationally efficient with an optimality gap lower than 2% in all cases, achieves the highest operating room utilization in six out of eight considered cases, and on average produces simulated overtime probabilities closest to the predefined target.