Workload Balancing Among Heathcare Workers Under Uncertain Service Time Using Distributionally Robust Optimization

TL;DR

This paper introduces a distributionally robust optimization approach to fairly balance healthcare workers' workloads under uncertain service times, aiming to improve resource allocation and job satisfaction.

Contribution

It develops a novel robust optimization model with a worst-case CVaR approximation for fair workload distribution in healthcare staffing under uncertainty.

Findings

Promising results on synthetic data validate the approach.

The model effectively reduces workload disparities.

Explicit formulas for hyperrectangle support sets are provided.

Abstract

Healthcare systems are facing serious challenges in balancing their human resources to cope with volatile service demand, while at the same time providing necessary job satisfaction to the healthcare workers. We propose in this paper a distributionally robust optimization formulation to generate a task assignment plan that promotes the fairness in allocation, attained by reducing the difference in the total working time among workers, under uncertain service time. The proposed joint chance constraint model is conservatively approximated by a worst-case Conditional Value-at-Risk, and we devise a sequential algorithm to solve the finite-dimensional reformulations which are linear (mixed-binary) optimization problems. We also provide explicit formula in the situation where the support set of the random vectors is a hyperrectangle. The experiment with synthetic data suggests promising results for our approach.