Nurse Workload Balancing in a Surgical Ward using Data-Driven Inverse Optimization

Published Online:https://doi.org/10.1287/serv.2025.0138

Sustained inequities in workload distribution can lead to increased stress, reduced job satisfaction, high turnover, and nursing shortages. Consequently, healthcare quality may also suffer from persistent imbalances in nursing workload. We develop a data-driven analytical framework to improve workload balance by optimizing nurse–patient assignment decisions at the beginning of each shift. To this end, we use an extensive dataset collected by a real-time location system installed in the surgical services department of a large tertiary hospital.

The nurse workload is modelled as a multi-attribute function that incorporates the number of assigned patients, travel distance, and direct care time. The relative importance of these attributes is elicited from historical assignment decisions using a data-driven inverse-optimization procedure and subsequently translated into assignment rules via clustering. These rules are then incorporated into a robust nurse workload-balancing model to generate nurse–patient assignments for upcoming shifts, accounting for uncertainty in workload preferences.

In the surgical ward we studied, the proposed approach reduces the maximum travel distance by 50%–77%. In addition, the average ranges of total direct care time, maximum travel distance, and number of assigned patients decrease by 65%, 45%, and 31%, respectively.

INFORMS site uses cookies to store information on your computer. Some are essential to make our site work; Others help us improve the user experience. By using this site, you consent to the placement of these cookies. Please read our Privacy Statement to learn more.