ORAHS2025
Abstract Submission

189. Shaping Outpatient Surgery Schedules: A Dual-Horizon Approach with Distributional Clustering

Invited abstract in session FA-2: Surgery scheduling 2, stream Sessions.

Friday, 9:00-10:30
Room: NTNU, Realfagbygget R8

Authors (first author is the speaker)

1. Davide Duma
Dipartimento di Matematica "Felice Casorati", Università degli Studi di Pavia
2. Alice Salacrist
Dipartimento di Matematica "Felice Casorati", Università degli Studi di Pavia

Abstract

The growing demand for outpatient surgeries raises the challenge of minimizing two key performance indicators: direct waiting time, experienced on the day of surgery, and indirect waiting time, defined as the number of days between surgical request and procedure. While direct waiting time depends on short-term allocation decisions, indirect waiting time emerges from a sequence of planning choices made over time, making it inherently more complex to control. In addition, these objectives depend on the level of resource utilization and robustness, resulting in conflict since reducing one requires trade-offs in the other.

Our study proposes a dual-horizon approach that combines clustering and multi-objective stochastic programming to jointly manage direct waiting time, indirect waiting time, and overtime. Surgical procedures are grouped using K-Means-type algorithms based on the similarity of their duration distributions. These clusters form the basis for constructing a cyclic surgical schedule, which improves predictability and facilitates long-term control of indirect waiting times, with positive implications for fairness across patients.

A case study based on real data from the Obstetrics and Gynaecology Department of Policlinico San Matteo in Pavia, Italy, is used to analyze the impact of using Euclidean or Wasserstein distances in the clustering of surgical procedures and to explore the balance between competing criteria.

Keywords

Status: accepted

Back to the list of papers