Related Experiment Video
Updated: Aug 9, 2026
Emergency Undocking in Robotic Surgery: A Simulation Curriculum
Published on: May 20, 2018
Improving Surgical Scheduling Efficiency with Operating Room Coordination and Allocation at Centre Antoine
Dorian Culié1,2, Renaud Schiappa2, Terence Viellard2
1From the Cervico-facial Oncology Surgical Department, University Institute of Face and Neck, Centre Antoine Lacassagne, University of Côte d'Azur, Nice, France (Culié, Poissonnet, Bozec, Delcour-Delembert, Ammirati, Eudeline, Villarme, Chamorey).
Background:
Operating room (OR) scheduling is critical for timely patient care, optimal resource usage, and equitable surgical access. Despite the cost and complexity of ORs, few tools address patient scheduling comprehensively. This study evaluates ORCAL (Operating Room Coordination and Allocation at Centre Antoine Lacassagne), a scheduling assistant designed to improve OR scheduling efficiency. Machine Learning (ML) was integrated to enhance prediction of surgery dates and scheduling reliability.
Study Design:
This retrospective, single-center study included all patients operated on between May 1, 2022, and May 1, 2024, excluding procedures requiring emergency intervention. Patients were prospectively assigned 1 of 4 priority grades reflecting clinical recommendations and surgical timelines. ORCAL replaced manual scheduling with an algorithm using a priority coefficient based on assigned grade, time since consultation, and patient availability date. Outcomes included waiting times, variability in priority coefficients, planned and actual surgical time per operative day, and discrepancies between initial and actual surgery dates. Multiple ML models were trained and tested on 1,485 ORCAL-scheduled cases to predict the actual date of surgery and evaluate scheduling accuracy. Performance was evaluated using the coefficient of determination (R2) and error metrics.
Results:
ORCAL reduced the average waiting time by 7.5 days (p < 0.0001), with greatest benefit for grade 1 cases (-12.3 days). The number of operative days, defined as the number of room-days available for surgery, decreased (417 vs 521, p < 0.001), whereas the planned surgical time per operative day increased (488.1 ± 155.3 vs 462.4 ± 163.9 minutes, p = 0.02). The best ML model (random forest) achieved R2=0.9,716 and reduced date discrepancies between the initially proposed and the actual surgery dates to 12.7 ± 23.6 days.
Conclusions:
ORCAL improves surgical scheduling efficiency and accuracy while supporting equitable, patient-centered care.
