EUVIMEDEUVIMED entdecken
Open Access

Using Machine Learning to Predict-Then-Optimize Elective Orthopedic Surgery Scheduling to Improve Operating Room Utilization: Retrospective Study

Johnathan R Lex iD, Aazad Abbas iD, Jacob Mosseri iD, Jay Singh Toor iD, Michael Simone iD, Bheeshma Ravi iD, Cari Whyne iD, Elias B Khalil iD

JMIR Medical Informatics · 2025

DOI: 10.2196/70857 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Medical Informatics, 2025. Verfasst von Johnathan R Lex und 7 weiteren Autor:innen. Beteiligte Einrichtung: Orthopaedic Biomechanics Lab, Sunnybrook Research Institute, 2075 Bayview Avenue, Suite S620, Toronto, ON, M4N 3M5, Canada. Hauptthemen laut MEDLINE: Machine Learning, Operating Rooms, Elective Surgical Procedures, Appointments and Schedules. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Total knee and hip arthroplasty (TKA and THA) are among the most performed elective procedures. Rising demand and the resource-intensive nature of these procedures have contributed to longer wait times despite significant health care investment. Current scheduling methods often rely on average surgical durations, overlooking patient-specific variability.

Objective

To determine the potential for improving elective surgery scheduling for TKA and THA, respectively, by using a 2-stage approach that incorporates machine learning (ML) prediction of the duration of surgery (DOS) with scheduling optimization.

Methods

In total, 2 ML models (one each for TKA and THA) were trained to predict DOS using patient factors based on 302,490 and 196,942 patients, respectively, from a large international database. In total, 3 optimization formulations based on varying surgeon flexibility were compared: Any (surgeons could operate in any operating room at any time), Split (limitation of 2 surgeons per operating room per day), and multiple subset sum problem (MSSP; limit of 1 surgeon per operating room per day). Two years of daily scheduling simulations were performed for each optimization problem using ML prediction or mean DOS over a range of schedule parameters. Constraints and resources were based on a high-volume arthroplasty hospital in Canada.

Results

The TKA and THA prediction models achieved test accuracy (with a 30 min buffer) of 78.1% (mean squared error 0.898) and 75.4% (mean squared error 0.916), respectively. Any scheduling formulation performed significantly worse than the Split and MSSP formulations with respect to overtime and underutilization ( P .05) over most schedule parameters. The ML prediction schedules outperformed those generated using a mean DOS for most scheduling parameters, with overtime reduced on average by 300-500 minutes per week (12‐20 min per operating room per day; P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningOperating RoomsElective Surgical ProceduresAppointments and SchedulesOrthopedic ProceduresHumansRetrospective StudiesArthroplasty, Replacement, KneeArthroplasty, Replacement, HipFemaleMaleCanada

Stichwörter der Autor:innen

elective surgeryhip and knee arthroplastymachine learningoptimizationorthopedic surgeryscheduling

Autor:innen und Institutionen

  • Orthopaedic Biomechanics Lab, Sunnybrook Research Institute, 2075 Bayview Avenue, Suite S620, Toronto, ON, M4N 3M5, Canada.
  • Institute of Biomedical Engineering, University of Toronto, Toronto, ON, Canada.
  • Department of Surgery, Division of Orthopedic Surgery, University of Toronto, 149 College St, Toronto, ON, M5T 1P5, Canada, 1 (416) 946-7957.
  • Department of Mechanical and Industrial Engineering, Faculty of Engineering, University of Toronto, Toronto, ON, Canada.
  • Winnipeg Spine Program, Health Sciences Centre, Department of Surgery, University of Manitoba, Manitoba, Canada.
  • Orthopaedic Surgery Section, Department of Surgery, University of Manitoba, Manitoba, Canada.

ORCID-Profile: Johnathan R Lex, Aazad Abbas, Jacob Mosseri, Jay Singh Toor, Michael Simone, Bheeshma Ravi, Cari Whyne, Elias B Khalil

Zitieren

APA

Lex, J. R., Abbas, A., Mosseri, J., Singh Toor, J., Simone, M., Ravi, B., Whyne, C., & Khalil, E. B. (2025). Using Machine Learning to Predict-Then-Optimize Elective Orthopedic Surgery Scheduling to Improve Operating Room Utilization: Retrospective Study. JMIR Medical Informatics. https://doi.org/10.2196/70857

Vancouver

Lex JR, Abbas A, Mosseri J, Singh Toor J, Simone M, Ravi B, et al. Using Machine Learning to Predict-Then-Optimize Elective Orthopedic Surgery Scheduling to Improve Operating Room Utilization: Retrospective Study. JMIR Medical Informatics. 2025. doi:10.2196/70857

BibTeX
@article{Lex2025,
  author = {Lex, Johnathan R and Abbas, Aazad and Mosseri, Jacob and Singh Toor, Jay and Simone, Michael and Ravi, Bheeshma and Whyne, Cari and Khalil, Elias B},
  title = {Using Machine Learning to Predict-Then-Optimize Elective Orthopedic Surgery Scheduling to Improve Operating Room Utilization: Retrospective Study},
  journal = {JMIR Medical Informatics},
  year = {2025},
  doi = {10.2196/70857}
}
Kostenlos starten →