Machine Learning to Predict-Then-Optimize Elective Orthopaedic Surgery Scheduling Improves Operating Room Utilization

Objective: To determine the potential for improving elective surgery scheduling for total knee and hip arthroplasty (TKA and THA, respectively) by utilizing a two-stage approach that incorporates machine learning (ML) prediction of the duration of surgery (DOS) with scheduling optimization. Materials and Methods: Two ML models (for TKA and THA) were trained to predict DOS using patient factors based on 302,490 and 196,942 examples, respectively, from a large international database. Three optimization formulations based on varying surgeon flexibility were compared: Any- surgeons could operate in any operating room at any time, Split- limitation of two surgeons per operating room per day, and MSSP- limit of one 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 Any scheduling formulation performed significantly worse than the Split and MSSP formulations with respect to overtime and underutilization (p<0.001). The latter two problems performed similarly (p>0.05) over most schedule parameters. The ML-prediction schedules outperformed those generated using a mean DOS over all schedule parameters, with overtime reduced on average by 300 to 500 minutes per week. Using a 15-minute schedule granularity with a wait list pool of minimum 1 month generated the best schedules. Conclusion: Assuming a full waiting list, optimizing an individual surgeons elective operating room time using an ML-assisted predict-then optimize scheduling system improves overall operating room efficiency, significantly decreasing overtime.