Machine Learning to Predict-Then-Optimize Elective Orthopaedic Surgery Scheduling Improves Operating Room Utilization: A Retrospective Study (Preprint)

BACKGROUND Total knee and hip arthroplasty (TKA and THA) are among the most performed elective procedures. Rising demand and the resources intensive nature of these procedures has contributed to longer wait times despite significant healthcare 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 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. METHODS Two 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. 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 TKA and THA prediction models achieved test accuracy (with a 30-minute buffer) of 78.1% (MSE 0.898) and 75.4% (MSE 0.916), respectively. Any scheduling formulation performed significantly worse than the Split and MSSP formulations with respect to overtime and underutilization (P<.001). The latter two problems performed similarly (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 to 500 minutes per week (12-20 minutes per operating room per day) (P <.001). However, there was more OR underutilization with the ML-prediction schedules, with it ranging from 70-192 minutes more underutilization (P<.001). Using a 15-minute schedule granularity with a waitlist pool of minimum one month generated the ML-schedule that outperformed the mean schedule 97.1% of times. CONCLUSIONS Assuming a full waiting list, optimizing an individual surgeon’s elective operating room time using an ML-assisted predict-then-optimize scheduling system improves overall operating room efficiency, significantly decreasing overtime. This has significant potential implications for healthcare systems struggling with pressures of rising costs and growing operative waitlists. CLINICALTRIAL