Key result
Machine learning for OR scheduling outperforms state-of-the-art models by ~43% in predicting ICU beds.
Why the study?
Most master surgery scheduling approaches focus only on the operating room while neglecting the impact on downstream units like the intensive care unit, or reflect overly simplified versions of real-world hospital settings.
Effect estimate: Outperforms by 43%
A machine learning-based prediction model for integrated operating room scheduling significantly improves the accuracy of ICU bed occupancy predictions compared to existing models.
ML models may refine OR scheduling predictions but should not yet change practice; leaves open prospective validation of clinical impact.
In a master surgery scheduling (MSS) problem, a hospital's operating room (OR) capacity is assigned to different medical specialties. This task is critical since the risk of assigning too much or too little OR time to a specialty is associated with overtime or deficit hours of the staff, deferral or delay of surgeries, and unsatisfied—or even endangered—patients. Most MSS approaches in the literature focus only on the OR while neglecting the impact on downstream units or reflect a simplified version of the real‐world situation. We present the first prediction model for the integrated OR scheduling problem based on machine learning. Our three‐step approach focuses on the intensive care unit (ICU) and reflects elective and urgent patients, inpatients and outpatients, and all possible paths through the hospital. We provide an empirical evaluation of our method with surgery data for Universitätsklinikum Augsburg, a German tertiary care hospital with 1700 beds. We show that our model outperforms a state‐of‐the‐art model by 43% in number of predicted beds. Our model can be used as supporting tool for hospital managers or incorporated in an optimization model. Eventually, we provide guidance to support hospital managers in scheduling surgeries more efficiently.
No takes yet. Share an insight, caveat, or question.
Schiele et al. (2020) studied Intensive care unit bed occupancy and operating room scheduling. Machine learning prediction model vs. State-of-the-art model was evaluated on Number of predicted beds (Outperforms by 43%). A machine learning prediction model for integrated operating room scheduling outperformed a state-of-the-art model by 43% in the number of predicted intensive care unit beds.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: