Operating Room Usage Time Estimation with Machine Learning Models

Abstract

Effectively handling the limited number of surgery operating rooms equipped with expensive equipment is a challenging task for hospital management such as reducing the case-time duration and reducing idle time. Improving the efficiency of operating room usage via reducing the idle time with better scheduling would rely on accurate estimation of surgery duration. Our model can achieve a good prediction result on surgery duration with a dozen of features. We have found the result of our best performing department-specific XGBoost model with the values 31.6 min, 18.71 min, 0.71, 28% and 27% for the metrics of root-mean-square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), mean absolute percentage error (MAPE) and proportion of estimated result within 10% variation, respectively. We have presented each department-specific result with our estimated results between 5 and 10 min deviation would be more informative to the users in the real application. Our study shows comparable performance with previous studies, and the machine learning methods use fewer features that are better suited for universal usability.

Applying Artificial Intelligence to Perioperative Nursing Practice

“…In 2022, a study showcased a model that accurately estimated the length of different surgery times. 8 The authors argue that the universal usability of this model would allow teams to effectively reduce idle time and balance the limited availability of ORs equipped with expensive equipment. 8 Similarly, in a Canadian study, authors demonstrated how they used machine learning to estimate the duration of the hip and knee surgeries that their institution offered and determine whether it was possible to add a fifth surgery to their daily workload without accumulating additional costs and overtime.…”

“…8 The authors argue that the universal usability of this model would allow teams to effectively reduce idle time and balance the limited availability of ORs equipped with expensive equipment. 8 Similarly, in a Canadian study, authors demonstrated how they used machine learning to estimate the duration of the hip and knee surgeries that their institution offered and determine whether it was possible to add a fifth surgery to their daily workload without accumulating additional costs and overtime. 9 The model demonstrated that, with a 77% success rate, 35 extra procedures per year were possible; and that, with a 100% success rate, 56 extra procedures per year were possible.…”

“…Artificial intelligence may also be useful in scheduling surgery and managing resources. In 2022, a study showcased a model that accurately estimated the length of different surgery times 8 . The authors argue that the universal usability of this model would allow teams to effectively reduce idle time and balance the limited availability of ORs equipped with expensive equipment 8 …”

Operative Time Accuracy in the Era of Electronic Health Records: Addressing the Elephant in the Room

“…More recently, electronic health record (EHR) systems and machine learning models have been used to improve OR scheduling accuracy. These predictive models can determine the expected operative time for a specific operation based on the average of the surgeon’s previous similar procedures (Bartek et al, 2019; Chu et al, 2022; Jiao et al, 2022; Kayis et al, 2012; Larsson, 2013; Pandit & Tavare, 2011; Strum et al, 2003).…”

Internet of Things and New Technologies for Tracking Perioperative Patients With an Innovative Model for Operating Room Scheduling: Protocol for a Development and Feasibility Study

“…If cases consistently run longer, OR overuse will result in costly overtime pay and staff dissatisfaction. On the other hand, if actual case times are shorter than expected, OR underuse will lead to staff idle time, which is associated with up to 60% higher costs [ 3 - 5 ]. Also, decisions about the number of surgeries to perform during a typical day or week of activity in the OR have a considerable impact on downstream resources and on the efficient flow of patients in the system.…”