Key result
Simulated case resequencing using an XGBoost machine learning model significantly reduced the frequency of operating room days with patients remaining in the PACU after 7:00 pm from 41.4% to 12.1%.
Why the study?
Post-anesthesia care unit length of stay is an important perioperative efficiency metric, motivating the development of preoperative machine learning models to identify patients at risk for prolonged stays and reduce after-hours staffing needs.
Does machine learning-based case resequencing reduce the frequency of patients remaining in the PACU after-hours in ambulatory surgical patients?
Observational (n=10,928)
No
Does machine learning-based case resequencing reduce the frequency of patients remaining in the PACU after-hours in ambulatory surgical patients?
Absolute Event Rate: 12.1% vs 41.4%
p-value: p=<0.0001
Machine learning models using preoperative characteristics can predict prolonged PACU length of stay and optimize surgical case sequencing to significantly reduce after-hours PACU utilization.
May support ML sequencing to cut after-hours PACU use in ambulatory surgery; hypothesis-generating and requires prospective trials.
PURPOSE The post-anesthesia care unit (PACU) length of stay is an important perioperative efficiency metric. The aim of this study was to develop machine learning models to predict ambulatory surgery patients at risk for prolonged PACU length of stay - using only pre-operatively identified factors - and then to simulate the effectiveness in reducing the need for after-hours PACU staffing. METHODS Several machine learning classifier models were built to predict prolonged PACU length of stay (defined as PACU stay ≥ 3 hours) on a training set. A case resequencing exercise was then performed on the test set, in which historic cases were re-sequenced based on the predicted risk for prolonged PACU length of stay. The frequency of patients remaining in the PACU after-hours (≥ 7:00 pm) were compared between the simulated operating days versus actual operating room days. RESULTS There were 10,928 ambulatory surgical patients included in the analysis, of which 580 (5.31%) had a PACU length of stay ≥ 3 hours. XGBoost with SMOTE performed the best (AUC = 0.712). The case resequencing exercise utilizing the XGBoost model resulted in an over three-fold improvement in the number of days in which patients would be in the PACU past 7pm as compared with historic performance (41% versus 12%, P<0.0001). CONCLUSION Predictive models using preoperative patient characteristics may allow for optimized case sequencing, which may mitigate the effects of prolonged PACU lengths of stay on after-hours staffing utilization.
No takes yet. Share an insight, caveat, or question.
Tully et al. (2023) conducted an observational in Ambulatory surgery patients (n=10,928). Machine learning-based case resequencing (XGBoost model) vs. Historic performance (actual case sequencing) was evaluated on Frequency of operating room days where patients remained in the PACU after-hours (≥ 7:00 pm) (p=<0.0001). Simulated case resequencing using an XGBoost machine learning model significantly reduced the frequency of operating room days with patients remaining in the PACU after 7:00 pm from 41.4% to 12.1%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: