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. 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. 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). 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.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10333394PMC
http://dx.doi.org/10.1007/s10916-023-01966-9DOI Listing

Publication Analysis

Top Keywords

length stay
24
pacu length
20
machine learning
12
case resequencing
12
prolonged pacu
12
pacu
9
ambulatory surgery
8
risk prolonged
8
stay ≥
8
≥ hours
8

Similar Publications

Background: Frail elderly patients have a higher risk of postoperative morbidity and mortality. Prehabilitation is a potential intervention for optimizing postoperative outcomes in frail patients. We studied the impact of a prehabilitation program on length of stay (LOS) in frail elderly patients undergoing elective surgery.

View Article and Find Full Text PDF

Objectives: To report the feasibility of a fluid management practice bundle and describe the pre- vs. post-implementation prevalence and odds of cumulative fluid balance greater than 10% in critically ill pediatric patients with respiratory failure.

Design: Retrospective cohort from May 2022 to December 2022.

View Article and Find Full Text PDF

Rationale: In critically ill patients receiving invasive mechanical ventilation, switching from controlled to assisted ventilation is a crucial milestone towards ventilator liberation. The optimal timing for switching to assisted ventilation has not been studied.

Objectives: Our objective was to determine whether a strategy of early as compared to delayed switching affects the duration of invasive mechanical ventilation, ICU length of stay, and mortality.

View Article and Find Full Text PDF

Background: Extracorporeal membrane oxygenation (ECMO) has emerged as a critical intervention in the management of patients with trauma-induced cardiorespiratory failure. This study aims to compare outcomes in patients with severe thoracic injuries with and without venovenous extracorporeal membrane oxygenation (VV-ECMO).

Methods: We performed a retrospective cohort study on Trauma Quality Improvement Program (2017-2021) and included all patients with isolated blunt thoracic injuries with Abbreviated Injury Scale score of ≥4 who required intubation.

View Article and Find Full Text PDF

Total hip arthroplasty (THA) is a widely performed surgical procedure in the United States, but disparities in THA outcomes related to hospital-level factors, such as safety-net burden, are underexplored. This study expands on previous research by analyzing multicenter, multistate data from 2015 to 2020 to investigate the impact of hospital safety-net burden-defined as the proportion of services billed to Medicaid and uninsured patients-on THA outcomes. This study is a retrospective analysis using data from the State Inpatient Databases for Florida, Kentucky, Maryland, New York, Washington, New Jersey, and North Carolina.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!