Development and validation of a nomogram for determining patients requiring prolonged postanesthesia care unit length of stay after laparoscopic cholecystectomy

Abstract

Background: Laparoscopic cholecystectomy (LC) is a common surgical procedure for managing gallbladder disease. Prolonged length of stay (LOS) in the postanesthesia care unit (PACU) may lead to overcrowding and a decline in medical resource utilization. In this work, we aimed to develop and validate a predictive nomogram for identifying patients who require prolonged PACU LOS.Methods: Data from 913 patients undergoing LC at a single institution in China between 2018 and 2019 were collected, and grouped into a training set (456, cases during 2018) and a test set (457, cases during 2019). The definition of PACU LOS is the duration between admission to discharge from PACU, which we can derive from the electronic medical record system. Using the least absolute shrinkage and selection operator regression model, the optimal feature was selected, and multivariable logistic regression analysis was used to build the prolonged PACU LOS risk model. The C-index, calibration plot, and decision curve analysis (DCA) were used in assessing the model calibration, discrimination, and clinical application value, respectively. For external validation, the test set data was evaluated. Results:The predictive nomogram had 8 predictor variables for prolonged PACU LOS, including age, American Society of Anesthesiologists (ASA) grade, active smoker, gastrointestinal disease, liver disease, and cardiovascular disease. This model displayed efficient calibration and moderate discrimination with a C-index of 0.662 (95% confidence interval, 0.603 to 0.721) for the training set, and 0.609 (95% confidence interval, 0.549 to 0.669) for the test set. DCA demonstrated that the prolonged PACU LOS nomogram was reliable for clinical application when an intervention was decided at the possible threshold of 7%. Conclusions:We developed and validated a predictive nomogram with efficient calibration and moderate discrimination, and can be applied to identify patients most likely to be subjected to prolonged PACU LOS. This novel tool may shun overcrowding in PACU and optimize medical resource utilization.

Optimizing the Sequence of Surgical Procedures in an Operating Room to Reduce Post-Anesthesia Care Unit Utilization During After-Hours Using Machine Learning

“…Elsharydah et al reported a subsequent study validating this model on their institutional data and re ned a model speci c to their institution using similar features, including anesthesia type, obstructive sleep apnea, surgical specialty, and scheduled case duration [20]. Development of a predictive model for prolonged PACU LOS after laparoscopic cholecystectomy had also been reported [19]. The current study showed the advantages of using ensemble learning such as XGBoost and oversampling techniques such as SMOTE to improve prediction.…”

“…Using this knowledge, the surgical procedures were resequenced and re-evaluated, demonstrating a statistically signi cant reduction in after-hours PACU care. Though previous studies have reported the use of machine learning for PACU LOS prediction [10,[18][19][20], utilization of ensemble learning with features only known preoperatively and the subsequent testing of the ability of the model to reduce after hours PACU stay is novel. The potential to resequence cases using preoperative metrics could reduce sta ng overages and other associated costs.…”

“…Scheduled case duration is also a known predictor for prolonged PACU LOS, which may be a direct indicator of surgical complexity and need for longer anesthesia times [10,20,29]. Age has also been demonstrated to be a predictor for prolonged PACU LOS [19], which could be related to longer recovery needed for elderly patients after anesthesia. Of note, our dataset did not include any features that were unknown preoperatively (e.g.…”

Development and validation of a novel nomogram to predict the risk of the prolonged postoperative length of stay for lumbar spinal stenosis patients

“…As a convenient model-visualizing tool, it can well display the multivariate logistic regression model, where every risk factor was allocated a score depending on its in uence on the outcome and can be calculated bedside in clinical daily practice. Previous researchers have used this toolkit in their own eld [24,25]. Lu et al [14] enrolled 310 patients who underwent open lumber fusion surgery and analyzed prolonged PLOS risk factors and also visualized the model as a nomogram.…”

Development and validation of a novel nomogram to predict the risk of the prolonged postoperative length of stay for lumbar spinal stenosis patients

“…As a convenient model-visualizing tool, it can well display the multivariate logistic regression model, where every risk factor was allocated a score depending on its influence on the outcome and can be calculated bedside in clinical daily practice. Previous researchers have used this toolkit in their own field [ 24 , 25 ]. Lu et al [ 14 ] enrolled 310 patients who underwent open lumber fusion surgery and analyzed prolonged PLOS risk factors and also visualized the model as a nomogram.…”