Introduction: The LOS following ASD surgery is a critical time period allowing for recovery to levels safe enough to return home or to rehabilitation. Thus, the goal is to minimize it for conserving hospital resources and third party payer pressure. Factors related to LOS have not been studied nor has a predictive model been created. The goal of this study was to construct a preadmission predictive model based on patients’ (pts) baseline variables and modifiable surgical parameters.
Methods: Retrospective review of a multicenter, prospective ASD database. Inclusion criteria: operative pts, age >18yrs, ASD. Pts with staged surgery at a separate hospitalization or LOS>30 days were excluded. 66 variables were initially evaluated with 40 being used for model building following univariable predictor importance =0.90, redundancy, and collinearity testing. Variables included: demographics, comorbidities, preop HRQOL, preop coronal and sagittal radiographic parameters, and modifiable surgical factors (Figure). A generalized linear model was constructed using a training dataset developed from a boostrapped sample with replacement using a random number generator. Pts randomly omitted from the boostrapped sample composed the testing dataset. Accuracy was calculated by comparison of predicted LOS to the actual LOS.
Results: A total of 689 patients were eligible with 653 meeting inclusion criteria. The mean LOS was 7.9±4.1 days (range: 1-28). Following bootstrapping, 893 pts were modeled in total, Training:653, Testing:240(36.6%). The linear correlations for the training and testing datasets were 0.632 and 0.507, respectively. Testing dataset accuracy within 2 days of actual LOS was 75.4% (181/240 pts). Predictor importance rankings are listed in the Figure.
Conclusions: A successful model was created to predict LOS to an accuracy of 75% within 2 days. There are some factors related to LOS that are not likely captured in large databases, which may partially explain the 75% accuracy, such as rehab bed availability and social support resources.
Patient Care: This model sets the groundwork for point-of-care predictive modeling for LOS to aid clinicians and third party payors in allocating hospital resources.
Learning Objectives: By the conclusion of this session, participants should be able to: 1) Describe the importance of preop predictive modeling for LOS, 2) Discuss in small groups 40 variables that contribute to LOS and 3) appreciate that a model for LOS is not perfect due to missing variables not usually captured.