Preoperative ambulatory assistive device predicts rehabilitation discharge following lumbar decompression

Introduction: Elective lumbar decompression, commonly performed via laminectomy or microdiscectomy, is a well-tolerated surgical procedure. Patients requiring discharge to inpatient rehabilitation facilities are infrequent but generate increased healthcare costs and can be burdensome to patients and families. This study aims to develop an accurate predictive model for rehabilitation discharge following elective lumbar decompression, as well as to identify associated factors.

Methods: A single-center, retrospective cohort study was conducted at our institution, reviewing clinical charts over a four-year period to collect demographic, clinical and procedural variables. Patients who underwent lumbar decompression were identified using Current Procedural Terminology codes for laminectomy and microdiscectomy. Those with confounding diagnosis or admitted from a rehabilitation facility were excluded. The primary outcome was rehabilitation discharge. An initial univariate analysis was performed. One logistic regression model and two machine learning models were trained and evaluated on the data using cross-validation.

Results: A total of 179 patients were considered for the analysis. After performing a Benjamini-Hochberg correction, the univariate analysis identified age, ASA score, and the need for a walking assistive device as significant predictors (p < 0.001) of rehabilitation discharge. A 5-fold, 10-times repeated cross-validation compared the performance of the three models: an AIC-weighted adjusted logistic regression model, a machine learning (ML) random forest model, and a ML k-nearest neighbors’ model. The logistic regression model demonstrated superior performance, with the highest area under the receiver operating characteristic curve (0.78), Youden’s J statistic (0.59) and balanced accuracy (0.80), reporting a significant association between the use of an ambulatory assistive device and rehabilitation discharge (p < 0.001).

Conclusion : When considered alongside frailty, lack of support, and other variables, the necessity for a walking assistive device can serve as a reliable predictor of rehabilitation discharge, thereby improving patient workflow and reducing healthcare costs.