In BriefAuthors of this study analyzed hospital readmissions following laminectomy and developed predictive models to identify readmitted patients with an accuracy >95% when using all variables and >79% when using only predischarge variables. A model capable of predicting 40% of readmitted patients was created using only the variables known predischarge. This investigation is important in its provision of data that will assist the development of predictive models for readmission as well as interventions to prevent readmission in high-risk patients.
Keywords: ASA = American Society of Anesthesiologists; AUC = area under the receiver operating characteristic curve; BMI = body mass index; GBM = gradient boosting machine; LOS = length of stay; RVU = relative value unit; SMOTE = Synthetic Minority Oversampling Technique; diagnostic technique; hospital readmission; lumbar; machine learning; predictive model; spine surgery.