Abstract and Introduction
Abstract
Study Design: A retrospective cohort study.
Objective: To identify the factors associated with readmissions after PLF using machine learning and logistic regression (LR) models.
Summary of Background Data: Readmissions after posterior lumbar fusion (PLF) place significant health and financial burden on the patient and overall health care system.
Materials and Methods: The Optum Clinformatics Data Mart database was used to identify patients who underwent posterior lumbar laminectomy, fusion, and instrumentation between 2004 and 2017. Four machine learning models and a multivariable LR model were used to assess factors most closely associated with 30-day readmission. These models were also evaluated in terms of ability to predict unplanned 30-day readmissions. The top-performing model (Gradient Boosting Machine; GBM) was then compared with the validated LACE index in terms of potential cost savings associated with the implementation of the model.
Results: A total of 18,981 patients were included, of which 3080 (16.2%) were readmitted within 30 days of initial admission. Discharge status, prior admission, and geographic division were most influential for the LR model, whereas discharge status, length of stay, and prior admissions had the greatest relevance for the GBM model. GBM outperformed LR in predicting unplanned 30-day readmission (mean area under the receiver operating characteristic curve 0.865 vs. 0.850, P<0.0001). The use of GBM also achieved a projected 80% decrease in readmission-associated costs relative to those achieved by the LACE index model.
Conclusions: The factors associated with readmission vary in terms of predictive influence based on standard LR and machine learning models used, highlighting the complementary roles these models have in identifying relevant factors for the prediction of 30-day readmissions. For PLF procedures, GBM yielded the greatest predictive ability and associated cost savings for readmission.
Level of Evidence: 3
Introduction
Spinal fusion is widely utilized to treat a variety of spinal conditions, including degenerative disease, scoliosis, spinal tumors, and spinal trauma. The volume of elective lumbar fusion surgery for the degenerative disease alone in the United States increased 62% from 2004 to 2015, with an estimated 60.4 cases per 100,000 and aggregate hospital costs exceeding $10 billion.[1] In 2014, spinal fusions were the sixth most common surgical procedure in the United States.[2] However, the procedure is associated with multiple complications, which are in turn, associated with increased cost. Previous studies have estimated that, for lumbar spinal fusion surgery, the 30-day readmission rate ranges from 5.5% to 11.1%.[3,4]
Thus, increased focus is being placed on developing predictive models that identify patients at high risk of readmission after spine surgery[5–9] and subsequently applying interventions to reduce their readmission risk. In particular, machine learning models have strong potential to improve clinical decision-making by providing data-driven aid in the optimization of resource allocation for the prevention of hospital readmissions.[10] Through complex use of patient demographic, clinical, and perioperative data, these models can assess patients' risk of readmission to the hospital after surgery, help guide perioperative resource allocation to decrease their likelihood of readmission and, in turn, lower overall health care utilization costs. This study aimed to identify risk factors associated with readmissions after posterior lumbar fusion and instrumentation using logistic regression (LR) and machine learning models. Furthermore, this study sought to assess the predictive performance of these models on readmission, compare their performance to that of the validated LACE index, and estimate the potential cost savings of implementing machine learning models to reduce readmissions in clinical practice.
Spine. 2023;48(17):1224-1233. © 2023 Lippincott Williams & Wilkins
