Predicting Readmission After Anterior, Posterior, and Posterior Interbody Lumbar Spinal Fusion: A Neural Network Machine Learning Approach

BACKGROUND: Readmission after spine surgery is costly and a relatively common occurrence. Previous research identified several risk factors for readmission; however, the conclusions remain equivocal. Machine learning algorithms offer a unique perspective in analysis of risk factors for readmission and can help predict the likelihood of this occurrence. This study evaluated a neural network (NN), a supervised machine learning technique, to determine whether it could predict readmission after 3 lumbar fusion procedures. METHODS: The American College of Surgeons National Surgical Quality Improvement Program database was queried between 2009 and 2018. Patients who had undergone anterior, lateral, and/or posterior lumbar fusion were included in the study. The Python scikit Learn package was used to run the NN algorithm. A multivariate regression was performed to determine risk factors for readmission. RESULTS: There were 63,533 patients analyzed (12,915 anterior lumbar interbody fusion, 27,212 posterior lumbar interbody fusion, and 23,406 posterior spinal fusion cases). The NN algorithm was able to successfully predict 30-day readmission for 94.6% of anterior lumbar interbody fusion, 94.0% of posterior lumbar interbody fusion, and 92.6% of posterior spinal fusion cases with area under the curve values of 0.64e0.65. Multivariate regression indicated that age >65 years and American Society of Anesthesiologists class >II were linked to increased risk for readmission for all 3 procedures. CONCLUSIONS: The accurate metrics presented indicate the capability for NN algorithms to predict readmission after lumbar arthrodesis. Moreover, the results of this study serve as a catalyst for further research into the utility of machine learning in spine surgery.