121 Development and Validation of a Predictive Score for Lumbar Synovial Cyst Recurrence

Abstract

INTRODUCTION: Lumbar Synovial Cysts represent a relatively rare clinical pathology that may result in radiculopathy or neurogenic claudication. Due to their potential for recurrence, some authors advocate for segmental fusion, as opposed to decompression alone, as a way to eliminate the risk for recurrence. METHODS: A retrospective review was conducted of all patients evaluated at a single center over 20 years who were found to have symptomatic lumbar synovial cysts requiring intervention. Only patients undergoing decompression without fusion were included in the analysis. Following this, baseline characteristics were obtained as well as radiographic information. A machine learning method (RiskSLIM) was then utilized to create a risk stratification score to identify patients at high risk for symptomatic cyst recurrence requiring repeat surgical intervention. Following this a 5-fold cross validation was completed. RESULTS: In total 89 patients were identified to have complete radiographic information. Of these, 11 patients developed cyst recurrence requiring reoperation. The Lumber Synovial Cyst Score (LSCS) was then created with an area under the curve of 0.83 with CAL error of 11.0%. Predicative factors were found to include facet inclination angle greater than 45 degrees, canal stenosis greater than 50%, T2 joint space hyperintensity, and presence of grade I spondylolisthesis. The probability of cyst recurrence ranged from < 5% for a score of 2 or less and > 88% for a score of 7. CONCLUSIONS: The LSCS model is a quick and accurate tool to assist in clinical decision making in treatment of lumbar synovial cysts.