(SS#II) What Factors Predict the Best Outcomes for Elderly Patients Operated for Grade 1 Degenerative Lumbar Spondylolisthesis? A Machine Learning Analysis from the Quality Outcomes Database
Medical Student Columbia University Vagelos College of Physicians and Surgeons New York City, New York, United States
Disclosure(s):
Eunice Yang, BS: No financial relationships to disclose
Introduction: The prevalence of lumbar spondylolisthesis in the elderly population is increasing, yet factors influencing surgical outcomes remain undefined. Our study uses machine learning to identify unique outcome clusters among elderly patients operated for grade 1 degenerative lumbar spondylolisthesis.
Methods: Data was obtained from the prospective Quality Outcomes Database spondylolisthesis cohort, including patients age≥65 with grade 1 degenerative lumbar spondylolisthesis. Principal components analysis was used to generate a composite operative outcome score based on patient-reported outcomes (PROs) after 24 months. We used a k-means clustering approach to differentiate patients by composite outcome, and logistic regression to assess variable importance.
Results: Of 608 patients, a total of 233 patients over 65 were included with 24-month follow-up. Our approach identified two outcome clusters: cluster 1 corresponding to optimal outcomes (less back/leg pain, lower disability levels, higher quality of life) and cluster 2 to suboptimal outcomes. The optimal-outcomes cluster exhibited greater improvements for all PROs (p < 0.001), and clusters did not differ significantly by age (cluster 1: 71.3, cluster 2: 73.0, p=0.18). Notably, patients in the optimal-outcomes cluster (70.5%) were significantly more likely to have received fusion than were patients in the suboptimal cluster (51.7%) (p=0.01). In a logistic regression analysis, performance of fusion was the only significant independent predictor of optimal outcomes. Patients receiving fusion were more likely to have optimal surgical outcomes (OR=1.57; 95% CI 1.12-2.19; p=0.01).
Conclusion : Our analysis of elderly patients operated for grade 1 degenerative lumbar spondylolisthesis reveals two distinct clusters of optimal and suboptimal outcomes. Addition of fusion to a procedure was associated with over 1.5 times the odds of reaching optimal outcomes. There was no evidence that age significantly differed between clusters—failing to support an age cutoff for surgery. These findings may be informative to surgeons choosing between decompression versus decompression and fusion approaches for elderly patients.