MACHINE LEARNING-DRIVEN CLINICAL AND IMAGING CLUSTERING OF DEGENERATIVE LUMBAR SPONDYLOLISTHESIS: IMPLICATIONS FOR STRATIFIED SURGICAL CARE

Degenerative lumbar spondylolisthesis (DLS) is the commonest reason for decompression and fusion in the elderly. Current evidence questions the necessity of accompanying fusion in all DLS because of significant clinical and radiographic heterogeneity. This heterogeneity creates substantial variability in surgeon reported decision-making and identification of the ideal patient for decompression vs. decompression and fusion. Our goal was to identify distinct DLS groups, aiming to inform clinical decision-making for decompression vs. decompression and fusion. Consensus cluster analysis was used based on demographic, clinical, and radiological characteristics of patients enrolled in the CSORN (Canadian Spine Outcomes and Research Network) prospective DLS study from 2015 to 2022 at eight Canadian sites. We selected clinically relevant variables to guide feature selection and evaluated the optimal number of clusters. Euclidean distance metric was used to determine the cluster number and structure, with up to seven clusters considered and 50 sampling iterations. Key characteristics of each cluster were identified, and post-surgical outcomes were compared using the Oswestry Disability Index (ODI) with pairwise statistical tests. Consensus cluster analysis of 486 DLS patient (mean [SD] age, 55.4 [9.2] years, 180 men [37%]) identified four distinct clusters. Cluster 1 (n=175) included patients with moderate disability, low comorbidity, low depression, and well-aligned spine. Cluster 2 (n=85) comprised predominantly female patients with severe disability, high comorbidity, high depression, and poor spine alignment. Cluster 3 (n=91) mainly consisted of male patients with moderate disability and malaligned spine, while Cluster 4 (n=135) included elderly patients with severe disability and relatively well-aligned spine. Clusters 1 and 3 showed the most favorable ODI outcomes at 1- and 2-years follow-up. Cluster 2 had the highest rate of fusion surgery (84%) and the greatest ODI change at 1 year (DODI mean [SD] 27.97 (19.32)). Decompression alone provided sustained benefit in Cluster 1 and 3, while improvement regressed in Cluster 2 and 4 at two years. Unsupervised machine learning identified four clinically distinct clusters of DLS patients with varying outcome and responses to surgical interventions, highlighting the importance of stratified care strategies to optimize patient outcomes.