Authors: Jetan Badhiwala, MD; Laureen Hachem, MD; Zamir Merali, MD; Christopher Witiw, MD, MS; Farshad Nassiri, MD; Muhammad Akbar, MD; Saleh Almenawer, MD; Markus Schomacher, MD; Jefferson Wilson, MD, PhD; Michael Fehlings, MD, PhD (Toronto, Canada)

Introduction: Patients with mild degenerative cervical myelopathy (DCM) represent a heterogeneous population, and indications for surgical decompression remain controversial. We sought to dissociate patient phenotypes within the broader population of mild DCM associated with degree of impairment in quality of life (QOL) and surgical outcomes. Methods: This was a post-hoc analysis of patients with mild DCM (mJOA 15-17) enrolled in the AOSpine CSM-NA/CSM-I studies. A k-means clustering algorithm was applied to baseline SF-36 scores to separate patients into two clusters based on pattern and degree of impairment in QOL. Baseline variables and surgical outcomes were compared between clusters. The primary outcome of interest was change in QOL (SF-36) at 1 year post-surgery compared to baseline. Secondary outcomes included change in mJOA, Nurick grade, NDI, and SF-6D scores. A k-nearest neighbors (kNN) algorithm was used to evaluate the ability to classify patients into the two clusters by significant baseline clinical variables. Results: One-hundred eighty-five patients were eligible. Two groups were generated by k-means clustering over baseline QOL (SF-36) scores. Cluster 1 (‘more impaired’) had a greater proportion of females (44% vs.28%, P=0.029) and symptoms of neck pain (32% vs. 11%, P=0.001), gait difficulty (57% vs. 40%, P=0.025), or weakness (75% vs. 59%, P=0.041). While baseline mJOA correlated with neither baseline QOL nor outcomes, Cluster 1 was associated with significantly greater improvement in disability (NDI) (P<0.01) and QOL (SF-36) (P<0.05) scores following surgery. A kNN algorithm could predict cluster classification with 71% accuracy by neck pain, motor symptoms, and gender alone. Conclusion: We have dissociated a distinct more impaired phenotype of patients with mild DCM, characterized by neck pain, motor symptoms, and female gender, in whom surgical intervention resulted in greater gains. Identification of patient-related predictive factors may help guide surgical decision-making and inform treatment paradigms for mild DCM.