Machine learning-based cluster analysis identi fi es four unique phenotypes of patients with degenerative cervical myelopathy with distinct clinical pro fi les and long-term functional and neurological outcomes

Background Degenerative cervical myelopathy (DCM), the predominant cause of spinal cord dysfunction among adults, exhibits diverse interrelated symptoms and signi fi cant heterogeneity in clinical presentation. This study sought to use machine learning-based clustering algorithms to identify distinct patient clinical pro fi les and functional trajectories following surgical intervention. Methods In this study, we applied k-means and latent pro fi le analysis (LPA) to identify patient phenotypes, using aggregated data from three major DCM trials. The combination of Nurick score, NDI (neck disability index), neck pain, as well as motor and sensory scores facilitated clustering. Goodness-of- fi t indices were used to determine the optimal cluster number. ANOVA and post hoc Tukey ' s test assessed outcome differences, while multinomial logistic regression identi fi ed signi fi cant predictors of group membership. Findings A total of 1047 patients with DCM (mean [SD] age: 56.80 [11.39] years, 411 [39%] females) had complete one year outcome assessment post-surgery. Latent pro fi le analysis identi fi ed four DCM phenotypes: " severe multimodal impairment " (n = 286), " minimal impairment " (n = 116), " motor-dominant " (n = 88) and " pain-dominant " (n = 557) groups. Each phenotype exhibited a unique symptom pro fi le and distinct functional recovery trajectories. The " severe multimodal impairment group " , comprising frail elderly patients, demonstrated the worst overall outcomes at one year (SF-36 PCS mean [SD]: 40.01 [9.75]; SF-36 MCS mean [SD], 46.08 [11.50]) but experienced substantial neurological recovery post-surgery ( Delta mJOA mean [SD]: 3.83 [2.98]). Applying the k-means algorithm yielded a similar four-class solution. A higher frailty score and positive smoking status predicted membership in the " severe multimodal impairment " group (OR 1.47 [95% CI 1.07 - 2.02] and 1.58 [95% CI 1.25 - 1.99, respectively]), while undergoing anterior surgery and a longer symptom duration were associated with the " pain-dominant " group (OR 2.0 [95% CI 1.06 - 3.80] and 3.1 [95% CI 1.38 - 6.89], respectively). Interpretation Unsupervised learning on multiple clinical metrics predicted distinct patient phenotypes. Symptom clustering offers a valuable framework to identify DCM subpopulations, surpassing single patient reported outcome measures like the mJOA. Funding No funding was received for the present work. The original studies were funded by AO Spine North America. Copyright (c) 2024 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).