Phenotypic Diversity in Multiple Sclerosis Can Be Represented by Four Additive Symptom Modules

Background: Multiple sclerosis (MS) lacks a single invariant phenotypic core. Patients accumulate heterogeneous combinations of sensory, motor, cognitive, and autonomic impairments over time, reflecting lesions disseminated in time and space. Methods: We analyzed 4,617 de-identified neurology progress notes from 578 patients with MS at a single academic medical center. A large language model (GPT-5.2) categorized each note with respect to 17 non-mutually exclusive neurological phenotype features, and note-level features were aggregated into patient-level binary phenotype vectors. Non-negative matrix factorization (NMF) was applied to generate 2-, 3-, 4-, and 5-module solutions. For each rank, we calculated relative reconstruction error and module-level feature loadings. In the preferred 4-module solution, we derived patient-level module percentages, identified highly dominant (greater than 55%), near-pure (greater than 70%), and pure single-module profiles, and quantified admixture using Shannon entropy and the effective number of modules. Results: The 4-module solution was the most clinically interpretable. The four latent modules were sensory-visual-pain, ataxic-spastic-falls, cognitive-psychologic-fatigue, and autonomic-bladder-bowel, aligning closely with established functional systems in MS. By module dominance, 244 were considered sensory-visual-pain dominant, 128 ataxic-spastic-falls dominant, 138 autonomic-bladder-bowel dominant, and 68 cognitive-psychologic-fatigue dominant. Most patients exhibited admixed phenotypes, with the effective number of modules spanning approximately 1 to 4. Using pre-specified thresholds, 154 patients (26.6%) were highly dominant in a single module, 72 (12.5%) were near-pure, and 7 patients had pure single-module profiles. Purer phenotypes were predominantly sensory-visual-pain dominant. Conclusions: MS phenotypic diversity in routine clinical practice can be parsimoniously represented as mixtures of four latent symptom modules rather than as positions along a single severity axis. Most patients show substantial admixture of sensory, motor, cognitive, and autonomic involvement, but a minority exhibit relatively pure or strongly dominant module patterns. This modular representation provides an interpretable framework for quantifying MS phenotype and for generating testable hypotheses about biologically meaningful MS subtypes.