Historically we have defined MS as relapsing and progressive but in the time of Boys with Toys and artificial intelligence there are moves to define MS Subtypes and this on using biomarkers in the form of neurofilament (NfL) as a marker of nerve damage and magnetic resonance imaging
Brummer T, Fleischer V. Beyond clinical labels: a molecular-structural framework for multiple sclerosis subtyping. Brain. 2025 Dec 4;148(12):4155-4157
“The early-sNfL subtype includes elevated NfL in tandem with lesion accrual and white matter disruption underscores the coupling of inflammation and axonal injury. Conversely, the late-sNfL groups early volumetric decline, prior to sNfL elevation, may reflect subclinical insidious neurodegeneration. These profiles are not simply different ‘stages’ but rather distinct pathways through which MS may progress”.
The early-sNfL group consists of younger people with more radiologically-active disease and better treatment responsiveness, consistent with an inflammatory-dominant phenotype. Conversely, patients in the late-sNfL subtype tend to be older, reflecting patterns of more silent MS progression”
Willard C, Puglisi L, Ravi D, Dmitrieva M, Mattiesing RM, Barkhof F, Alexander DC, Harlow DE, Piani-Meier D, Eshaghi A. Combined magnetic resonance imaging and serum analysis reveals distinct multiple sclerosis types. Brain. 2025 ;148(12):4578-4591. doi: 10.1093/brain/awaf331. PMID: 41325776.
Multiple sclerosis (MS) is a highly heterogeneous disease in its clinical manifestation and progression. Predicting individual disease courses is key for aligning treatments with underlying pathobiology. We developed an unsupervised machine learning model (AI) integrating MRI-derived measures with serum neurofilament light chain (sNfL) levels to identify biologically informed MS subtypes and stages. Using a training cohort of patients with relapsing-remitting and secondary progressive MS (n = 189), with validation on a newly diagnosed population (n = 445), we discovered two distinct subtypes defined by the timing of sNfL elevation and MRI abnormalities (early- and late-sNfL types). In comparison to MRI-only models, incorporating sNfL with MRI improved correlations of data-derived stages with the Expanded Disability Status Scale in the training and external test sets. The early-sNfL subtype showed elevated sNfL, corpus callosum injury and early lesion accrual, reflecting more active inflammation and neurodegeneration, whereas the late-sNfL group showed early volume loss in the cortical and deep grey matter volumes, with later sNfL elevation. Cross-sectional subtyping predicted longitudinal radiological activity: the early-sNfL group showed a 144% increased risk of new lesion formation compared with the late-sNfL group. Baseline subtyping, over …time, predicted treatment effect on new lesion formation ……in addition to treatment effects on brain atrophy. Integration of sNfL provides an improved framework in comparison to MRI-only subtyping of MS to stage disease progression and inform prognosis. Our model predicted treatment responsiveness in early, more active disease states. This approach offers a powerful alternative to conventional clinical phenotypes and supports future efforts to refine prognostication and guide personalized therapy in MS.
The dreaded P for predicted which… as ever means pants as the level of prediction is in my mind too weak as the levels of correlation are the usual stuff….which I personally think are not good enough to predict the course for individuals.. which is what we want.
COI: none
disclaimer my views
Source: multiple-sclerosis-research.org