Truace
Subscribe

Imaging subtypes reveal distinct biological substrates and disability profiles in multiple sclerosis

Multiple sclerosis is characterized by marked biological heterogeneity that is only partly captured by conventional clinical phenotypes and age-at-onset categories. MRI can detect focal lesions, diffuse microstructural damage and atrophy, but these measures are usually considered separately. We therefore aimed to use Subtype and Stage Inference (SuStaIn), an unsupervised machine learning framework, to identify biologically meaningful MRI subtypes of multiple sclerosis and determine their associations with disabi…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-1187· cite & verify
Imaging subtypes reveal distinct biological substrates and disability profiles in multiple sclerosis
Molecular-analysis-of-endothelial-progenitor-cell-(EPC)-subtypes-reveals-two-distinct-cell-1755-8794-3-18-S2 by Medina R, O'Neill C, Sweeney M, Guduric-Fuchs J, Gardiner T, Simpson D, Stitt A. CC BY 2.0 · https://creativecommons.org/licenses/by/2.0

In brief

Multiple sclerosis is characterized by marked biological heterogeneity that is only partly captured by conventional clinical phenotypes and age-at-onset categories. MRI can detect focal lesions, diffuse microstructural damage and atrophy, but these measures are usually considered separately.

We therefore aimed to use Subtype and Stage Inference (SuStaIn), an unsupervised machine learning framework, to identify biologically meaningful MRI subtypes of multiple sclerosis and determine their associations with disability, age at onset, cognition, genetic susceptibility to more severe disease, and relapse-independent progression. Cognitive testing was available in 501 patients, genetic profiling in 650, and longitudinal clinical follow-up in 645 (median follow-up=6.57 years).

Main points

  1. Multiple sclerosis is characterized by marked biological heterogeneity that is only partly captured by conventional clinical phenotypes and age-at-onset categories.
  2. MRI can detect focal lesions, diffuse microstructural damage and atrophy, but these measures are usually considered separately.
  3. We therefore aimed to use Subtype and Stage Inference (SuStaIn), an unsupervised machine learning framework, to identify biologically meaningful MRI subtypes of multiple sclerosis and determine their associations with disability, age at onset, cognition, genetic susceptibility to more severe disease, and relapse-independent progression.

The problem

Imaging subtypes reveal distinct biological substrates and disability profiles in multiple sclerosis: Cognitive performance and genetic risk scores for multiple sclerosis severity did not differ across subtypes, but within each subtype advancing SuStaIn stage was associated with worse global and domain-specific cognitive performance (all p≤0.030).

The rundown

We therefore aimed to use Subtype and Stage Inference (SuStaIn), an unsupervised machine learning framework, to identify biologically meaningful MRI subtypes of multiple sclerosis and determine their associations with disability, age at onset, cognition, genetic susceptibility to more severe disease, and relapse-independent progression. We applied SuStaIn to multimodal 3T brain MRI data from 1017 multiple sclerosis patients and 548 healthy controls.

Sources

  1. Peer-reviewedBrain2026-09-23

The debate