Moderate evidence
More
AI finds distinct subtypes of multiple sclerosis in brain scans of 1017 patients
Study title: Imaging subtypes reveal distinct biological substrates and disability profiles in multiple sclerosis
- Evidence type
- Observational study
- Sample
- n = 501
- Sources
- 1 sourcePeer-reviewed
- Published
- 1 min read
- Truvace record
- TRV-2026-1187cite or check it
Study title: 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.
Read the study abstract
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…
The gain
Within each MRI subtype, advancing SuStaIn stage was associated with worse cognitive performance, showing the ML staging captures cognitive decline, though cognition and genetic risk did not differ across subtypes.
In brief
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
- 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.
The full story
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. We applied SuStaIn to multimodal 3T brain MRI data from 1017 multiple sclerosis patients and 548 healthy controls.
Sources
1 on file- Braindoi:10.1093/brain/awag320
ace
What readers say