Today’s article is about a groundbreaking study published in Nature Medicine in 2025:
“AI-driven reclassification of multiple sclerosis progression.”
It was led by an international research team including Habib Ganjgahi, Dieter Häring, Fred Lublin, Ludwig Kappos, Heinz Wiendl and many more experts. The analysis was based on data from over 8,000 patients, 118,000 clinical visits, and 35,000 MRI scans. This makes it one of the largest MS data evaluations ever done.
You are currently viewing a placeholder content from Default. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationTable of Contents
The traditional way of classifying MS
So far, multiple sclerosis has usually been divided into:
Relapsing-Remitting MS (RRMS) – relapses followed by more or less good recovery.
Secondary Progressive MS (SPMS) – steady worsening after a relapsing course.
Primary Progressive MS (PPMS) – continuous worsening from the beginning.
These categories are useful but mainly describe the disease from the outside. They don’t necessarily reflect what happens biologically in the central nervous system.
What the AI-driven study discovered
The research team applied artificial intelligence (AI), more precisely machine learning, to search for hidden patterns in patient data.
Instead of three rigid boxes, the AI revealed that MS can be described along four dimensions:
Physical disability – functional impact on daily life.
Brain damage – changes visible on MRI, like lesions or atrophy.
Relapses – acute worsening of symptoms.
Asymptomatic activity – MRI-visible inflammation without symptoms.
Key insight: MS is not three separate types. It is a continuum.
The four new meta-states of MS
Based on these dimensions, the AI proposed four meta-states:
Early / Mild / Evolving MS (EME) – low disability, minimal brain changes.
Asymptomatic activity – silent inflammation visible on MRI only.
Relapse – acute symptom worsening.
Advanced MS – higher disability, more brain damage, fewer chances to return.
Interestingly, patients rarely move directly from early to advanced MS. They usually pass through active stages first—either relapses or silent activity.
Why this matters for patients
- MS should be seen as a spectrum, not three distinct diseases.
- Invisible MRI activity can still drive progression. That’s why regular scans and treatment adjustments matter.
- Early, effective therapy helps keep patients longer in the EME phase.
- The traditional separation between SPMS and PPMS in advanced stages may lose its importance.
Links to further in-depth knowledge
If you want to go deeper:
Prof. Gavin Giovannoni explained the concept of smoldering MS in Episode 95. This highlights hidden disease activity that is not reflected by relapses alone.
Prof. Tjalf Ziemssen discussed future treatment strategies and precision medicine in Episode 50.
Both interviews fit perfectly with the findings of this AI study.
Conclusion
This reclassification of MS is not yet part of everyday clinical practice. But it offers a promising new framework for:
better patient management,
more personalized treatment,
and simplified drug development.
MS is complex—but with modern tools like AI, researchers and doctors are getting closer to understanding the real nature of the disease.
See you soon and try to make the best out of your life,
Nele
For more information and positive thoughts, subscribe to my newsletter for free.
Click here for an overview of all podcast episodes published so far.
And at many more places.
* This text contains affiliate links. This means that I get a small compensation if you buy the product recommended by me through the link. For you nothing changes in the price of the product. And it helps me to pay for the blog and to write new posts.
