For the first time, UCL researchers have used AI to identify two biologically distinct forms of MS, supporting the potential for more personalised care and improved treatment decisions for patients worldwide
A study led by University College London has used artificial intelligence to reveal two biologically distinct forms of multiple sclerosis (MS). By combining routine MRI brain scans with a simple blood biomarker test, the team used a machine learning model to identify early‑sNfL and late‑sNfL MS subtypes, highlighting differences in disease progression that had previously been invisible.
Published in Brain, this research has the potential to transform diagnosis, enable more personalised treatments, and help clinicians better predict the disease course for people living with MS globally.
Rethinking MS subtypes: Why biology matters
The researchers used data from 634 participants across two clinical trial groups, revealing two distinct forms of MS:
- Early-sNfL: These patients had elevated sNfL levels early in the disease, along with visible corpus callosum damage. They also developed brain lesions (damaged areas) quickly. This type appears to be more aggressive and active.
- Late-sNfL: These patients showed brain shrinkage in areas such as the limbic cortex and deep grey matter before sNfL levels rose (so the disease had progressed much further). This type seems slower, with overt damage occurring later.
This approach may help doctors more accurately identify which patients are at higher risk of developing new brain lesions.
Lead author of the study, Dr Arman Eshaghi (UCL Queen Square Institute of Neurology and UCL Hawkes Institute in UCL Computer Science) said: “MS is not one disease and current subtypes fail to describe the underlying tissue changes, which we need to know to treat it.
“By using an AI model combined with a highly available blood marker with MRI, we have been able to show two clear biological patterns of MS for the first time. This will help clinicians understand where a person sits on the disease pathway and who may need closer monitoring or earlier, targeted treatment.”
How AI and Big Data are changing MS research
Nearly 3 million people worldwide are living with multiple sclerosis (MS), a disease that often strikes young adults and can cause significant disability early in life. Traditionally, clinicians have classified MS based on how symptoms progress, but these categories do not reflect the underlying biological causes, leading to a disconnect between diagnosed types and the actual disease mechanisms. As a result, treatments chosen based on symptoms and disease course may not be effective because they fail to target the disease’s underlying biological mechanisms.
Queen Square Analytics (QSA), a UCL spinout, leveraged large datasets and artificial intelligence to uncover patterns in MS subtypes that had previously gone unnoticed. These data-driven subtypes can be paired with therapies that directly address the underlying biological changes, allowing for more effective treatment choices. Since changes in brain imaging and blood biomarkers appear before clinical symptoms worsen, these insights now empower clinicians to better predict and potentially prevent disability progression.
