Scientists have made a significant breakthrough in understanding multiple sclerosis (MS), potentially leading to more effective treatments. A team of researchers employed artificial intelligence (AI) to analyze brain scans and assess blood markers for nerve cell injury, uncovering two distinct sub-types of the condition. This advancement could enhance personalized treatment strategies for the millions affected by MS globally.
The study, conducted by experts from the University College London (UCL) and published in the journal Brain in March 2024, focused on the serum neurofilament light chain (sNfL) as a crucial biomarker. By evaluating the sNfL levels in 634 patients diagnosed with MS, the researchers identified two biologically informed sub-types: early-sNfL and late-sNfL. These new classifications provide insight into the varying progression of the disease among individuals.
New Insights into MS Progression
Patients categorized under the early-sNfL sub-type exhibited elevated levels of the blood biomarker early in their disease course. This increase was associated with damage to the corpus callosum, a brain region vital for cognitive function and movement coordination. Conversely, the late-sNfL sub-type demonstrated a delayed rise in sNfL, accompanied by early volume loss in critical brain areas, including cortical and deep grey matter.
Lead author of the study, Dr. Arman Eshaghi, affiliated with the UCL Queen Square Institute of Neurology and the UCL Hawkes Institute, emphasized the implications of these findings for MS treatment. He stated, “Using routine brain images and a blood marker of nerve-cell injury, we identified two distinct biological trajectories in multiple sclerosis. This helps explain why people living with MS can follow different paths and it’s a step toward more personalized monitoring and treatment.”
The current classification of MS, which includes relapsing-remitting, secondary progressive, and primary progressive forms, often fails to account for the biological variations among patients. This new research aims to refine the understanding and definition of MS types, potentially leading to improved treatment outcomes.
Pathway to Personalized Treatment
The implications of this study extend beyond academic interest. According to Caitlin Astbury, senior research communications manager at the MS Society, the use of machine learning to analyze MRI and biomarker data represents a significant advancement in MS research. Astbury noted, “Over recent years, we’ve developed a better understanding of the biology of the condition. But, currently, definitions are based on the clinical symptoms a person experiences.”
She further explained that the complexity of MS often leads to oversimplified classifications, which can hinder effective treatment. “The more we learn about the condition, the more likely we will be able to find treatments that can stop disease progression,” Astbury added.
As research continues to evolve, this study highlights the promise of using advanced technology and biological markers to deepen the understanding of MS. The goal remains to transform how this complex neurological condition is treated, ultimately improving the quality of life for those affected.
