Scientists Identify Two Distinct Subtypes of Multiple Sclerosis
A recent study led by researchers at University College London (UCL) has revealed the presence of two distinct subtypes of multiple sclerosis (MS). This groundbreaking finding, if confirmed, could revolutionize the way doctors approach the diagnosis and treatment of MS patients.
The study utilized machine learning technology to analyze data from 634 patients enrolled in two clinical trials. Machine learning models are designed to detect subtle patterns that may not be readily apparent to human observers.
The data included blood tests to measure levels of a protein known as serum neurofilament light chain (sNfL), which serves as a biomarker for nervous system diseases like MS. Additionally, MRI scans were used to examine damage and other changes in the brain caused by MS, an autoimmune condition where the body attacks the protective covering of nerve cells.
Through the comparison of blood test results and MRI scans, the machine learning model successfully categorized patients into two distinct subtypes of MS.
The first subtype, referred to as “early-sNfL,” exhibited elevated levels of sNfL early on, along with damage to the corpus callosum, a brain structure that connects the two hemispheres. Patients in this group showed a more aggressive disease progression, developing brain lesions at a faster rate.
Conversely, the second subtype, labeled “late-sNfL,” progressed more slowly. These patients initially displayed shrinkage in the limbic cortex and deep grey matter of the brain, with sNfL levels increasing at a later stage.
Lead researcher Arman Eshaghi noted, “By utilizing an AI model in combination with a widely available blood marker and MRI, we have identified two distinct biological patterns of MS for the first time. This insight will enable clinicians to determine the disease stage of a patient and tailor their treatment accordingly.”
The machine learning model was trained on data from 189 patients with different types of MS and validated on 445 recently diagnosed patients. Neurofilaments are crucial proteins that support neurons in the nervous system, with elevated levels indicating neurodegeneration.
While sNfL levels in blood serum can be challenging to interpret, combining this data with MRI scans provides a more comprehensive understanding of MS progression. The researchers believe that this integrated approach enhances the diagnostic accuracy and treatment efficacy for MS patients.
The researchers concluded, “By incorporating sNfL, a reliable indicator of neuroaxonal injury, we have surpassed the limitations of MRI in providing a comprehensive view of MS pathology.”
Currently, MS diagnosis and treatment are primarily symptom-based, overlooking the underlying mechanisms of the disease. The innovative approach proposed in this study could lead to more personalized and effective treatment strategies for MS patients, pending further validation in future research.
The findings of this study were published in the journal Brain.
