A significant advancement in understanding multiple sclerosis (MS) has emerged with the identification of two new sub-types of the disease. Researchers utilized artificial intelligence (AI) to analyze brain scans and blood markers, offering fresh insights that could lead to more effective treatments. This study, involving 634 MS patients, was conducted by experts from Queen Square Analytics and University College London.
The research revealed two distinct “biologically informed MS sub-types.” The first, named ‘early-sNfL’, demonstrated elevated levels of the serum neurofilament light chain (sNfL) early in the disease progression. This sub-type was associated with damage to the corpus callosum, a critical brain region responsible for thought, memory, and movement coordination. The second sub-type, termed ‘late-sNfL’, exhibited a delayed increase in sNfL, correlated with early volume loss in both cortical and deep grey matter regions.
Dr. Arman Eshaghi, lead author of the study from the UCL Queen Square Institute of Neurology and UCL Hawkes Institute, emphasized the implications of the findings. “Using routine brain images and a blood marker of nerve-cell injury, we identified two distinct biological trajectories in multiple sclerosis,” he stated. This advancement not only clarifies why individuals with MS experience varied disease pathways but also moves towards more personalized monitoring and treatment options.
Current classifications of MS—relapsing-remitting, secondary progressive, and primary progressive—often fall short of capturing the complexities of the disease, according to Dr. Eshaghi. “This work is helping to change our understanding and definition of MS types and their treatment in the near future,” he added.
The impact of MS on individuals can be profound, affecting the brain and spinal cord. In this condition, the protective membrane surrounding nerve cells becomes damaged, leading to symptoms such as fatigue, pain, muscle spasms, and difficulties with mobility.
Caitlin Astbury, senior research communications manager at the MS Society, noted the importance of this study in the context of evolving understandings of MS. She highlighted that the research employed machine learning to analyze MRI and biomarker data from patients with both relapsing-remitting and secondary progressive forms of the disease. “By combining this data, they were able to identify two new biological subtypes of MS,” Astbury explained.
In recent years, there has been a growing understanding of the biological basis of MS. Despite this progress, current definitions often rely on clinical symptoms, which can lead to treatment challenges. “MS is complex, and these categories do not always accurately reflect what is occurring in the body,” Astbury said. She expressed optimism regarding the future, stating, “The more we learn about the condition, the more likely we will be able to find treatments that can stop disease progression.”
This research, published in the journal Brain, underscores the potential of AI and advanced analytical techniques in reshaping the landscape of MS treatment and management. As scientists continue to explore the intricacies of this condition, the hope for more tailored therapies grows stronger, promising a brighter future for those affected by multiple sclerosis.
