Artificial Intelligence Identifies Novel Multiple Sclerosis Subtypes

A new study published in Nature Communications used artificial intelligence (AI) to identify 3 new multiple sclerosis (MS) subtypes, which may help identify which individuals are more likely to have disease progression, according to the authors. Further, these new subtypes could assist in more effective targeted treatments.

MS is a neurological condition that arises when the immune system mistakenly attacks the myelin sheaths that wrap around nerves in the brain and spinal cord, resulting in the disruption of electrical signals in the nervous system. It is classified as either relapsing MS, in which nerves are damaged, repaired, and damaged again, or progressive MS, in which nerve damage is continual and unrecovered, resulting in worsening disability.

“Currently MS is classified broadly into progressive and relapsing groups, which are based on patient symptoms; it does not directly rely on the underlying biology of the disease, and therefore cannot assist doctors in choosing the right treatment for the right patients,” said study lead author Arman Eshaghi, PhD, MD, in a press release. “Here, we used artificial intelligence and asked the question: can AI find MS subtypes that follow a certain pattern on brain images? Our AI has uncovered 3 data-driven MS subtypes that are defined by pathological abnormalities seen on brain images.”

Researchers used the AI tool Subtype and Stage Inference (SuStaIn) to scan the MRI brain scans of 6322 patients with MS, letting SuStaIn train itself unsupervised. The AI identified 3 previously unknown patterns, which were defined as “cortex-led,” “normal-appearing white matter-led,” and “lesion-led,” referring to the earliest abnormalities seen on the MRI scans in each pattern. After these initial scans, SuStaIn was then locked and used to identify the 3 subtypes in a separate independent cohort of 3068 patients in order to validate its ability to detect the new MS subtypes.

“We did a further retrospective analysis of patient records to see how people with the newly identified MS subtypes responded to various treatments,” Eshaghi said in the release. “While further clinical studies are needed, there was a clear difference, by subtype, in patients' response to different treatments and in accumulation of disability over time. This is an important step towards predicting individual responses to therapies.”

The results of the study suggest that MRI-based subtypes can be used to predict MS disability progression and response to treatment and can now be used to define groups of patients in interventional trials, according to the researchers. Clinical trials are required in order to confirm these findings.

REFERENCE

New multiple sclerosis subtypes identified using artificial intelligence [news release]. EurekAlert; April 6, 2021. Accessed April 8, 2021. https://www.eurekalert.org/pub_releases/2021-04/ucl-nms040621.php