AI Used to Identify 3 MS Subtypes

Currently, multiple sclerosis (MS), an autoimmune and neurological disorder, is considered either progressive or relapsing-remitting. But could there be additional subtypes? According to new research, yes. As explained in Medical XPress, researchers and scientists from UCL wanted to explore the underlying biology of MS to determine if there were any neurological patterns that could aid with better diagnosis, treatment, and disease management. Using artificial intelligence (AI), the research team discovered and identified 3 additional subtypes of MS. Check out the full findings published in Nature Communications.

Artificial Intelligence (AI)

According to BuiltIn, artificial intelligence (AI) is a:

wide-ranging branch of computer science concerned with building smart machines capable of performing tasks that typically require human intelligence.

In this case, researchers used SuStaIn, a tool specifically developed by UCL. The researchers asked the AI program whether it could identify certain MS subtypes using specific patterns and abnormalities found on brain imagery. Overall, researchers believed that this could assist in providing patients with better and more targeted treatment and management options. Currently, treatments and guidance are given based on symptoms, clinical observations, and MRI-sourced brain images.

Altogether, researchers sourced brain scans from 6,322 patients with multiple sclerosis. After giving this to the SuStaIn AI system, the program trained itself on the neurological imagery. Next, the program was able to identify three new patterns on the images that had not previously been discovered by scientists. Once it identified these patterns, researchers applied the AI program to more data sourced from 3,068 patients with MS. Again, the technology was able to identify the newly discovered subtypes.

MS Subtypes

So what were the newly discovered subtypes? According to the research, the subtypes were considered:

  • Cortex-led.
  • Lesion-led.
  • Normal-appearing white matter-led.

These refer to what part of the brain was being affected by MS, where the disease was developing, and how the earliest neurological abnormalities appeared.

Additional research highlighted how patients with various subtypes responded differently to MS treatment options. Now, researchers are aware that different treatments could be more effective for patients with varied subtypes. Using AI to identify these differences, and finding ways to evaluate treatment options for these subtypes within clinical trials, would be the ideal next step.

Multiple Sclerosis (MS)

Although multiple sclerosis (MS) has no known cause, many doctors consider it to be an autoimmune disorder. In MS, the immune system mistakenly attacks myelin, or the protective coating of nerve cells. While MS typically appears between ages 15-60, it is most common between ages 20-50. Females are 2x more likely to develop MS than males.

As described above, there have historically been two main forms of MS. In progressive MS, the condition progresses without any periods of remission (without symptoms). Alternately, patients with relapsing and remitting MS experience symptomatic periods as well as periods of remission. Symptoms vary from patient to patient. However, symptoms may include:

  • Fatigue
  • Loss of balance and coordination
  • Blurry or double vision
    • Note: In some cases, MS may result in vision loss.
  • Weakness or numbness throughout the body
  • Muscle stiffness and/or muscle spasms
  • Changes in gait
  • Diarrhea or constipation
  • Frequent urination
  • Changes in mood or behavior
  • Difficulty breathing or swallowing
Jessica Lynn

Jessica Lynn

Jessica Lynn has an educational background in writing and marketing. She firmly believes in the power of writing in amplifying voices, and looks forward to doing so for the rare disease community.

Share this post

Share on facebook
Share on twitter
Share on linkedin
Share on pinterest
Share on print
Share on email