Scientists at the University of California Los Angeles have used artificial intelligence (AI) to identify three new subtypes of multiple sclerosis.
The researchers say their findings will help identify those people who are more likely to have progression of the disease and help predict treatment more effectively.
In their new work, the researchers wanted to find out if there were any as yet unidentified patterns in brain images that would best guide treatment choices and identify patients who would respond best to a particular therapy.
Currently, multiple sclerosis is broadly classified into progressive and recurrent groups based on the patient’s symptoms.
The authors decided to use AI to search for subtypes of multiple sclerosis: the algorithm found three subtypes, which are determined by pathological abnormalities observed in images of the brain. All three are among the earliest abnormalities seen on MRI scans within each pattern.
Scientists believe this is an important step in predicting individual responses to therapy.