Three new multiple sclerosis subtypes identified using AI
2021
University College London, London, United Kingdom
Multiple sclerosis (MS) can be divided into four phenotypes based on clinical evolution. The pathophysiological boundaries of these phenotypes are unclear, limiting treatment stratification. Machine learning can identify groups with similar features using multidimensional data. To classify MS subtypes based on pathological features, the artificial intelligence tool SuStaIn (Subtype and Stage Inference) was applied to MRI scans of the brain acquired in previously published studies. A training dataset from 6322 MS patients was analysed to define MRI-based subtypes and an independent cohort of 3068 patients was used for validation. Based on the earliest abnormalities, the authors define MS subtypes as cortex-led, normal-appearing white matter-led, and lesion-led. People with the lesion-led subtype have the highest risk of confirmed disability progression and the highest relapse rate. People with the lesion-led MS subtype show positive treatment response in selected clinical trials. The findings suggest that MRI-based subtypes predict MS disability progression and response to treatment and may be used to define groups of patients in interventional trials.
Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data
Arman Eshaghi
Added on: 04-15-2021
[1] https://www.nature.com/articles/s41467-021-22265-2[2] https://www.technologynetworks.com/neuroscience/news/three-new-multiple-sclerosis-subtypes-identified-using-ai-347414
