Use of Artificial Intelligence for Prognosis, Monitoring, and Treatment of Multiple Sclerosis

Multiple sclerosis (MS) is a complex autoimmune disease that primarily affects the central nervous system. Affecting around 2.8 million people worldwide, MS is a very variable disease, stemming from different causes and having several different subtypes. This variability is what makes prognosis and personalized treatment very difficult for doctors. However, recent developments using artificial intelligence (AI), such as deep learning (DL) and machine learning (ML) models, have been made by researchers attempting to utilize large sets of data to find patterns in patients affected by MS. These models then have the potential to be used to help with prediction of the disease course for a particular patient and help treat them for their specific subtype and issue. This review provides an overview of multiple studies in the field of AI in MS, as well as the current challenges and the future potential of the matter. Topics addressed include the use of AI in prognosis, subtype identification, brain atrophy analysis, and treatment decision optimization. When applied in real-world clinical practice, AI has the potential to use specific patient data to accurately predict the disease course and therefore create an optimal treatment plan for any patient. However, shortcomings such as quality of data, understanding of models, and clinical validation need to be addressed to fully reap the benefits of AI.