Researchers use AI to study multiple sclerosis

Neurology researchers at Nottingham are studying how artificial intelligence could help plan treatment for people with multiple sclerosis.

Nikos Evangelou, Professor of Neurology at the University of Nottingham and Honorary Consultant Neurologist at Nottingham University Hospitals NHS Trust, said: “As part of the monitoring of patients with multiple sclerosis, we do a lot of MRI scans of the brain. Taken over the years Checking, measuring and comparing scans can take a long time. We hope that from this study we will learn how to use “state-of-the-art technology for automated scan reading” to help us treat our patients appropriately In which we need all the information.

They are working on the ASSISTMS study (Artificial Intelligence-Assisted Magnetic Resonance Imaging for Quality, Efficiency and Equity in NHS Care for Multiple Sclerosis) with Nottingham University Hospitals NHS Trust, Barts Health, AI company Iconometrics and Queen Mary University of London . by the AI ​​Award from the National Institute for Care and Health Research (NIHR).

The project is also supported by the East Midlands Imaging Network (EMRAD), InHealth Group and the MS Society of Great Britain and Northern Ireland.

The collaboration will investigate the impact of AI on MRI assessment and decision-making for multi-disciplinary team meetings for people with MS. Clinicians will be able to detect signs of disease activity faster and more effectively, enabling them to make quicker decisions about treatment.

AssistMS will focus on the reporting of MRI head by neuroradiologists in routine clinical practice. People with MS receiving disease-modifying treatments undergo annual MRIs of the central nervous system to monitor disease activity. This allows doctors to find out whether the treatment is working.

MRI is much more sensitive than clinical indices and early detection of disease activity may help replace DMTs such that MRI-detectable disease activity does not lead to clinical deterioration. However, the detection of subtle changes on MRI is often time-consuming, tedious, and thus prone to human error.