Scientists from University College London (UCL) have found three new multiple sclerosis (MS) subtypes – by using artificial intelligence (AI).
Researchers wanted to find out if there were patterns in brain images that could help guide MS treatment choices and identify patients with the best chance of responding to specific therapies.
To achieve this they applied the UCL-developed AI tool, SuStaIn (Subtype and Stage Inference), to the MRI brain scans of 6,322 MS patients. According to the University, the unsupervised SuStaIn trained itself and identified three previously unknown patterns – which became known as the new subtypes called ‘cortex-led’, ‘normal-appearing white matter-led’, and ‘lesion-led.’
After completing its analysis on the training MRI dataset, SuStaIn was ‘locked’ and then used to ‘identify the three subtypes in a separate independent cohort’ of 3,068 patients, for validation purposes.
It’s hoped the breakthrough will help identify those ‘more likely to have disease progression’ and ‘target treatments more effectively’. According to UCL, researchers say ‘the findings suggest that MRI-based subtypes predict MS disability progression and response to treatment’ and can now be used to ‘define groups of patients in interventional trials’ – although further research and clinical trials are required to confirm the findings.
The study’s lead author Dr Arman Eshaghi, from the UCL Queen Square Institute of Neurology, said: “Currently MS is classified broadly into progressive and relapsing groups, which are based on patient symptoms; it does not directly rely on the underlying biology of the disease, and therefore cannot assist doctors in choosing the right treatment for the right patients.
“Here, we used artificial intelligence and asked the question: can AI find MS subtypes that follow a certain pattern on brain images? Our AI has uncovered three data-driven MS subtypes that are defined by pathological abnormalities seen on brain images.
“While further clinical studies are needed, there was a clear difference, by subtype, in patients’ response to different treatments and in accumulation of disability over time. This is an important step towards predicting individual responses to therapies.”
Professor Alan Thompson, Dean of the UCL Faculty of Brain Sciences, added: “With the help of AI and large datasets, we have made the first step towards a better understanding of the underlying disease mechanisms which may inform our current clinical classification. This is a fantastic achievement and has the potential to be a real game-changer, informing both disease evolution and selection of patients for clinical trials.”
According to UCL study, MS affects over 2.8 million people globally. While the MS Society and Public Health England report that there are currently over 130,000 people in the UK with the condition and 7,000 being newly diagnosed every year.
The full paper – ‘Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data’ – is now published in Nature Communications and available to read online.
As well as in important research and disease detection, HTN has previously covered how AI is currently being applied in a broad range of areas – from ophthalmology and colonoscopies through to drug creation. Read some of the other case studies we’ve found so far in our three-part series: the diverse applications of AI in healthcare.