Artificial intelligence tool developed to predict multiple sclerosis patients' evolution

A study coordinated by Dr. Pablo Villoslada, director of the Neurosciences program at the Hospital del Mar Research Institute and head of the Neurology Department at the Hospital del Mar, has made it possible to develop a tool based on artificial intelligence to predict the evolution of people diagnosed with multiple sclerosis. The work is published in the Journal of Neurology and is the result of the Sys4MS project of the European Commission. The Hospital Clínic de Barcelona, the Charité University of Berlin in Germany, the Policlinic San Martino Hospital in Genoa, Italy, and the Oslo University Hospital in Norway have participated in the project.

To develop this tool, a group of more than 300 patients with multiple sclerosis and a hundred people free of the disease were followed for two years. During this period, their condition was comprehensively analyzed. They were evaluated on the basis of various clinical and cognitive scales, as well as with imaging tests (brain MRI and optical coherence tomography to analyze the state of the retina). They also underwent a complete analysis of their genetics, proteins and inflammatory cells present in their blood. The data obtained were validated with a second cohort of 271 people with multiple sclerosis.

High level of accuracy
The tool, developed with different approaches to artificial intelligence and learning from the data of the participants, achieves high levels of precision, especially in relation to those patients who will undergo changes in their condition and those who will have to change their treatment for others that are more effective. Dr. Villoslada explains that the work carried out "indicates that, through a detailed study of the patients and using artificial intelligence tools, we can profile which patients will be more active and, therefore, advise them, with more knowledge, on treatments that may have more side effects, but which can be more effective in controlling the disease".

Although it cannot yet be used in clinical practice, the results obtained in the development of this predictive tool can allow the teams that monitor people with multiple sclerosis "to have information to be able to decide and choose the best treatment, since the existing treatments at present have different levels of efficacy, but also of risk", points out the coordinator of the study, Dr. Villoslada. The study concludes that "the combination of clinical and MRI information is what most helps to predict the evolution of patients, and these are data that can be easily obtained in the healthcare setting," according to Dr. Sara Llufriu, a neurologist at the Neuroimmunology Unit of the Hospital Clínic de Barcelona, group leader at IDIBAPS and collaborator in the study. The researchers are already working to continue the work by extending the follow-up time of the patients to 7 years. A fact of great importance if we take into account that this is a pathology that mainly affects people under forty years of age, with a survival of about thirty years.

Multiple sclerosis is an autoimmune disease in which the immune system destroys the protective covering of nerve cells in the brain, optic nerve and spinal cord. It cannot be cured and causes disability to those who suffer from it. In Catalonia the prevalence is 123 cases per 100,000 inhabitants.

The study is also supported by the Sys4MS project of the Eracosysmed program of the European Commission and the Instituto de Salud Carlos III.

Image: Dr. Pablo Villoslada

Reference article: Andorra, M., Freire, A., Zubizarreta, I. et al. Predicting disease severity in multiple sclerosis using multimodal data and machine learning. J Neurol (2023). https://doi.org/10.1007/s00415-023-12132-z