Using AI, they predict the 10-year evolution of patients with multiple sclerosis with 90% accuracy.

Compilation
An AI model is already predicting the evolution of patients with multiple sclerosis 10 years ahead and he does it very accurately: achieves a confidence level close to 90%This is the result of a study that has just been published in Science Magazine Plos One in which the Santiago Health Research Institute (IDIS) and the Southern Galicia Health Research Institute (IIS Galicia Sur) participated.

The researchers extracted data from the first MRI scans of patients with multiple sclerosis from the neurology service of the Santiago de Compostela Clinical Hospital. A total of 1,000 patients were analyzed 446 records of affected people with at least one year of follow-up..

Researchers extract data from first MRI scans of multiple sclerosis patients in Galicia

This machine learning model predicts disability progression in patients based on baseline MRI and clinical assessments using the Expanded Disability Status Scale. “The job involves New models for describing patient progression using AI programs “which predict their trajectories using these descriptors, and also give us an idea of ​​what factors contribute to this evolution, such as age of onset or injury.”— explains Silvia Campagnioni, the first author of the work.

Among the most notable findings, the study found that “age of debut” is one of the most influential features for the developed regressor models. In addition, the number traumatic brain injury greater than or equal to nine In the original MRI, it was found to be the most influential variable in the classifier model’s decisions.

Roberto Agis: “We could obtain objective data and indicators of preventive measures that would help predict the therapeutic effectiveness of treatment”

“This work has significant impact not only in scientific and technical terms, but also in economic and social terms, as it affects health, quality of life and development cooperation.”points to IDIS researcher Roberto Agisthe last author of the project. “We could obtain objective data and indicators of preventive measures that would help predict the therapeutic effectiveness of treatment.”Explain.

The study will allow optimize the dosage of treatment multiple sclerosis in terms of dose and duration of treatment, and optimizing its use based on the profile of each patient or treatment, while improving the trajectory through the use of personalized ML predictors.

Research using artificial intelligence will allow the optimization of the dosage of MS treatments and their application depending on the profile of each patient or treatment method.

According to the findings of the research team, research using artificial intelligence (AI) has the potential to provide versatile and powerful tools for the treatment of multiple sclerosis. “Artificial intelligence technologies such as deep learning and machine learning may promote the integration of biological, psychological and social factors when addressing issues of prevention, diagnosis and treatment of multiple sclerosis, including other diseases”– explains Cesar Veiga.

Treatment decision making in multiple sclerosis continues to rely on the integration of the same patient demographic, clinical, and paraclinical variables observed many years ago, such as resonance imaging and the presence of oligoclonal bands. “Still There are many open problems in this area. and improvements are coming from several areas of convergence, such as the integration of datasets that can improve personalization and the predictive power of AI algorithms in healthcare.” points to ITEN IDIS band leader Jose Maria Prieto.

Jose Maria Prieto: “Integration of data sets that can improve personalization and predictive power of artificial intelligence algorithms in healthcare”

The 2020 Multiple Sclerosis Atlas shows that about 3,800 patients are diagnosed in Galicia and 55,000 in Spain. prevalence 75% among women and an average diagnosis of 32 years. It is one of the diseases with the highest prevalence in this autonomous community and is increasing worldwide.