AI predicts sclerosis progression with 90% accuracy in one examination
Forecast what to expect in ten years, with 90% accuracy and only based on some initial data, This is what the latest IDIS project in Santiago offers. patients with multiple sclerosis (MS). Key? A … exhaustive analysis and exploitation of the possibilities of artificial intelligence in the field of medicine and health care; and the team that carries out this task in their study is made up of researchers from IDIS and IIS Galicia Sur.
The cornerstone of this process, the data on which the program makes its calculations and predictions, is the data provided by the first MRI performed on a patient with multiple sclerosis. At first glance, the AI model uses Machine learning systems for predicting progress deterioration due to the disease, which affects almost 3,800 people in the Community, according to the 2020 MS Atlas.
“The work proposes new models to describe the progression of patients using artificial intelligence programs that predict their trajectories using these descriptors, and also gives us an idea of what factors contribute to said evolution, such as age of onset or injury,” explains Silvia Campanioni, first author of the work. It will thus be possible Optimize treatment precision, from dose to duration, and create personalized predictions. So far, the investigation has analyzed 446 records of victims from the Hospital Clínico de Santiago (CHUS) Neurology Service database.
As IDIS points out, the program understands the patient’s age of onset as one of the most influential factors in predicting its prognosis. And when classifying the condition by severity, pay special attention to whether the MRI reveals nine or more brain lesions. Roberto Agis, an IDIS researcher and the final author of the project, emphasizes the “impact” it will have “not only in scientific and technical terms, but also in economic and social terms, thanks to implications for health, quality of life and development cooperation. According to him, it is possible to collect “objective evidence” that will now determine the best possible preventive measures for each case and improve the effectiveness of treatment.
In conclusion, the authors argue that Proper use of AI can provide versatile and powerful tools for the treatment of multiple sclerosis. “Artificial intelligence technologies such as deep learning and machine learning can contribute to the integration of biological, psychological and social factors in the prevention, diagnosis and treatment of multiple sclerosis, including other diseases,” explains César Veiga, a researcher at IIS South Galicia.
The study involves the Translational Research Group of Neurological Diseases (ITEN) and the Neuroepigenetics Laboratory of IDIS; the Cardiovascular Research Group and the Artificial Intelligence Platform for Biomedical Analysis of IIS Galicia Sur; and the Neurology Service of CHUS.