Machine Learning Models to Aid Early Accurate Diagnosis of Multiple Sclerosis 

Machine learning models performed with sensitivity and specificity for distinguishing between the brains of people with and without multiple sclerosis (MS). These models were constructed using a medical device software program that computes volumetric brain measurement from MRIs (NeuroQuant 3.0; CorTechs Labs, San Diego, CA). An artificial intelligence (AI) algorithm was trained on MRIs analyzed by the software to create the models. Age-specific models found different key features enabling different precision and sensitivity performance for MS classification at different ages.. 
 
These data suggest that volumetric brain changes may provide a more detailed understanding of the effects and symptoms of MS as a disease, and could possibly be used for classifying stages of MS for clinical decision making. 

“We are dedicated to improving patient outcomes and up-leveling the standard of patient care through best in class clinical applications and patient-centric analysis and reporting,” said Chris Airriess, Ph.D., chief executive officer of CorTechs Labs. “Having a good friend with the disease, I have seen firsthand the impact MS can have on a person’s life. We work hard every day to provide software solutions to enable early, accurate diagnosis of MS to ultimately help patients get the treatment they need as soon as possible. The research being presented at ACTRIMS provides hope for furthering these advancements in the diagnosis and classification of MS.”

T1 MRI scans from 463 people with MS (102 men and 361 women) and 2,315 people (1,080 men and 1,235 women) without MS were evaluated with the software to generate brain volumetric information. The Random Forests algorithm was used to create machine learning models and brain structure volume normalized by intracranial volume was used as the initial input. Two-thirds of the data were used to train the algorithm and create the models and one-third was used to test the performance of the models. 

These data were presented at the Americas Committee for Treatment & Research in Multiple Sclerosis’ (ACTRIMS) 2020 annual forum February 27-29, 2020 in Palm Beach, FL.