Machine Learning Helps Define New Subtypes of Parkinson’s Disease

Researchers at Weill Cornell Medicine used machine learning to identify three types of Parkinson's disease based on how quickly the disease progresses. These subtypes could help doctors diagnose and treat Parkinson's more effectively. The subtypes are: Inching Pace (PD-I): Slow progression and mild symptoms, affecting 36% of patients. Moderate Pace (PD-M): Moderate progression, affecting 51% of patients. Rapid Pace (PD-R): Fast progression with severe symptoms. They discovered distinct genetic markers for each subtype, which could lead to tailored treatments. For example, they found that the diabetes drug metformin might help patients, especially those with the rapid progression subtype, by improving cognitive symptoms and reducing falls. This research, if validated, could lead to personalized treatment plans and the repurposing of existing drugs to better manage Parkinson's disease.