Parkinson’s disease is notoriously difficult to diagnose because it relies primarily on the appearance of motor symptoms such as tremors, stiffness and slowness that often appear several years after the disease onset. An artificial intelligence (AI) model developed by a PhD student and postdoc at MIT promises to improve diagnoses by assessing whether or not someone has Parkinson’s from their nocturnal breathing. Read this blog for an overview of the work and the important implications for Parkinson’s drug development and clinical care.