In June of 2016, The Michael J. Fox Foundation challenged data scientists and computational analysts to work with PPMI’s unprecedented collection of open-access clinical, molecular, and imaging data to answer two fundamental questions about Parkinson’s disease: what are the subtypes of the disease, and what baseline factors predict disease progression?
In total, forty researchers submitted models that answered the questions above; 2 researchers split the $50,000 cash prize. GE Healthcare, a PPMI industry partner, and the Fox Foundation each provided $25,000 for the prizes.
Duygu Tosun-Turgut, PhD, is an assistant professor of radiology and biomedical imaging at UC San Francisco and co-director of the Center for Imaging of Neurodegenerative Diseases at the San Francisco Veterans Affairs Health Care System. Dr. Tosun-Turgut’s findings suggest that, when analyzed together, diffusion tensor imaging (DTI) and Unified Parkinson’s Disease Rating Scale III (UPDRS) total score at baseline are the best factors to predict slow or fast disease progression.
Fei Wang, PhD, is an assistant professor of health care policy and research at Weill Cornell Medicine. Dr. Wang’s analysis led him to posit three main subgroups of Parkinson’s: (i) progression of both motor and cognitive dysfunction; (ii) progression of cognitive dysfunction but not motor progression; and (iii) progression of motor dysfunction but not cognitive progression.
“Identifying early clinical markers of rate of progression can benefit clinical care and testing of new therapies,” said Dr. Tosun-Turgut. Understanding Parkinson’s disease subtypes and predicting the disease’s progression is crucial in new drug development; these findings suggest that current clinical tools could be leveraged to do so. “Characterizing subgroups based on clinical symptoms may allow trial sponsors to test a new therapy, such as a cognition drug, in a subpopulation with greater need that is more likely to respond,” said Dr. Wang.
Both winners of the 2016 PPMI Data Challenge will present their findings in live webinar on Friday, February 24. The webinar is open to all – register here.