TY - JOUR T1 - Crowdsourcing digital health measures to predict Parkinson’s disease severity: the <em>Parkinson’s Disease Digital Biomarker DREAM Challenge</em> JF - bioRxiv DO - 10.1101/2020.01.13.904722 SP - 2020.01.13.904722 AU - Solveig K. Sieberts AU - Jennifer Schaff AU - Marlena Duda AU - Bálint Ármin Pataki AU - Ming Sun AU - Phil Snyder AU - Jean-Francois Daneault AU - Federico Parisi AU - Gianluca Costante AU - Udi Rubin AU - Peter Banda AU - Yooree Chae AU - Elias Chaibub Neto AU - Ray Dorsey AU - Zafer Aydın AU - Aipeng Chen AU - Laura L. Elo AU - Carlos Espino AU - Enrico Glaab AU - Ethan Goan AU - Fatemeh Noushin Golabchi AU - Yasin Görmez AU - Maria K. Jaakkola AU - Jitendra Jonnagaddala AU - Riku Klén AU - Dongmei Li AU - Christian McDaniel AU - Dimitri Perrin AU - Nastaran Mohammadian Rad AU - Erin Rainaldi AU - Stefano Sapienza AU - Patrick Schwab AU - Nikolai Shokhirev AU - Mikko S. Venäläinen AU - Gloria Vergara-Diaz AU - Yuqian Zhang AU - the Parkinson’s Disease Digital Biomarker Challenge Consortium AU - Yuanjia Wang AU - Yuanfang Guan AU - Daniela Brunner AU - Paolo Bonato AU - Lara M. Mangravite AU - Larsson Omberg Y1 - 2020/01/01 UR - http://biorxiv.org/content/early/2020/01/16/2020.01.13.904722.abstract N2 - Mobile health, the collection of data using wearables and sensors, is a rapidly growing field in health research with many applications. Deriving validated measures of disease and severity that can be used clinically or as outcome measures in clinical trials, referred to as digital biomarkers, has proven difficult. In part due to the complicated analytical approaches necessary to develop these metrics. Here we describe the use of crowdsourcing to specifically evaluate and benchmark features derived from accelerometer and gyroscope data in two different datasets to predict the presence of Parkinson’s Disease (PD) and severity of three PD symptoms: tremor, dyskinesia and bradykinesia. 40 teams from around the world submitted features, and achieved drastically improved predictive performance for PD (best AUROC=0.87), as well as severity of tremor (best AUPR=0.75), dyskinesia (best AUPR=0.48) and bradykinesia (best AUPR=0.95). ER -