npj Digital Medicine (Mar 2021)
Crowdsourcing digital health measures to predict Parkinson’s disease severity: the Parkinson’s Disease Digital Biomarker DREAM Challenge
- Solveig K. Sieberts,
- Jennifer Schaff,
- Marlena Duda,
- Bálint Ármin Pataki,
- Ming Sun,
- Phil Snyder,
- Jean-Francois Daneault,
- Federico Parisi,
- Gianluca Costante,
- Udi Rubin,
- Peter Banda,
- Yooree Chae,
- Elias Chaibub Neto,
- E. Ray Dorsey,
- Zafer Aydın,
- Aipeng Chen,
- Laura L. Elo,
- Carlos Espino,
- Enrico Glaab,
- Ethan Goan,
- Fatemeh Noushin Golabchi,
- Yasin Görmez,
- Maria K. Jaakkola,
- Jitendra Jonnagaddala,
- Riku Klén,
- Dongmei Li,
- Christian McDaniel,
- Dimitri Perrin,
- Thanneer M. Perumal,
- Nastaran Mohammadian Rad,
- Erin Rainaldi,
- Stefano Sapienza,
- Patrick Schwab,
- Nikolai Shokhirev,
- Mikko S. Venäläinen,
- Gloria Vergara-Diaz,
- Yuqian Zhang,
- the Parkinson’s Disease Digital Biomarker Challenge Consortium,
- Yuanjia Wang,
- Yuanfang Guan,
- Daniela Brunner,
- Paolo Bonato,
- Lara M. Mangravite,
- Larsson Omberg
Affiliations
- Solveig K. Sieberts
- Sage Bionetworks
- Jennifer Schaff
- Elder Research, Inc
- Marlena Duda
- Department of Computational Medicine and Bioinformatics, University of Michigan
- Bálint Ármin Pataki
- Department of Physics of Complex Systems, ELTE Eötvös Loránd University
- Ming Sun
- Google Inc
- Phil Snyder
- Sage Bionetworks
- Jean-Francois Daneault
- Dept of PM&R, Harvard Medical School, Spaulding Rehabilitation Hospital
- Federico Parisi
- Dept of PM&R, Harvard Medical School, Spaulding Rehabilitation Hospital
- Gianluca Costante
- Dept of PM&R, Harvard Medical School, Spaulding Rehabilitation Hospital
- Udi Rubin
- Early Signal Foundation, 311 W 43rd Street
- Peter Banda
- Luxembourg Centre for Systems Biomedicine, University of Luxembourg
- Yooree Chae
- Sage Bionetworks
- Elias Chaibub Neto
- Sage Bionetworks
- E. Ray Dorsey
- Center for Health + Technology, University of Rochester
- Zafer Aydın
- Department of Electrical and Computer Engineering, Abdullah Gul University
- Aipeng Chen
- Prince of Wales Clinical School, UNSW Sydney
- Laura L. Elo
- Turku Bioscience Centre, University of Turku and Åbo Akademi University, Tykistökatu 6
- Carlos Espino
- Early Signal Foundation, 311 W 43rd Street
- Enrico Glaab
- Luxembourg Centre for Systems Biomedicine, University of Luxembourg
- Ethan Goan
- School of Electrical Engineering and Robotics, Queensland University of Technology
- Fatemeh Noushin Golabchi
- Dept of PM&R, Harvard Medical School, Spaulding Rehabilitation Hospital
- Yasin Görmez
- Department of Electrical and Computer Engineering, Abdullah Gul University
- Maria K. Jaakkola
- Turku Bioscience Centre, University of Turku and Åbo Akademi University, Tykistökatu 6
- Jitendra Jonnagaddala
- School of Public Health and Community Medicine, UNSW Sydney
- Riku Klén
- Turku Bioscience Centre, University of Turku and Åbo Akademi University, Tykistökatu 6
- Dongmei Li
- Clinical and Translational Science Institute, University of Rochester Medical Center
- Christian McDaniel
- Artificial Intelligence, University of Georgia
- Dimitri Perrin
- School of Computer Science, Queensland University of Technology
- Thanneer M. Perumal
- Sage Bionetworks
- Nastaran Mohammadian Rad
- Institute for Computing and Information Sciences, Radboud University
- Erin Rainaldi
- Verily Life Sciences, 269 East Grand Ave
- Stefano Sapienza
- Dept of PM&R, Harvard Medical School, Spaulding Rehabilitation Hospital
- Patrick Schwab
- Institute of Robotics and Intelligent Systems, ETH Zurich
- Nikolai Shokhirev
- Early Signal Foundation, 311 W 43rd Street
- Mikko S. Venäläinen
- Turku Bioscience Centre, University of Turku and Åbo Akademi University, Tykistökatu 6
- Gloria Vergara-Diaz
- Dept of PM&R, Harvard Medical School, Spaulding Rehabilitation Hospital
- Yuqian Zhang
- School of Biomedical Engineering, Shanghai Jiao Tong University
- the Parkinson’s Disease Digital Biomarker Challenge Consortium
- Yuanjia Wang
- Department of Biostatistics, Mailman School of Public Health, Columbia University
- Yuanfang Guan
- Department of Computational Medicine and Bioinformatics, University of Michigan
- Daniela Brunner
- Early Signal Foundation, 311 W 43rd Street
- Paolo Bonato
- Dept of PM&R, Harvard Medical School, Spaulding Rehabilitation Hospital
- Lara M. Mangravite
- Sage Bionetworks
- Larsson Omberg
- Sage Bionetworks
- DOI
- https://doi.org/10.1038/s41746-021-00414-7
- Journal volume & issue
-
Vol. 4,
no. 1
pp. 1 – 12
Abstract
Abstract Consumer wearables and sensors are a rich source of data about patients’ daily disease and symptom burden, particularly in the case of movement disorders like Parkinson’s disease (PD). However, interpreting these complex data into so-called digital biomarkers requires complicated analytical approaches, and validating these biomarkers requires sufficient data and unbiased evaluation methods. 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 PD and severity of three PD symptoms: tremor, dyskinesia, and bradykinesia. Forty teams from around the world submitted features, and achieved drastically improved predictive performance for PD status (best AUROC = 0.87), as well as tremor- (best AUPR = 0.75), dyskinesia- (best AUPR = 0.48) and bradykinesia-severity (best AUPR = 0.95).
