Helmholtz Gemeinschaft

Search
Browse
Statistics
Feeds

Crowdsourcing digital health measures to predict Parkinson's disease severity: the Parkinson's Disease Digital Biomarker DREAM Challenge

[img]
Preview
PDF (Original Article) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB
[img] Other (Supplementary Material)
1MB

Item Type:Article
Title:Crowdsourcing digital health measures to predict Parkinson's disease severity: the Parkinson's Disease Digital Biomarker DREAM Challenge
Creators Name:Sieberts, S.K. and Schaff, J. and Duda, M. and Pataki, B.Á. and Sun, M. and Snyder, P. and Daneault, J.F. and Parisi, F. and Costante, G. and Rubin, U. and Banda, P. and Chae, Y. and Chaibub Neto, E. and Dorsey, E.R. and Aydın, Z. and Chen, A. and Elo, L.L. and Espino, C. and Glaab, E. and Goan, E. and Golabchi, F.N. and Görmez, Y. and Jaakkola, M.K. and Jonnagaddala, J. and Klén, R. and Li, D. and McDaniel, C. and Perrin, D. and Perumal, T.M. and Rad, N.M. and Rainaldi, E. and Sapienza, S. and Schwab, P. and Shokhirev, N. and Venäläinen, M.S. and Vergara-Diaz, G. and Zhang, Y. and Wang, Y. and Guan, Y. and Brunner, D. and Bonato, P. and Mangravite, L.M. and Omberg, L.
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).
Source:NPJ Digital Medicine
ISSN:2398-6352
Publisher:Springer
Volume:4
Number:1
Page Range:53
Date:19 March 2021
Additional Information:Wolfgang Kopp is a member of the Parkinson’s Disease Digital Biomarker Challenge Consortium.
Official Publication:https://doi.org/10.1038/s41746-021-00414-7
PubMed:View item in PubMed

Repository Staff Only: item control page

Downloads

Downloads per month over past year

Open Access
MDC Library