Crowdsourcing digital health measures to predict Parkinson’s disease severity: the Parkinson’s Disease Digital Biomarker DREAM Challenge
Authors:
- Solveig K. SiebertsSSSolveig K. Sieberts
- Jennifer SchaffJSJennifer Schaff
- Marlena DudaMDMarlena Duda
- Bálint Ármin PatakiBPBálint Ármin Pataki
- Ming SunMSMing Sun
- Phil SnyderPSPhil Snyder
- Jean-Francois DaneaultJDJean-Francois Daneault
- Federico ParisiFPFederico Parisi
- Gianluca CostanteGCGianluca Costante
- Udi RubinURUdi Rubin
- Peter BandaPBPeter Banda
- Yooree ChaeYCYooree Chae
Preprint
- 16 January 2020
- preprint
- Published by Cold Spring Harbor Laboratory in bioRxiv
Abstract
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. 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 (best AUPR=0.95) severity.Keywords
All Related Versions
- Published version: npj Digital Medicine, 4 (1), 1.
This publication has 20 references indexed in Scilit:
- The mPower study, Parkinson disease mobile data collected using ResearchKitScientific Data, 2016
- The self‐assessment trap: can we all be better than average?Molecular Systems Biology, 2011
- Multiobjective evolutionary algorithms to identify highly autocorrelated areas: the case of spatial distribution in financially compromised farmsAnnals of Operations Research, 2011
- NWChem: A comprehensive and scalable open-source solution for large scale molecular simulationsComputer Physics Communications, 2010
- Feature Selection with theBorutaPackage2010
- Movement Disorder Society‐sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS‐UPDRS): Scale presentation and clinimetric testing resultsMovement Disorders, 2008
- The relationship between Precision-Recall and ROC curves2006
- Frequency of levodopa‐related dyskinesias and motor fluctuations as estimated from the cumulative literatureMovement Disorders, 2001
- The PDQ-8: Development and validation of a short-form parkinson's disease questionnairePsychology & Health, 1997
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987