1. Crowdsourcing digital health measures to predict Parkinson’s disease severity: the Parkinson’s Disease Digital Biomarker DREAM Challenge
- Author
-
Sieberts, S.K., Schaff, J., Duda, M., Pataki, B.Á., Sun, M., Snyder, P., Daneault, J.F., Parisi, F., Costante, G., Rubin, U., Banda, P., Chae, Y., Chaibub Neto, E., Dorsey, E.R., Aydın, Z., Chen, A., Elo, L.L., Espino, C., Glaab, E., Goan, E., Golabchi, F.N., Görmez, Y., Jaakkola, M.K., Jonnagaddala, J., Klén, R., Li, D., McDaniel, C., Perrin, D., Perumal, T.M., Rad, N.M., Rainaldi, E., Sapienza, S., Schwab, P., Shokhirev, N., Venäläinen, M.S., Vergara-Diaz, G., Zhang, Y., Abrami, A., Adhikary, A., Agurto, C., Bhalla, S., Bilgin, H., Caggiano, V., Cheng, J., Deng, E., Gan, Q., Girsa, R., Han, Z., Heisig, S., Huang, K., Jahandideh, S., Kopp, W., Kurz, C.F., Lichtner, G., Norel, R., Raghava, G.P.S., Sethi, T., Shawen, N., Tripathi, V., Tsai, M., Wang, T., Wu, Y., Zhang, J., Zhang, X., Wang, Y., Guan, Y., Brunner, D., Bonato, P., Mangravite, L.M., Omberg, L., AGÜ, Mühendislik Fakültesi, Elektrik - Elektronik Mühendisliği Bölümü, Aydin, Zafer, Fonds National de la Recherche - FnR [sponsor], and Luxembourg Centre for Systems Biomedicine (LCSB): Biomedical Data Science (Glaab Group) [research center]
- Subjects
Movement disorders ,Parkinson's disease ,Biotechnologie [F06] [Sciences du vivant] ,Neurology [D14] [Human health sciences] ,Medicine (miscellaneous) ,Disease ,Multidisciplinaire, généralités & autres [F99] [Sciences du vivant] ,0302 clinical medicine ,Health Information Management ,Evaluation methods ,Biotechnology [F06] [Life sciences] ,Multidisciplinary, general & others [D99] [Human health sciences] ,0303 health sciences ,Outcome measures ,Computer Science Applications ,machine learning ,smart sensors ,bradykinesia ,Biomarker (medicine) ,Technology Platforms ,medicine.symptom ,medicine.medical_specialty ,Multidisciplinaire, généralités & autres [D99] [Sciences de la santé humaine] ,Computer applications to medicine. Medical informatics ,R858-859.7 ,Health Informatics ,Multidisciplinary, general & others [F99] [Life sciences] ,Digital Biomarker ,Crowdsourcing ,Article ,VALIDATION ,Parkinson’s Disease ,03 medical and health sciences ,Physical medicine and rehabilitation ,Machine learning ,medicine ,030304 developmental biology ,mobile phone ,GENDER-DIFFERENCES ,Neurologie [D14] [Sciences de la santé humaine] ,business.industry ,biomarkers ,medicine.disease ,tremor ,Digital health ,nervous system diseases ,Clinical trial ,dyskinesia ,Dyskinesia ,Cardiovascular and Metabolic Diseases ,HYPOTHESIS TESTS ,business ,Biomarkers ,030217 neurology & neurosurgery - 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)., npj Digital Medicine, 4 (1), ISSN:2398-6352
- Published
- 2021
- Full Text
- View/download PDF