BIROn - Birkbeck Institutional Research Online

    The cloudUPDRS app: a medical device for the clinical assessment of Parkinson's Disease

    Stamate, C. and Magoulas, George D. and Kueppers, S. and Nomikou, E. and Daskalopoulos, I. and Jha, A. and Pons, J.S. and Rothwell, J. and Luchini, M.U. and Moussouri, T. and Iannone, M. and Roussos, George (2018) The cloudUPDRS app: a medical device for the clinical assessment of Parkinson's Disease. Pervasive and Mobile Computing 43 , pp. 146-166. ISSN 1574-1192.

    [img] Text
    PMC-The cloudUPDRS app.pdf - Author's Accepted Manuscript
    Restricted to Repository staff only until 21 December 2018.

    Download (3MB) | Request a copy

    Abstract

    Parkinson's Disease is a neurological condition distinguished by characteristic motor symptoms including tremor and slowness of movement. To enable the frequent assessment of PD patients, this paper introduces the cloudUPDRS app, a Class I medical device that is an active transient non-invasive instrument, certified by the Medicines and Healthcare products Regulatory Agency in the UK. The app follows closely Part III of the Unified Parkinson's Disease Rating Scale which is the most commonly used protocol in the clinical study of PD; can be used by patients and their carers at home or in the community unsupervised; and, requires the user to perform a sequence of iterated movements which are recorded by the phone sensors. The cloudUPDRS system addresses two key challenges towards meeting essential consistency and efficiency requirements, namely: (i) How to ensure high-quality data collection especially considering the unsupervised nature of the test, in particular, how to achieve firm user adherence to the prescribed movements; and (ii) How to reduce test duration from approximately 25 minutes typically required by an experienced patient, to below 4 minutes, a threshold identified as critical to obtain significant improvements in clinical compliance. To address the former, we combine a bespoke design of the user experience tailored so as to constrain context, with a deep learning approach based on Recurrent Convolutional Neural Networks, to identify failures to follow the movement protocol. We address the latter by developing a machine learning approach to personalize assessments by selecting those elements of the test that most closely match individual symptom profiles and thus offer the highest inferential power, hence closely estimating the patent's overall score.

    Metadata

    Item Type: Article
    School: Birkbeck Schools and Departments > School of Business, Economics & Informatics > Computer Science and Information Systems
    Depositing User: Prof George Magoulas
    Date Deposited: 18 Dec 2017 09:03
    Last Modified: 02 Jul 2018 09:53
    URI: http://eprints.bbk.ac.uk/id/eprint/20640

    Statistics

    Downloads
    Activity Overview
    2Downloads
    92Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item