AI-PROGNOSIS dBM-DEV study

  • Research type

    Research Study

  • Full title

    AI-prognosis digital biomarkers development study (dBM-DEV study)

  • IRAS ID

    340929

  • Contact name

    K Ray Chaudhuri

  • Contact email

    ray.chaudhuri@kcl.ac.uk

  • Sponsor organisation

    King's College London

  • Clinicaltrials.gov Identifier

    Not applicable, Not applicable

  • Duration of Study in the UK

    1 years, 0 months, 28 days

  • Research summary

    The i-Prognosis mobile app platform developed during earlier project (IRAS: 220439) will be used to develop further digital biomarkers towards Parkinson's disease management.
    The main objective of this study is to identify features extracted from passive smartwatch data that are associated with episodes of REM sleep behaviour disorder (RBD) and demonstrate that these features can potentially help increase specificity of RBD detection as compared to the score of the RBD screening questionnaire (RBDSQ).
    RBD is the best predictor for neurodegenerative diseases synuclein (a type of protein in the brain) pathology, including Parkinson’s disease (PD). RBD affects 0.5-1 % of the general population. It can only be diagnosed by polysomnography (a test which measures various body functions whilst alseep), which is a cumbersome procedure that cannot be used for screening. An RBD screening questionnaire (RBDSQ) has been developed which has high sensitivity but low specificity. Thus, to facilitate detection of PD prior to diagnosis, digital assessments can potentially be used to identify people with a high probability of RBD for polysomnography.
    The study is conducted step-wise on two subsequent cohorts referred to as the development cohort (comprising 30 patients with RBD and 30 matched controls) and the confirmation cohort (comprising 30 patients with PD). Following a baseline visit, participants will undergo daily-life digital biomarker tracking over a duration of 4 weeks and 3 months, respectively. Additionally, PD patients enrolled in the confirmation cohort will receive a polysomnography.
    The main objective of this study is to identify features extracted from passive smartwatch data that are associated with episodes of RBD and demonstrate that these features can potentially help increase specificity of RBD detection, as compared to the score of the RBD screening questionnaire (RBDSQ).

  • REC name

    North of Scotland Research Ethics Committee 1

  • REC reference

    24/NS/0069

  • Date of REC Opinion

    28 Jun 2024

  • REC opinion

    Favourable Opinion