The Early Detection of Neurodegenerative diseases initiative: emerging insights from the initial implementation of a digital toolkit

Abstract

AbstractBackgroundThe benefits of the early detection of the neurodegenerative and vascular pathologies which cause dementia are widely acknowledged. These include the opportunity to initiate risk‐reduction strategies, disease‐modifying therapies, and future care planning. However, current pathological biomarkers have several important drawbacks, as they are typically invasive, expensive, impractical, insensitive, or lack real‐world validation. Conversely, the targeted utilization of non‐invasive and inexpensive digital technologies which can be integrated into everyday life raises the possibility of capturing a ‘digital‐fingerprint’ of early disease.MethodThe Early Detection of Neurodegenerative diseases (EDoN) initiative is a meta‐cohort study spearheaded by Alzheimer’s Research UK. EDoN is acquiring high‐dimensional data from a ‘digital toolkit’ comprising a smartwatch (Fitbit Charge 4/5), smartphone software (Mezurio and Longevity), and an electroencephalography headband (Dreem 3). In combination with conventional digital, cognitive and biological markers, these data will inform the development of powerful machine learning models to detect dementia‐causing diseases at the very earliest stages. The initial phase, incorporating four cohorts across three continents, is already underway, and will recruit nearly 900 participants. Cohorts are recruiting healthy individuals, as well as patients with subjective/mild cognitive impairment, or established dementia. Data from version‐1 of the toolkit is being collected over two‐week periods at 3‐monthly intervals for a minimum of 12 months.ResultWe will present early insights from the implementation of the EDoN digital toolkit version‐1. These will include sample characteristics, feasibility and acceptability, and participants’ compliance. PPI data confirmed good acceptability but the potential for inequity due to technical problems and poor digital literacy. Pilot data indicate that six‐month adherence to the EDoN digital tools varies between 82‐89%. The forthcoming AAIC presentation will include important recruitment, toolkit acceptability and analytic updates.ConclusionThe initial implementation of the EDoN digital toolkit suggests that it is feasible and acceptable to collect high‐dimensional digital data over a six‐month period. These ‘digital‐fingerprints’ will form the basis of the initial development of machine learning models to identify dementia‐causing pathologies substantially earlier. The insights gained will also inform the development of version‐2 of the EDoN digital toolkit which will be incorporated into the next meta‐cohort prospective study of around 4,000 participants.