Harnessing the Potential of Digital Technologies for the Early Detection of Neurodegenerative Diseases (EDoN)

Abstract

The increasing global prevalence of dementia and the lack of disease-modifying treatments give rise to the need for early detection of dementia-causing diseases to enable the development and targeted administration of preventative interventions. However, current methods that have potential for the early detection of dementia-causing diseases, such as positron emission tomography or cerebrospinal fluid sampling, are invasive and costly, which constitutes a barrier to the large-scale assessment of dementia risk. The Early Detection of Neurodegenerative diseases (EDoN) initiative was established by Alzheimer’s Research UK to address this challenge. As part of EDoN, digital data and low-burden clinical measures, such as blood tests, will be collected in thousands of people to create machine learning models that can detect specific dementia-causing diseases decades before noticeable cognitive symptoms arise. This effort will be supported by the development of a data platform and a digital toolkit (likely consisting of wearables and smartphone applications) that will collect active and passive physiological and behavioural measures (e.g. cognition, mood, heart rate, gait, sleep, and navigation). After extensive testing, EDoN aims to introduce the digital toolkit into annual health checks, which will allow for the early detection of dementia-causing diseases in a cost-effective, low-burden manner on a population-wide scale. Moreover, the information derived from the digital data will be used to inform lifestyle changes and to triage and stratify individuals into clinical trials or further targeted medical testing. As such, the outputs of the EDoN initiative will benefit the public, patients, carers, and clinicians, as well as the broader healthcare system and the pharmaceutical industry.

A Survey of Human Gait-Based Artificial Intelligence Applications

“…Looking into the future, digital technologies such as smartwatches, headbands, and smartphones will be exploited to collect population-wide scale data to facilitate health monitoring and early detection of various diseases. One aspect of such systems is the multimodality of the data ( Frey et al, 2019 ), ( Abeysekara et al, 2020 ). Their integrated approach will demand cross-disciplinary research and collaborations.…”

“… 4) ML community can benefit from the collaborative effort. It fosters competition against established benchmarks and open research promoted by initiatives such as the Parkinson’s Disease Digital Biomarker (PDDB) DREAM Challenge ( Zhang et al, 2020a ) 5) ML-driven gait-based studies can benefit from large-scale population data through smartphones, smartwatches, and other wearable devices ( Frey et al, 2019 ), as well as individual or small-scale data easily collected at low cost, via pervasive techniques such as MS Kinect ( Dolatabadi et al, 2017 ), smartphone ( Pepa et al, 2020 ), triboelectric nanogenerator (TENG) smart shoes ( Zou et al, 2020 ) and socks ( Zhang et al, 2020g ) which makes them suitable for implementation at home, clinic, etc. These systems stand to benefit from the recent fast and continuing advancements in sensing technology, textiles, parallel processing, cloud computing, and IoT grids.…”

Ethical issues when using digital biomarkers and artificial intelligence for the early detection of dementia

“…The widespread adoption of smartphones and devices such as the Apple Watch and Fitbit has suggested the possibility of collecting data about an individual's real world cognitive function and providing repeated, real‐time measurements taken in real‐life settings, as opposed to cognitive assessments and brain scans administered in the clinic only once or at spaced intervals (Dagum, 2018). Major programs, including collaborations between Apple, Evidation and Eli Lilly (Chen et al, 2019), Apple and Biogen (Intuition Study), Alzheimer's Research UK's Early Detection of Neurodegenerative Diseases (EDoN; EDON Initiative, 2021; Frey et al, 2019), RADAR‐AD (Muurling et al, 2021) the MRC Deep and Frequent Phenotyping study (Koychev et al, 2019) and the SENDA trial (Müller et al, 2020) are exploring the potential of a range of digital technologies to collect data from community dwelling adults. Measures captured by digital devices may include sleep, neural activity, cognition, speech and language, gait, heart rate, fine motor skills and physical activity, with the aim of collecting a digital picture of individual's daily function, linking fluctuations in memory performance with specific daily life activities or experiences and identifying subtle changes suggestive of cognitive decline (Kourtis et al, 2019).…”

Developments in scalable strategies for detecting early markers of cognitive decline

“…Indeed, some of these studies are already underway. For example, the Early Detection of Neurodegenerative diseases (EDoN) [164] project aims to collect data from passive sensors and easily obtained clinical measures to detect the earliest signatures of dementia. EDoN's ultimate goal is to develop a digital toolkit to deployed at a population level for people over age 40.…”