An update on mobile phone applications collecting data among subjects with or at risk of dementia
Lydia A Piendel, Jakub Hort, Martin Vališ- Psychiatry and Mental health
- Cellular and Molecular Neuroscience
- Geriatrics and Gerontology
- Neurology (clinical)
- Developmental Neuroscience
- Health Policy
- Epidemiology
Abstract
Background
The ubiquity of smart mobile phones is increasing worldwide, creating an opportunity for telemedicinal use by screening people at risk of or with dementia through monitoring daily routines, behaviors, and cognitive changes. Data logged or tracked in an app and analyzed with machine learning (ML) could be shared with physicians and specialists to allow for screening, follow‐up, and timely diagnoses, and could provide users information on preventive measures or disease management. This review comments on existing evidence of mobile device applications designed to passively and/or actively collect data on cognition relevant for Alzheimer’s disease (AD) and other dementias.
Method
The PubMed database was searched to identify existing literature on applications related to dementia and cognitive health data collection. The search deadline was December 1, 2022. Criteria for inclusion was limited to articles in English which referenced data collection via mobile app from adults 50+ concerned, at risk of, or diagnosed with dementia.
Result
We identified relevant literature (n = 25) which fit our criteria. A common theme among excluded literature was the mention of apps that provide users, primarily caregivers, with cognitive health information but fail to collect data. We found the existing library of data collecting dementia‐related apps has existed for several years yet remains underdeveloped; however, it may serve as proof of concept and feasibility as there is much supporting evidence on their predictive utility.
Conclusion
Concerns about the validity of mobile apps for cognitive screening and privacy issues remain prevalent. Mobile applications and use of ML is widely considered a financially and socially viable method of compiling symptomatic data but currently this large potential dataset, telemedicine communication tool, and research resource is still largely untapped.