An update on mobile applications collecting data among subjects with or at risk of Alzheimer's disease

Abstract

Smart mobile phone use is increasing worldwide, as is the ability of mobile devices to monitor daily routines, behaviors, and even cognitive changes. There is a growing opportunity for users to share the data collected with their medical providers which may serve as an accessible cognitive impairment screening tool. Data logged or tracked in an app and analyzed with machine learning (ML) could identify subtle cognitive changes and lead to more timely diagnoses on an individual and population level. This review comments on existing evidence of mobile device applications designed to passively and/or actively collect data on cognition relevant for early detection and diagnosis of Alzheimer's disease (AD). The PubMed database was searched to identify existing literature on apps related to dementia and cognitive health data collection. The initial search deadline was December 1, 2022. Additional literature published in 2023 was accounted for with a follow-up search prior to publication. 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 AD dementia. We identified relevant literature (n = 25) which fit our criteria. Many publications were excluded because they focused on apps which fail to collect data and simply provide users with cognitive health information. We found that although data collecting cognition-related apps have existed for years, the use of these apps as screening tools remains underdeveloped; however, it may serve as proof of concept and feasibility as there is much supporting evidence on their predictive utility. 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, screening tool, and research resource is still largely untapped.

Keywords: Alzheimer's disease; dementia; mobile phone applications; technology; tracking.

Figure 1

A concept map of the screening methods for including literature related to the collection of data. Our initial literature search yielded 113 results, 39 of which were excluded due to title irrelevance. Title relevance was determined due to the presence of explicit reference to one of three main categories for exclusion: animal modeling, apps exclusively developed as dementia support for caregivers, or papers on other diseases (i.e., HIV). If a title did not explicitly state a focus outside of our scope, the paper was included for abstract review. Out of the 74 abstracts reviewed, 24 results were deemed irrelevant and 50 total articles were reviewed in full if available. An abstract was excluded if the following criteria were not met: papers must have mentioned cognition, cognitive health, or dementia, and the use mobile phone application(s) by older adults at risk of or diagnosed with MCI or AD. Papers were excluded at full text review in the absence of discussion of a mobile phone application that collected data from the user, or if the paper focused on a specific dementia other than Alzheimer's disease. The final analysis of included publications is discussed in Table 2.