Analysis of digital health data: from research lab to app store
Digital health technologies typically include mobile device apps as well as browser-based apps to a lesser extent, and can include telephony-based services, text-based chatbots, and voice-activated chatbots. Many of these digital products and services are simultaneously available across many channels. Such digital health and wellbeing interventions offer methods for real-time data capture of the interactions of users with the products and services. It is possible to design what data are recorded, how and where it may be stored, and, crucially, how it can be analysed to reveal individual or collective usage patterns.
Digital phenotyping is the term given to the capturing and use of user log data from health and wellbeing technologies used in apps and cloud-based services. In some cases, the data are physiological, while in other cases, the data is metadata; for example, when a sensor reading is made it may be the duration of the reading rather than the value of the reading that is useful. Oftentimes, as would be expected from a personal device located on the body of the user, rich data pertaining to geo-location, social media use and interaction is also gathered.
Another form of digital phenotype data is from Ecological Momentary Assessment (EMA). EMA secures data about both behavioural and intrapsychic aspects of individuals' daily activities, and it obtains reports about the experience as it occurs, thereby minimizing the effects of reliance on memory and reconstruction which can often be impaired by hindsight bias or recall bias. Health and wellbeing-related, scientifically validated assessment scales may be presented to users via EMA.
Digital phenotyping and its analysis using machine learning is important since many national public health organizations are planning to or are using digital technologies for new digital-based health interventions for self-management, where logging user interactions provides insight into user needs and provides evidence for improving these digital interventions, for example through enhanced personalization. In such cases, public health services may benefit since the data can be automatically and cost-effectively collected. Such data may facilitate new methods for digital epidemiological analyses and provide data to inform health policy improvement. However, collecting and ownership of such personal data gives rise to increased risks and new ethical concerns which are discussed.
Maurice Mulvenna has kindly given permission for this webinar to be recorded.
To register for the Zoom link please email Imogen at email@example.com