JMIR Publications

ABSTRACT

Background:

Mobile health methods often rely on active input from participants, for example in the form of self-report questionnaires delivered via web or smartphone, to measure health and behavioral indicators and deliver interventions in everyday life settings. For short-term studies or interventions, these techniques are deployed intensively, causing nontrivial participant burden. For cases of where the goal is long-term maintenance, limited infrastructure exists to balance information needs with participant constraints. Yet the increasing precision of passive sensors such as wearable physiology monitors, smartphone-based location history, and Internet-of-Things (IoT) devices, in combination with statistical feature selection and adaptive interventions have begun to make such things possible.

Objective:

We introduce Wear-IT, a smartphone app and cloud framework intended to begin to fill this gap by allowing researchers to leverage commodity electronics and real-time decision-making to optimize the amount of useful data collected while minimizing participant burden.

Methods:

By using a combination of active and passive sensing technology, real-time analysis tools, responsive intervention and assessment, individualized visualization, modeling and feedback, and novel data collection methods, it is possible to actively balance participant burden and engagement with data quality within the resource limitations of the device.

Results:

Wear-IT provides a novel framework for both researchers seeking to study ways of optimizing burden and engagement for mHealth and uHealth research; it also can be deployed as a means of using these techniques to balance these quantities against data quality for adaptive interventions, especially for longer-term deployments. We provide use cases from ongoing deployments, and a brief example of visualization tools for an addiction recovery intervention.

Conclusions:

Engagement and participant burden are serious concerns for any mHealth or uHealth deployment, whether for research or active intervention, and balancing these quantities against data quality and intervention precision represents a nontrivial task. The use of individualized modeling to combine passive and active sensing, feedback, and responsiveness seems necessary to balance these concerns against the need for quality real-time data. Wear-IT takes the first step towards this goal by providing a general-purpose framework for mHealth and uHealth researchers seeking to study these concerns, and for practitioners and clinicians seeking to optimize these quantities in their interventions.