Evaluation framework for selecting wearable activity monitors for research.

BACKGROUND: Wearable devices that support activity tracking and other measurements hold great potential to increase awareness of health behaviors and support the management of chronic health conditions. There is a scarcity of guidance for researchers of all disciplines when planning new studies to evaluate and select technologies appropriate for study purpose, population, and overall context. The aim of this study was to develop and test an evaluation framework to rapidly and systematically evaluate and select consumer-grade wearable devices that serve individual study needs in preparation for evaluations with target populations. METHODS: The wearable evaluation framework was defined based on published literature and past research experiences of the research team. We tested the framework with example case studies to select devices for two different research projects focused on aging-in-place and gestational diabetes. We show how knowledge of target population and research goals help prioritize application of the criteria to inform device selection and how project requirements inform sequence of criteria application. RESULTS: The framework for wearable device evaluation includes 27 distinct evaluation criteria: 12 for everyday use by users, 6 on device functionality, and 9 on infrastructure for developing the research infrastructure required to obtain the data. We evaluated 10 devices from four vendors. After prioritizing the framework criteria based on the two example case studies, we selected the Withings Steele HR, Garmin Vivosmart HR+ and Garmin Forerunner 35 for further evaluation through user studies with the target populations. CONCLUSIONS: The aim of this paper was to develop and test a framework for researchers to rapidly evaluate suitability of consumer grade wearable devices for specific research projects. The use of this evaluation framework is not intended to identify a definitive single best device, but to systematically narrow the field of potential device candidates for testing with target study populations. Future work will include application of the framework within different research projects for further refinement.

Continuous Detection of Physiological Stress with Commodity Hardware.

Timely detection of an individual's stress level has the potential to improve stress management, thereby reducing the risk of adverse health consequences that may arise due to mismanagement of stress. Recent advances in wearable sensing have resulted in multiple approaches to detect and monitor stress with varying levels of accuracy. The most accurate methods, however, rely on clinical-grade sensors to measure physiological signals; they are often bulky, custom made, and expensive, hence limiting their adoption by researchers and the general public. In this article, we explore the viability of commercially available off-the-shelf sensors for stress monitoring. The idea is to be able to use cheap, nonclinical sensors to capture physiological signals and make inferences about the wearer's stress level based on that data. We describe a system involving a popular off-the-shelf heart rate monitor, the Polar H7; we evaluated our system with 26 participants in both a controlled lab setting with three well-validated stress-inducing stimuli and in free-living field conditions. Our analysis shows that using the off-the-shelf sensor alone, we were able to detect stressful events with an F1-score of up to 0.87 in the lab and 0.66 in the field, on par with clinical-grade sensors.

Investigating Contextual Cues as Indicators for EMA Delivery.

In this work, we attempt to determine whether the contextual information of a participant can be used to predict whether the participant will respond to a particular Ecological Momentary Assessment (EMA) trigger. We use a publicly available dataset for our work, and find that by using basic contextual features about the participant's activity, conversation status, audio, and location, we can predict if an EMA triggered at a particular time will be answered with a precision of 0.647, which is significantly higher than a baseline precision of 0.41. Using this knowledge, the researchers conducting field studies can efficiently schedule EMAs and achieve higher response rates.