Assessing the availability of users to engage in just-in-time intervention in the natural environment

Abstract

Wearable wireless sensors for health monitoring are enabling the design and delivery of just-in-time interventions (JITI). Critical to the success of JITI is to time its delivery so that the user is available to be engaged. We take a first step in modeling users’ availability by analyzing 2,064 hours of physiological sensor data and 2,717 self-reports collected from 30 participants in a week-long field study. We use delay in responding to a prompt to objectively measure availability. We compute 99 features and identify 30 as most discriminating to train a machine learning model for predicting availability. We find that location, affect, activity type, stress, time, and day of the week, play significant roles in predicting availability. We find that users are least available at work and during driving, and most available when walking outside. Our model finally achieves an accuracy of 74.7% in 10-fold cross-validation and 77.9% with leave-one-subject-out.

Innovations in the Use of Interactive Technology to Support Weight Management

“…These modalities can be combined in many ways, for instance a sensor-based plus time-based intervention that only intervenes on sedentary behavior in children after school. Finally, interactive mHealth technologies provide streaming data that can be used to adapt the intervention to the needs of the participant, according, for instance, to momentary availability to be able to react to prompts 55 , or changes in participant behaviors 56 . For instance, if an intervention to reduce sugar intake focuses on reduction of sugar sweetened beverage intake, and one participant is quickly successful while another still struggles, intervention goals can be personalized and adjusted on a momentary basis to fit the needs of each individual participant according to available data in real- or near-time.…”

Extended, continuous measures of functional status in community dwelling persons with Alzheimer’s and related dementia: Infrastructure, performance, tradeoffs, preliminary data, and promise

“…However, all of these systems require subjects to remain within spaces monitored by sensors, and do not provide data when subjects leave the home. Other groups have addressed this problem by providing subjects with wearable sensors (Ertin et al, 2011; Sarker et al, 2014), or using sensor functions intrinsic to SmartPhones (Schueller et al, 2014). Not surprisingly, major strengths of these systems are their ability to follow subjects throughout the community.…”

mCerebrum

“…Intelligent scheduling mechanisms for delivering prompts has been proposed in earlier works such as InterruptMe [19] and our prior work [29]. The key innovation of mCerebrum framework is its flexibility so as to allow implementation of these and other scheduling mechanisms via changes only to configuration files.…”

“…Making scheduling decisions from biomarkers incurs only minimal energy cost (9.37 mA). Fourth, using the screen for 25 minutes to complete EMA or EMI (10 times a day for 2.5 minutes each [29]) consumes one-third the energy needed for adding the first BLE sensor. In a base configuration consisting of two wrist sensors, of the total energy, baseline operation consumes 9%, sensing consumes 48%, computation consumes 28%, and user interaction with the screen consumes the remaining 15%.…”