EAGER: Defining a Dynamical Behavioral Model to Support a Just in time Adaptive Intervention

Project: Research project

Description

Smartphones and wearable/ubiquitous sensors, such as physical activity monitors, have the potential to help individuals improve their lives through behavior change by monitoring a person and then using that information to provide the most appropriate customized interventions exactly when and where it would be most beneficial for that person. While these mHealth technologies have this capacity in theory, in practice the models and decision rules required to determine exactly when, where, and how to intervene do not exist. The goal of this EAGER project is to create a mathematical model that will provide the insights for making decisions about when, where, and how a "just in time" adaptive mHealth physical activity intervention (JITAI) should intervene.

Creating this dynamical behavioral model is a challenging problem that requires insights from different disciplines, behavioral science and control systems engineering in particular. Behavioral science provides insights regarding what to measure, and behavioral intervention strategies that could be used dynamically; however, current behavioral theories fail to provide any real insights on when, where, and how to intervene at the opportune moment. Control systems engineering provides a methodology for creating dynamic mathematical models and decision-making, but this methodology has only sparsely been applied in a human behavioral context. A key first step for developing a dynamical behavioral model is to gather informative empirical data to estimate the model. During this EAGER project, we will conduct a system identification informative experiment within a human context that builds on lessons from behavioral science about experimental designs and that takes full advantage of the temporally rich data available from mHealth technologies. We will use these data to develop a fundamental yet empirically-supported dynamical behavioral model for understanding steps per day as our target behavior based on our previous experience with physical activity for mHealth interventions,1-7 dynamical simulation models,8,9 and system identification (ID) analyses.10 This work will support the next step in model development, namely, the design of an optimized experiment that could experimentally evaluate if the decision rules generated in the informative experiment are actually useful. If they do prove useful, this would provide a solid empirical foundation for an optimized JITAI.
StatusFinished
Effective start/end date8/1/147/31/16

Funding

  • National Science Foundation (NSF): $287,544.00

Fingerprint

Systems engineering
Identification (control systems)
Decision making
Mathematical models
Control systems
Experiments
Smartphones
Design of experiments
mHealth
Monitoring
Sensors