Behavioral Informatics and Computational Modeling in Support of Proactive Health Management and Care

Behavioral Informatics and Computational Modeling in Support of Proactive Health Management and Care 170 177 IEEE Transactions on Biomedical Engineering (TBME)


Misha Pavel, Holly B. Jimison, Ilkka Korhonen, Christine M. Gordon, and Niilo Saranummi, Northeastern University, USA

Behaviors are killing us – poor health-related behaviors are emerging to be among the key reasons for unnecessary reduction in quality of life and health outcomes. Improving health behaviors would therefore be an effective way to address this global challenge to enhance health outcomes and mitigate the escalating challenges arising from an increasingly aging population and the proliferation of chronic diseases. As behaviors have proven difficult to change, researchers are developing technological solutions that could help people to improve their behaviors. In this paper, we describe a vision and an approach to providing health behavior interventions using the tools of behavioral informatics, an emerging transdisciplinary research domain leveraging system-theoretic principles in combination with computer science, engineering, communication technology, behavioral science and information technology. Behavioral informatics processes comprise behavior monitoring, assessment, computational modeling, inference and intervention. The field is poised to advance a set of technologies and computational approaches to facilitate successful interventions that are scalable, cost-effective, and timely. We describe the components of a closed-loop system for health interventions, where each component is enhanced by a corresponding computational model that embodies the transformations from fine grain sensor characterizations to coaching protocols and individual-based predictive models of behavior change. The predictive nature of the computational models within behavioral informatics has the potential to optimize interventions through monitoring, assessing, and modeling behavior in support of providing tailored and just-in-time adaptive interventions. We explore an example of a research health coaching platform that incorporates a closed-loop intervention based on these multiscale models.   Using this platform prototype, we show how the optimized and personalized methodology and technology can support self-management, remote care, and behavioral change.

Keywords: Behavioral informatics, computational models, multiscale models, health behavior change, multiscale, self-management, wearable sensors, sensor networks, precision medicine, BD2K, models of behaviors.