The majority of morbidity and mortality during adolescence is preventable and related to behaviors such as substance use and vehicle-related injuries. Most adolescents visit a healthcare provider once a year, providing an ideal opportunity to integrate behavioral health screening into clinical care. Although the majority of adolescent health problems are amenable to behavioral intervention, few health information technology interventions have been integrated into adolescent care. With complementary theoretical advances (social-cognitive theories of behavior change) and technology advances (intelligent narrative-centered learning environments, user modeling, and machine learning), the field is now well positioned to design health behavior change systems that can realize significant impacts on behavior change for adolescent preventive health.
Computationally-enabled models of behavior change hold significant promise for adolescent healthcare. The objective of the proposed research is to design, implement, and investigate INSPIRE, a self-adaptive personalized behavior change system for adolescent preventive health. INSPIRE will utilize a social-cognitive theory of behavior change built around a tight feedback loop in which a narrative-centered behavior change environment will produce improved behaviors in patients, and the resulting patient outcome data will be used by a reinforcement learning optimization system to learn refined computational behavior change models. With a focus on risky behaviors and an emphasis on substance use, adolescents will interact with INSPIRE to develop an experiential understanding of the dynamics and consequences of their substance use decisions. A unique feature of INSPIRE afforded by recent advances in machine learning will be its ability to optimize health behavior change at both the individual and population levels. At the individual level, INSPIRE will utilize a patient behavior model to personalize its behavior change narratives for individual adolescents. It will customize interactions based on an adolescent's goals and affective models. At the population level, INSPIRE will utilize reinforcement learning to adapt its narrative generation system to systematically increase its ability to improve two types of outcomes: behavior change and self-efficacy. The project will culminate with an experiment conducted with a fully implemented version of INSPIRE at outpatient clinics within the UC San Francisco Department of Pediatrics, Benioff Children's Hospital.
It is anticipated that INSPIRE interventions will yield two types of outcomes: 1) improved health behavior through significant reductions in adolescent risky behavior, relative to standard of care; and 2) increased self-efficacy with respect to adolescents' ability to make good decisions about their health behaviors, relative to standard of care. Designed for natural integration into clinic workflow, interoperability with EHR and patient portal systems, and security and privacy requirements, INSPIRE will report patient behavior change summaries to healthcare providers. Through multi-platform deployments supporting laptop, desktop, tablet, and mobile computing devices, INSPIRE will serve as an empowering tool for adolescents, making them full participants in their own wellbeing. It will also enable researchers to run behavior analytics to investigate which properties of alternate interventions contribute most effectively to behavior change outcomes. Going forward, it is anticipated that INSPIRE will provide a testbed for a broad range of behavior change research and serve as the foundation for next-generation personalized preventive healthcare through computationally-enabled behavior change.
