Supporting Adolescent Engagement with Artificial Intelligence-Driven Digital Health Behavior Change Interventions.

Understanding and optimizing adolescent-specific engagement with behavior change interventions will open doors for providers to promote healthy changes in an age group that is simultaneously difficult to engage and especially important to affect. For digital interventions, there is untapped potential in combining the vastness of process-level data with the analytical power of artificial intelligence (AI) to understand not only how adolescents engage but also how to improve upon interventions with the goal of increasing engagement and, ultimately, efficacy. Rooted in the example of the INSPIRE narrative-centered digital health behavior change intervention (DHBCI) for adolescent risky behaviors around alcohol use, we propose a framework for harnessing AI to accomplish 4 goals that are pertinent to health care providers and software developers alike: measurement of adolescent engagement, modeling of adolescent engagement, optimization of current interventions, and generation of novel interventions. Operationalization of this framework with youths must be situated in the ethical use of this technology, and we have outlined the potential pitfalls of AI with particular attention to privacy concerns for adolescents. Given how recently AI advances have opened up these possibilities in this field, the opportunities for further investigation are plenty.

"What's Important to You, Max?": The Influence of Goals on Engagement in an Interactive Narrative for Adolescent Health Behavior Change.

Interactive narrative technologies for preventive health care offer significant potential for promoting health behavior change in adolescents. By improving adolescents' knowledge, personal efficacy, and self-regulatory skills these technologies hold great promise for realizing positive impacts on adolescent health. These potential benefits are enabled through story-centric learning experiences that provide opportunities for adolescents to practice strategies to reduce risky health behaviors in engaging game-based environments. A distinctive feature of interactive narrative that promotes engagement is players' ability to influence the story through the choices they make. In this paper, we present initial work investigating engagement in an interactive narrative that focuses on reducing adolescents' risky behaviors around alcohol use. Specifically, we consider how the short-term and long-term goals adolescents choose as being important to the protagonist character relates to their engagement with the interactive narrative. Leveraging interaction log data from a pilot study with 20 adolescents, we conduct a cluster-based analysis of the goals players selected. We then examine how engagement differs between the identified clusters. Results indicate that adolescents' choices for the protagonist's short-term and long-term goals can significantly impact their engagement with the interactive narrative.

Fostering Engagement in Health Behavior Change: Iterative Development of an Interactive Narrative Environment to Enhance Adolescent Preventive Health Services.

PURPOSE: Accidents and unintentional injuries account for the greatest number of adolescent deaths, often involving use of alcohol and other substances. This article describes the iterative design and development of Interactive Narrative System for Patient-Individualized Reflective Exploration (INSPIRE), a narrative-centered behavior change environment for adolescents focused on reducing alcohol use. INSPIRE is designed to serve as an extension to clinical preventive care, engaging adolescents in a theoretically grounded intervention for health behavior change by leveraging 3D game engine and interactive narrative technologies. METHODS: Adolescents were engaged in all aspects of the iterative, multiyear development process of INSPIRE through over 20 focus groups and iterative pilot testing involving more than 145 adolescents. Qualitative findings from focus groups are reported, as well as quantitative findings from small-scale pilot sessions investigating adolescent engagement with a prototype version of INSPIRE using a combination of questionnaire and interaction trace log data. RESULTS: Adolescents reported that they found INSPIRE to be engaging, believable, and relevant to their lives. The majority of participants indicated that the narrative's protagonist character was like them (84%) and that the narrative featured virtual characters that they could relate to (79%). In the interactive narrative, the goals most frequently chosen by adolescents were "stay in control" (60%) and "do not get in trouble" (55%). CONCLUSIONS: With a strong theoretical framework (social-cognitive behavior change theory) and technology advances (narrative-centered learning environments), the field is well positioned to design health behavior change systems that can realize significant impacts on behavior change for adolescent preventive health.

Teen Preferences for Clinic-Based Behavior Screens: Who, Where, When, and How?

PURPOSE: Previous research examining computer-based adolescent risk behavior screening was done before widespread adoption of smartphones and merits updating. METHODS: This is a cross-sectional survey among 115 adolescents seeking primary care age 12-18 years. It is a diverse sample with 59% female, 51% white, 18% African-American, and 27% Latino. Respondents were asked level of comfort and honesty (1 = strongly disagree, 5 = strongly agree) when answering health behavior questions by paper, interview, or electronic device. Differences in the level of agreement were tested using a Wilcoxon signed rank test. RESULTS: Adolescents reported a higher level of comfort and honesty for screening conducted via electronic device versus paper (90% vs. 57%, p < .001; 89% vs. 61%, p < .001). Sixty-two percent adolescents prefer waiting room electronic screening versus at home (4.7%) or by provider in the examination room (11.2%). CONCLUSIONS: Electronic same-day risk behavior screening is the preferred method for adolescents and should be incorporated into preventive services.

Use of theory in computer-based interventions to reduce alcohol use among adolescents and young adults: a systematic review.

BACKGROUND: Alcohol use and binge drinking among adolescents and young adults remain frequent causes of preventable injuries, disease, and death, and there has been growing attention to computer-based modes of intervention delivery to prevent/reduce alcohol use. Research suggests that health interventions grounded in established theory are more effective than those with no theoretical basis. The goal of this study was to conduct a literature review of computer-based interventions (CBIs) designed to address alcohol use among adolescents and young adults (aged 12-21 years) and examine the extent to which CBIs use theories of behavior change in their development and evaluations. This study also provides an update on extant CBIs addressing alcohol use among youth and their effectiveness. METHODS: Between November and December of 2014, a literature review of CBIs aimed at preventing or reducing alcohol in PsychINFO, PubMed, and Google Scholar was conducted. The use of theory in each CBI was examined using a modified version of the classification system developed by Painter et al. (Ann Behav Med 35:358-362, 2008). RESULTS: The search yielded 600 unique articles, 500 were excluded because they did not meet the inclusion criteria. The 100 remaining articles were retained for analyses. Many articles were written about a single intervention; thus, the search revealed a total of 42 unique CBIs. In examining the use of theory, 22 CBIs (52 %) explicitly named one or more theoretical frameworks. Primary theories mentioned were social cognitive theory, transtheoretical model, theory of planned behavior and reasoned action, and health belief model. Less than half (48 %), did not use theory, but mentioned either use of a theoretical construct (such as self-efficacy) or an intervention technique (e.g., manipulating social norms). Only a few articles provided detailed information about how the theory was applied to the CBI; the vast majority included little to no information. CONCLUSIONS: Given the importance of theory in guiding interventions, greater emphasis on the selection and application of theory is needed. The classification system used in this review offers a guiding framework for reporting how theory based principles can be applied to computer based interventions.