Novel use of mHealth data to identify states of vulnerability and receptivity to JITAIs

点击翻译按钮获取中文摘要

Abstract: Smoking cessation decreases morbidity and mortality and is a cornerstone of cancer prevention. The ability to impact current and future vulnerability (e.g., high risk for a lapse) in real-time via engagement in self-regulatory activities (e.g., behavioral substitution, mindful attention) is considered an important pathway to quitting success. However, poor engagement represents a major barrier to maximizing the impact of self- regulatory activities. Hence, enhancing real-time, real-world engagement in evidence-based self-regulatory activities has the potential to improve the effectiveness of smoking cessation interventions. Just-In-Time Adaptive Interventions (JITAIs) delivered via mobile devices have been developed for preventing and treating addictions. JITAIs adapt over time to an individual’s changing status and are optimized to provide appropriate intervention strategies based on real time, real world context. Organizing frameworks on JITAIs emphasize minimizing disruptions to the daily lives and routines of the individual, by tailoring strategies not only to vulnerability, but also to receptivity (i.e., an individual’s ability and willingness to utilize a particular intervention). Although both vulnerability and receptivity are considered latent states that are dynamically and constantly changing based on the constellation and temporal dynamics of emotions, context, and other factors, no attempt has been made to systematically investigate the nature of these states, as well as how knowledge of these states can be used to optimize real-time engagement in self-regulatory activities. To close this gap, the proposed project will apply innovative computational approaches to one of the most extensive and racially/ethnically diverse collection of real time, real world data on health behavior change (smoking cessation). Intensive longitudinal self-reported and sensor data from 5 studies (3 completed and 2 ongoing) of ~1,500 smokers attempting to quit will be analyzed with advanced probabilistic latent variable models and machine learning to investigate how the temporal dynamics and interactions of emotions, self-regulatory capacity (SRC), context, and other factors can be used to detect (Aim 1) states of vulnerability to a lapse and (Aim 2) states of receptivity to engaging in self-regulatory activities. We will also investigate (Aim 3) how knowledge of these states can be used to optimize real-time engagement in self-regulatory activities by conducting a Micro-Randomized Trial (MRT) enrolling 150 smokers attempting to quit. Utilizing a mobile smoking cessation app, the MRT will randomize each individual multiple times per day to either (a) no intervention prompt; (b) a prompt recommending engagement in brief (low effort) strategies; or (c) a prompt recommending a more effortful practice of self-regulation strategies. The proposed research will be the first to yield a comprehensive conceptual, technical, and empirical foundation necessary to develop effective JITAIs based on dynamic models of vulnerability and receptivity.