(689g) Experimental Design for Estimating “Just-in-Time” States in Control-Oriented Behavioral Interventions for Physical Activity
AIChE Annual Meeting
2022
2022 Annual Meeting
Computing and Systems Technology Division
Modeling, Control and Optimization Applications
Friday, November 18, 2022 - 9:54am to 10:13am
Fluid analogies relying on chemical engineering principles such as conservation of mass enable mathematically representing theories of behavioral change as systems of ordinary differential equations (ODEs). In previous work, a fluid analogy representation of the Social Cognitive Theory (SCT) has been developed to describe dynamics at a daily level [5,6]. In the constructed computational model, interrelations between external stimuli including temperature, daily goals and goal attainment (depicted as inflows/outflows) and the main constructs of SCT such as behavior, self-efficacy, and behavioral outcomes (represented as inventories) have been proposed to model and predict engagement of an individual in healthy behavior. While earlier research findings have been instrumental, the scope of the work was focused on daily level dynamics and did not incorporate within-day dynamic processes in real-world settings that can facilitate (or hinder) engagement in PA. There is still a need for a better understanding of the multi-timescale dynamic processes that constitute an individual's behavior, which would allow for the prediction of the behavior over the timescales of interest, and by extension dynamic decision-making in behavioral interventions. The concept of the âjust-in-timeâ adaptive interventions (JITAI) has been advanced in the field of behavioral science [7], where support is provided when the person has the need for a specific type of support, the receptivity to receive the support, and the opportunity to respond favorably to the provided support. This can facilitate the adaptation over time that yields a meaningful and sustained behavioral change. Thus, it is important to provide âjust-in-timeâ support, which can be conceptualized as a multi-timescale problem, in which robust prediction and decision-making are needed in both the short timescale, and the longer timescale.
In this work we propose an innovative experimental design to identify âjust-in-timeâ states and multi-timescale dynamics for a digital health intervention, Just Walk JITAI [8]. The experimental design relies on concepts from control engineering and system identification leading to input signals that elicit participant response resulting in an improved understanding of JIT behavior. The design leverages and improves on prior domain knowledge about processes that influence PA in the form of a dynamical model inspired by (SCT) [3,4,5], and are incorporated in our computational model. Two input signals are designed to address two principal components of the Just Walk JITAI intervention: a multisine signal to handle goal setting, and a combination of a pseudo-random binary signal (PRBS) with a three-level random sequence for âinspiring boutsâ which define JIT support provision rules for need, receptivity, and opportunity. Each signal design ensures that there is enough excitation of states along different ends of the frequency range (lower frequency for the goal setting, and higher frequency for the inspiring bouts). The orthogonal design of the signals facilitates analysis of the data. The improved SCT computational model is used in simulations to analyze plausible responses for different kinds of participants to the proposed input signal design, in order to assess the quality of the data that will be produced out of the intervention. These simulations indicate that the proposed experimental design will result in experimental data of sufficient quality to capture the multi-timescale dynamics of behavioral change and lead to improved control-oriented interventions. These ideas are currently being evaluated in the Just Walk JITAI.
References:
[1] Centers for Disease Control and Prevention. (2022, February 17). Adult physical inactivity prevalence maps by race/ethnicity. Centers for Disease Control and Prevention. Retrieved From https://www.cdc.gov/physicalactivity/data/inactivity-prevalence-maps/index.html
[2] Saint-Maurice, P. F., Troiano, R. P., Bassett, D. R., Graubard, B. I., Carlson, S. A., Shiroma, E. J., Fulton, J. E., & Matthews, C. E. (2020). Association of Daily Step Count and step intensity with mortality among US adults. JAMA, 323(12), 1151. https://doi.org/10.1001/jama.2020.1382
[3] Rivera, D.E., Hekler, E.B., Savage, J.S., Downs, D.S. (2018). Intensively Adaptive Interventions Using Control Systems Engineering: Two Illustrative Examples. In: Collins, L., Kugler, K. (eds) Optimization of Behavioral, Biobehavioral, and Biomedical Interventions. Statistics for Social and Behavioral Sciences. Springer, Cham. https://doi.org/10.1007/978-3-319-91776-4_5
[4] Hekler, E. B., Klasnja, P., Riley, W. T., Buman, M. P., Huberty, J., Rivera, D. E., & Martin, C. A. (2016). Agile science: Creating useful products for behavior change in the real world. Translational Behavioral Medicine, 6(2), 317â328. https://doi.org/10.1007/s13142-016-0395-7
[5] Martin, C. A., Rivera, D. E., Hekler, E. B., Riley, W. T., Buman, M. P., Adams, M. A., & Magann, A. B. (2020). Development of a control-oriented model of social cognitive theory for optimized mhealth behavioral interventions. IEEE Transactions on Control Systems Technology, 28(2), 331â346. https://doi.org/10.1109/tcst.2018.2873538
[6] Freigoun, M. T., Martin, C. A., Magann, A. B., Rivera, D. E., Phatak, S. S., Korinek, E. V., & Hekler, E. B. (2017). System identification of just walk: A behavioral mhealth intervention for promoting physical activity. 2017 American Control Conference (ACC). https://doi.org/10.23919/acc.2017.7962940
[7] Perski, O., Hébert, E. T., Naughton, F., Hekler, E. B., Brown, J., & Businelle, M. S. (2021). Technologyâmediated justâinâtime adaptive interventions (JITAIS) to reduce harmful substance use: A systematic review. Addiction, 117(5), 1220â1241. https://doi.org/10.1111/add.15687
[8] U.S. Department of Health and Human Services. (n.d.). Control Systems Engineering for Counteracting Notification Fatigue: An Examination of Health Behavior Change. National Institutes of Health. Retrieved April 10, 2022, from https://reporter.nih.gov/search/4nbzE01LtkiJMuHh9psRIw/project-details/10359062
R01LM013107: National Institute of Health, National Cancer Institute.