Sweetgoals: A Conversational Agent for Young Adults with Type 1 Diabetes
Many young adults with type 1 diabetes (T1D) struggle with the complex daily demands of adherence to their medical regimen and face challenges achieving glycemic control at target levels. However, few interventions have been developed specifically for this age group. In the proposed study, we will provide an app (SweetGoals) to all participants as a “core” intervention. The app prompts participants to upload their diabetes devices weekly to a device-agnostic uploader (Glooko), will automatically retrieve uploaded data and apply decision rules about daily and weekly self-management goals, and will generate feedback messages about goal attainment. We will use a novel digital direct-to-patient recruitment method and intervention delivery model that transcends the clinic. Instead of relying on the clinic to transform its system of care, our intervention will directly assist young adult patients in developing skills to improve their utilization of the health care system. A prior pilot study comparing this intervention approach to usual care among adolescents showed a significant and sustained impact on A1c. These results were very promising, and we believe this intervention is well suited to young adults. In the proposed study, 300 young adults ages 19-25 with T1D and above target (Hb)A1c (≥ 8.0%) will be recruited via social media. All participants will receive the SweetGoals app built on the open-source software platform MobileCoach for smartphone-based and conversational agent-delivered interventions and ecological momentary assessments. The app automatically retrieves diabetes device data “digested” by Glooko and prompts and provides feedback on adherence goals. Adherence targets include (a) daily glucose monitoring; and (b) mealtime behaviours. Participants will be randomized to receive (1) modest financial incentives for meeting adherence targets (yes vs. no) and (2) web health coaching (yes vs. no). Coaches will teach a problem-solving approach that generates personalized solutions to adherence challenges. The intervention will last 6 months. The primary outcome will be a reduction in A1c. Successful completion of these aims will support dissemination and effectiveness studies of this intervention that seeks to improve glycemic control in this high-risk and understudied population of young adults with T1D.
Public Health Relevance
This project addresses a key public health issue with broad applicability to many diseases and health behaviours: how to help people follow a complicated medical regimen and achieve better health outcomes. We will test the role of coaching support focused on problem solving and incentives to help young adults with type 1 diabetes feel better and be healthier. We expect that the things we learn about helping young adults with type 1 diabetes will apply to many other health problems.
Kowatsch, T., Volland, D., Shih, I., Rüegger, D., Künzler, F., Barata, F., Filler, A., Büchter, D., Brogle, B., Heldt, K., Gindrat, P., Farpour-Lambert, N., l’Allemand, D. (2017) Design and Evaluation of a Mobile Chat App for the Open Source Behavioral Health Intervention Platform MobileCoach, In: Maedche A., vom Brocke J., Hevner A. (eds) Designing the Digital Transformation. DESRIST 2017. Lecture Notes in Computer Science, vol 10243. Springer: Berlin; Germany, 485-489. (Paper-PDF | Poster-PDF | Slide-PDF | Screencast)
Filler, A., Kowatsch, T., Haug, S., Wahle, F., Staake, T. & Fleisch, E. (2015) MobileCoach: A Novel Open Source Platform for the Design of Evidence-based, Scalable and Low-Cost Behavioral Health Interventions – Overview and Preliminary Evaluation in the Public Health Context. Wireless Telecommunications Symposium 2015 (WTS 2015), New York, USA. ***Outstanding Paper Award & Best Graduate Student Paper Award*** PDF