Adaptive Digital Assistants for Type-2 Diabetes Patients
Diabetes is rising globally, with 422 million adults’ worldwide currently living with the condition, equating to 1 in 11 individuals. In Switzerland, diabetes is likewise becoming more prevalent, with 7.4% of the adult population (469 400 adults) diagnosed. Shadowed amongst these figures is the growing burden on healthcare systems facing increasing pressures to maintain or improve health outcomes whilst coping with additional patient numbers. Failure to effectively self-manage type-2 diabetes can lead to a variety of life-changing complications such as cardiovascular disease, kidney disease, vision loss, neuropathy and amputation amongst others. Thusly, tools to enable effective self-care and health literacy are vital. This project, therefore, introduces digital coaching through a text-based healthcare chatbot embedded in a smartphone application as a strategy to meet the healthcare challenges in type-2 diabetes care for Switzerland, with implications for the wider world.
A variety of effective diabetes management programs have been developed combining fitness and nutrition advice to help achieve clinical outcomes such as glycemic control or weight loss. Although useful, these programs rely too far on human coaching only, and thus cannot be scaled effectively across all patients. Our approach is to utilize a socially-oriented chatbot to deliver prompts and reminders for treatment activities, whilst enabling another channel for clinician-patient monitoring and communication. To do this we will assess various theories such as social determination theory (SDT) and communication strategies such as motivational interviewing (MI). SDT posits that all humans are growth-oriented, and strive for autonomy (ability to effect outcomes), competence (self-efficacy to achieve desired outcomes) and relatedness (social connection with others). MI provides a set of practical tools such as expressing empathy, supporting self-efficacy, reflective listening and other techniques in pursuit of these SDT aims. Both approaches have been validated in a variety of traditional face-to-face coach settings, and thus remain an area of critical research interest for digital coaching and text-based healthcare chatbots.
For the current project, our coaching approach will be rooted in relevant concepts such as SDT/MI, and will link with the established Swiss Diafit program. Diafit aims to encourage nutrition and fitness goals amongst current type-2 diabetics, and is based upon the widely applied Diabetes Prevention Program (DPP). DPP utilizes lifestyle coaches, frequent contact with patients, health literacy, physical activity sessions, monitoring and feedback and is thus perfectly suited for translation to a digital coaching approach, which offers continuous support and utilizes smartphone data to make “just-in-time adaptive interventions” in the everyday life of individuals.
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)