Key result
Community workshops identify 10 priority rural diabetes challenges and co-develop AI-powered mobile health apps.
Why the study?
Diabetes has a disproportionately higher burden in the rural South, where access to specialized diabetes care and technological advances is often inadequate.
A community-based, problem-focused approach can successfully drive the development of contextually appropriate health technologies for diabetes management in low-resource rural settings.
May inform context-specific mHealth development for rural diabetes; leaves open clinical effectiveness in low-resource settings.
Introduction and Objective: Diabetes represents a growing health burden with disproportionately higher prevalence, mortality and morbidity in the rural South, relative to urban counties in the U.S.. In rural areas, access to specialized diabetes care, as well as technological advances, are often inadequate. The objective of this project was to identify region-specific diabetes challenges and develop effective technological solutions for rural communities in the Southeastern U.S. Artificial intelligence and other health technological solutions were used to meet a critical need in rural areas. Methods: A diabetes problem discovery workshop was organized, based on human-centered design and community-based participatory principles. A Steering Committee of rural health leaders helped recruit subject matter experts (SMEs) representing medicine, nursing, pharmacy, nutrition, mental health, public health, laboratory science, and information technology. Participants refined 25 challenges faced by patients and other stakeholders in rural Georgia into ten priority diabetes-focused problems. Technological innovations were then co-developed by computer science students and rural health stakeholders, culminating in a “DiaTech” demonstration day. Results: The problems reflected gaps in clinical practice, systemic care delivery, medication access and adherence, and nutrition and lifestyle support. The need for offline functionality, digital literacy support, and relation-based care was emphasized. Mobile health applications were developed for nutritional guidance, including an AI powered chat-bot that uses food pantry and refrigerator inventory to customize healthy meal planning. Other mobile health applications engaged users with comic-like visuals and interactive guidance on diabetes self-management and culturally tailored education on medications. Conclusion: This community-based, problem-focused approach represents a model for driving contextually appropriate and innovative health technologies for low-resource settings.
No takes yet. Share an insight, caveat, or question.
Glenn et al. (2026) studied Diabetes. Community-based participatory design of health technological solutions was evaluated on Identification of priority diabetes-focused problems and co-development of technological innovations. A community-based participatory workshop identified 10 priority diabetes challenges in rural Georgia and co-developed mobile health applications, including an AI-powered nutritional chat-bot.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: