Glycobuddy: Building Scalable and User-Friendly AI Applications for Diabetic Dietary Management by Integrating FastAPI, PostgreSQL, and AI-Driven Recommendations

Muhammad Ibrahim Baba, Abdullahi Musa, Kamorudeen Hassan Taiwo, Ajayi Ore-Ofe, Nnamani Stanley Wisdom, Ibrahim Ibrahim

Abstract


Diabetic patients face significant challenges in managing their dietary habits, particularly in regions like Nigeria, where traditional diets are rich in carbohydrates. This paper presents Glycobuddy, a scalable and AI-powered dietary management application designed specifically for diabetic patients in these regions. The app integrates the CLIP model for meal image classification and Gemini Large Language Models (LLMs) for natural language processing, providing personalized dietary recommendations based on glycemic index and patient dietary needs. Built using FastAPI and PostgreSQL for backend scalability and React Native for a cross-platform user interface, the system ensures real-time performance and secure data management. Glycobuddy achieved an 84.37% accuracy in classifying 24 Nigerian dishes, offering tailored nutritional advice to users. This paper discusses the system architecture, design decisions, performance evaluation, and future improvements, including the integration of real-time health data and enhanced personalization for diabetic dietary management. 


Full Text:

PDF

References


International Diabetes Federation, "Diabetes Facts and Figures," 2019.

American Diabetes Association, "Standards of Medical Care in Diabetes—2020," Clinical Diabetes, vol. 38, no. 1, pp. 10-38, 2020.

E. J. Topol, Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. Basic Books, 2019.

International Diabetes Federation, "Diabetes Facts and Figures," 2019.

Zhang, J., Li, J., & Lin, Z. (2015). Snap-n-Eat: A mobile food recognition system. Journal of Medical Internet Research, 17(8), 234-241.

Modave, F., Bian, J., Rosenberg, E., Mendoza, T. M., Liang, Z., Bhosale, R., Maeztu, C., Rodriguez, C., & Cardel, M. I. (2016). DiaFit: The development of a smart app for patients with type 2 diabetes and obesity. JMIR Diabetes, 1(2), e5.

Darby, A., Strum, M. W., Holmes, E., & Gatwood, J. (2016). A review of nutritional tracking mobile applications for diabetes patient use. Diabetes Technology & Therapeutics, 18(3), 200-212.

Petersen, M., & Hempler, N. F. (2017). Development and testing of a mobile application to support diabetes self-management for people with newly diagnosed type 2 diabetes: A design thinking case study. BMC Medical Informatics and Decision Making, 17(91). https://doi.org/10.1186/s12911-017-0493-6

Trawley, S., Baptista, S., Browne, J., Pouwer, F., & Speight, J. (2017). The use of mobile applications among adults with type 1 and type 2 diabetes. Diabetes Technology & Therapeutics, 19(12), 730-738.

Chavez, S., Fedele, D., Guo, Y., Bernier, A., Smith, M., Warnick, J., & Modave, F. (2017). Mobile apps for the management of diabetes. Diabetes Care, 40(10), e145-e146.

Schmocker, K., Zwahlen, F., & Denecke, K. (2018). Mobile app for simplifying life with diabetes: Technical description and usability study of GlucoMan. JMIR Diabetes, 3(1), e6.

Weatherall, J., Paprocki, Y., Meyer, T., Kudel, I., & Witt, E. (2018). Sleep tracking and exercise in patients with type 2 diabetes mellitus (Step-D). JMIR mHealth and uHealth, 6(6), e131.

Shan, R., Sarkar, S., & Martin, S. S. (2019). Digital health technology and mobile devices for the management of diabetes mellitus: State of the art. Diabetologia, 62(6), 877-887.

Joshua, S. R., Abbas, W., & Lee, J.-H. (2023). M-Healthcare model: An architecture for a type 2 diabetes mellitus mobile application. Applied Sciences, 13(8), 200-212.


Refbacks

  • There are currently no refbacks.