Fuzzy Logic Based Personalised Diet Recommendation engine for Dietary Prevention and Control of Diabetes

Abstract

Dietary management is very important not only to prevent Type 2 diabetes mellitus but also to treat it. Despite the fact that there are great strides in knowledge dietary strategies, many patients continue to rely on generic advice instead of individualized plans. There is limited integration of technology-based tools into routine care to assist healthcare providers in delivering personalized dietary recommendations. This research developed a personalized system that aligns dietary recommendations with the health conditions and preferences of diabetes patients. The system used Fuzzy Logic interpretability capabilities for both diabetes prediction and dietary recommendation generation. The system derives its framework from the Nigerian food composition table thus providing culturally appropriate advice to its users. The FL system transforms prediction outputs to dietary recommendations according to rules defined by three predictive factors of HbA1c, BMI and Age thus enabling clinical translation from diagnosis to therapeutic actions. Through the Flask-based web interface patients can submit patient information to obtain performance scores together with personalized dietary recommendation in real time. The recommendation helps people better manage their blood sugar and overall health, which is essential for preventing serious long-term complications. It offers a more effective way to give dietary advice, improving patient outcomes and making healthcare more efficient.