Food and Nutrition Recommendation based Therapy for T2DM using User-User Collaborative Filtering Model

Abstract

A reliable food plan is essential for Type-2 Diabetes Mellitus (T2DM) in order to sustain ideal glucose control and prevent long-term issues. Individual inclinations, lifestyle habits, and peer-based behavioral likenesses are typically overlooked by traditional food planning approaches. In order to provide T2DM patients, a modified dietary advice model presents a food and nutrition recommendation therapy method that creates the use of a User-User Collaborative Filtering Algorithm (UUCFA). The proposed strategy values interpersonal harmony based on these clinical indicators, dietary consumption patterns, lifestyle choices, and demographics inputs. The method suggests nutrient-dense meals that satisfy diabetic dietary requirements based on dietary results and experiences. The collaborative filtering approach promotes relevancy while identifying individual issues that occur in traditional rule-based systems by using collective capacity. Here, recommendation systems based experimental examination employed using real-time datasets, revealed an improved dietary faithfulness, user satisfaction, and accuracy. Hence, UUCF algorithm can aid to improve beneficial outcomes and self-care by serving as a valuable decision-support tool in adapted dietary therapy in T2DM control.