Enhancing Personalized Nutrition through BMI Classification and AI Language Models: The NutriFit Approach

Personalized nutrition plays a pivotal role in supporting human health and mitigating chronic lifestyle diseases. Conventional diet advisory platforms generally follow fixed, one-size-fits-all guidelines and often fall short in addressing unique individual physiological needs. To overcome these limitations, this study introduces NutriFit- an intelligent personalized nutrition system that leverages Body Mass Index (BMI) evaluation combined with advanced large language models (LLMs) to deliver highly customized meal plans. The proposed framework collects key user inputs such as height, weight, age, gender, and physical activity level. It then computes the BMI value and classifies the individual into appropriate health categories. Based on this assessment, the system automatically generates a tailored prompt and forwards it to a large language model, which produces context-sensitive dietary suggestions in real time. Developed as a scalable web application with a layered modular design, NutriFit integrates user data management, health analytics, and AI inference modules. In contrast to conventional rule-driven systems that depend on pre-defined meal templates, NutriFit generates dynamic and responsive recommendations. The results underscore the effectiveness of merging traditional health metrics with cutting-edge artificial intelligence to improve personalization, accessibility, and precision in digital nutrition services.