NutriGuard: LLM-Driven Nutritional Assessment for Chronic Disease Prevention

This conference paper presents NutriGuard, an innovative multimodal AI framework integrating optical character recognition (OCR), deep learning, and fine-tuned large language models (LLMs) for personalized nutrition management. The system delivers real-time, context-aware dietary recommendations tailored to users’ health profiles, advancing AI-driven preventive healthcare through multilingual, clinically validated frameworks.

Authors:

• Md Azizul Hakim (Lead Author, Bangladesh Sweden Polytechnic Institute, Bangladesh)
• Rashedul Arefin Ifty (International Islamic University Chittagong, Bangladesh)
• Khaled Eabne Delowar (International Islamic University Chittagong, Bangladesh)
• Sazzad Hossen Chowdhury (International Islamic University Chittagong, Bangladesh)
• Imdadur Rashid (International Islamic University Chittagong, Bangladesh)
• Md Shakib (International Islamic University Chittagong, Bangladesh)

DOI: 10.1109/QPAIN66474.2025.11171750

Key Contributions:

• Hybrid OCR pipeline combining PaddleOCR (English) and Surya (Bengali) with CNN-based fallback
• Fine-tuned Llama-3.2 model on clinical guidelines for health condition-specific recommendations
• Multilingual, clinically-validated framework for dietary risk mitigation
• Modular design permitting adaptation to regional food cultures and emerging research

Topics: Big Data, Artificial Intelligence, Machine Learning, Healthcare AI

Recommended citation: Hakim, M.A., Ifty, R.A., Delowar, K.E., Chowdhury, S.H., Rashid, I., & Shakib, M. (2025). "NutriGuard: LLM-Driven Nutritional Assessment for Chronic Disease Prevention." IEEE Conference Proceedings. DOI: 10.1109/QPAIN66474.2025.11171750
Download Paper