Authors S AnbarasanDepartment of Electronics and Communication Engineering, AVS College of Engineering, Salem, Tamilnadu, IndiaSathish Kumar MDepartment of Electronics and Communication Engineering, AVS College of Engineering, Salem, Tamilnadu, India Abstract The rapid advancement of Artificial Intelligence (AI) and Large Language Models (LLMs) has transformed the delivery of healthcare services by enabling intelligent, interactive, and personalized medical assistance. The increasing demand for accessible healthcare information, coupled with the shortage of medical professionals in many regions, has highlighted the need for AI-powered virtual health assistants capable of providing reliable preliminary healthcare guidance. This paper presents an AI-Powered Health Assistant Using Large Language Models for Personalized Healthcare Support, designed to offer users natural language-based interactions for symptom assessment, health-related queries, medication information, wellness recommendations, and nutritional guidance. The proposed system leverages advanced Large Language Models to understand user inputs, interpret medical concerns, and generate context-aware responses that are accurate, informative, and easy to understand. Additionally, the system integrates image-based food recognition technology to analyze uploaded food images and provide detailed nutritional information, calorie estimation, and dietary recommendations for promoting healthy lifestyles. The architecture incorporates secure user authentication, conversational AI, medical knowledge retrieval, personalized recommendation modules, and continuous learning mechanisms to improve response quality through user feedback and model refinement. Furthermore, the framework emphasizes data privacy, secure communication, and ethical AI practices to protect sensitive healthcare information while maintaining user trust. Experimental evaluation demonstrates that the proposed health assistant delivers fast, reliable, and personalized healthcare support, significantly enhancing user engagement and improving access to essential medical information without replacing professional medical consultation. The system serves as a practical solution for preliminary health assessment, preventive healthcare awareness, nutritional counseling, and patient education, making healthcare services more accessible, efficient, and user-friendly. The proposed AI-powered healthcare assistant contributes to the growing field of intelligent digital healthcare by combining conversational AI, large language models, and personalized health analytics into a unified platform that supports informed health decision-making and promotes overall well-being. Keywords Artificial Intelligence (AI) Large Language Models (LLMs) AI Health Assistant Personalized Healthcare Healthcare Chatbot Conversational AI Medical Question Answering Symptom Assessment Health Monitoring Nutrition Analysis Food Image Recognition. Citation of this Article S Anbarasan, & Sathish Kumar M. (2026). AI-Powered Health Assistant Using Large Language Models for Personalized Healthcare Support. Current Journal of Engineering and Science Research. 3(6), 30-40. Article DOI: https://doi.org/10.47001/CJESR/2026.306004 Licence Copyright (c) 2026 Current Journal of Engineering and Science Research. This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International Licence. References E. Topol, Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. New York, NY, USA: Basic Books, 2019. World Health Organization (WHO), "Global Strategy on Digital Health 2020–2025," WHO, Geneva, Switzerland, 2021. J. Devlin, M. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," Proc. NAACL-HLT, 2019, pp. 4171–4186. T. Brown et al., "Language Models are Few-Shot Learners," Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 1877–1901, 2020. OpenAI, "GPT-4 Technical Report," 2023. Google DeepMind, "Gemini: A Family of Highly Capable Multimodal Models," 2023. D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed., Pearson, 2024. R. Szeliski, Computer Vision: Algorithms and Applications, 2nd ed., Springer, 2022. C. C. Aggarwal, Artificial Intelligence: A Textbook, Springer, 2021. I.Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016. A.Esteva et al., "A Guide to Deep Learning in Healthcare," Nature Medicine, vol. 25, no. 1, pp. 24–29, 2019. W. H. Organization, "Ethics and Governance of Artificial Intelligence for Health," WHO, Geneva, Switzerland, 2021. S. Holzinger, “From machine learning to explainable ai,” in 2018 world symposium on digital intelligence for systems and machines (DISA). IEEE, 2018, pp. 55–66. K. Wang, D. S. Varma, and M. Prosperi, “A systematic review of the effectiveness of mobile apps for monitoring and management of mental health symptoms or disorders,” Journal of psychiatric research, vol. 107, pp. 73–78, 2018. C. Oliveira, A. Pereira, P. Vagos, C. No´brega,J. Gonc¸alves, and B. Afonso, “Effectiveness of mobile app-based psychological interventions for college students: a systematic review of the literature,” Frontiers in psychology, vol. 12, p. 647606, 2021. C. Nash, R. Nair, and S. M. Naqvi, “Machine learning in adhd and depression mental health diagnosis: A survey,” IEEE Access, 2023. K. Iyortsuun, S.-H. Kim, M. Jhon, H.-J. Yang, and S. Pant, “A review of machine learning and deep learning approaches on mental health diagnosis,” in Healthcare, vol. 11, no. 3. MDPI, 2023, p. 285. X. Wu, X. Guo, Z. Zhang et al., “The efficacy of mobile phone apps for lifestyle modification in diabetes: systematic review and meta-analysis,” JMIR mHealth and uHealth, vol. 7, no. 1, p. e12297, 2019. K. I. Roumeliotis, N. D. Tselikas, and D. K. Nasiopoulos, “Llama 2: Early adopters’ utilization of Meta’s new open-source pretrained model,” 2023. Y. Natarajan, S. P. KR, S. Pandian, S. U. Geetha, and S. Senthilkumar, “Enhancing medical information retrieval with a language model,” in 2024 International Conference on Cognitive Robotics and Intelligent Systems (ICC-ROBINS). IEEE, 2024, pp. 437–441. Y. S. Kıyak, E. Emekli et al., “A prompt for generating script con- cordance test using chatgpt, claude, and llama large language model chatbots,” Revista Espan˜ola de Educacio´n Me´dica, vol. 5, no. 3, 2024. Y. Li, Z. Li, K. Zhang, R. Dan, S. Jiang, and Y. Zhang, “Chatdoctor: A medical chat model fine- tuned on a large language model meta-ai (llama) using medical domain knowledge,” Cureus, vol. 15, no. 6, 2023.
