Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195036,
        author = {C. JULIET LILLYAN and Ms. Yamuna Bee},
        title = {SympAI: A GENERATIVE AI-POWERED HEALTH ASSISTANT},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {5914-5922},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195036},
        abstract = {In the modern world, recent advancements in Artificial Intelligence (AI) and Natural Language Processing (NLP) have revolutionized healthcare by enabling intelligent, data-driven interactions between patients and medical systems. SympAI is a Generative AI-powered health assistant designed to assist patients in understanding symptoms, offering preliminary assessments, and suggesting suitable next steps. The system utilizes Google Gemini large language models through a FastAPI backend with Jinja2 templating to provide a seamless conversational web interface.
This Phase 2 report documents the complete implementation of SympAI, including the system architecture, methodology, algorithms, code implementation, testing results, and deployment process. The system follows a client-server architecture where the frontend captures user symptoms in natural language, the backend processes the input through the Generative AI engine, and returns structured health guidance comprising possible causes, home remedies, and recommendations for when to consult a doctor. Every response includes a mandatory medical disclaimer ensuring ethical AI compliance.
The system was evaluated on multiple metrics including response accuracy, user satisfaction, response latency, and safety compliance. Results demonstrate that SympAI significantly outperforms traditional rule-based symptom checkers with 92% accuracy, 95% user satisfaction, and average response time of 2.1 seconds. The integration of a model fallback strategy ensures high availability across different Gemini model versions.},
        keywords = {Generative AI, Health Assistant, NLP, FastAPI, Google Gemini, Healthcare Automation, Chatbot, Python, SQLAlchemy, Jinja2 Templates, Large Language Models},
        month = {March},
        }