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{203261,
        author = {Shubham Dashore and Suryansh Singh and Tanisha Agrawal and Shivam Prajapati and Vickey Bagde and Aarti Joshi},
        title = {An NLP-Driven Healthcare Information Chatbot Utilizing Knowledge Base Retrieval and Regional Disease Patterns},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {12261-12270},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203261},
        abstract = {In a world where everything has turned out to be more digital, finding reliable health information has become a challenge, and most people have to depend on unverified sources of information on the internet, resulting in misinformation and misinformed health choices. In this paper, we will design and develop a healthcare chatbot based on AI that will be able to provide relevant, accurate health advice in response to natural language queries. Using a combination of sophisticated natural language processing methods, which is a fine-tuned BERT model, and a structured geographical symptom-disease knowledge base, the system intelligently interprets queries provided by the user, including regional and seasonal variations, to provide reliable health advice. The retrieval mechanism uses semantic matching by cosine similarity to retrieve pertinent information using a large validated health database. Such a combined solution increases semantic knowledge, facilitates the regional awareness of the disease, and increases the accuracy of the response. Assessment of a wide range of health-related queries proves effectiveness of the system with great semantic alignment scores and strong intent recognition, therefore, exemplifying the prospects of integrating NLP models with local health information to deliver reliable health information.},
        keywords = {Healthcare Information, Natural Language Processing, Knowledge Base, BERT},
        month = {May},
        }