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{203470,
        author = {Siddhi and Jannyabi Gupta and Riddhi and Koustubh Raj},
        title = {MediSense AI using LLM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {12726-12730},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203470},
        abstract = {Artificial intelligence is becoming an increasingly popular tool in healthcare organizations to help expedite and enhance the quality of clinical decisions. Most of the currently existing prediction tools are disease-specific and rely almost entirely on structured inputs like glucose level, blood pressure, cholesterol or body mass index. In this work, I will introduce a multi-disease prediction platform, MediSense AI, that incorporates both traditional machine learning models and Large Language Models to enhance clinical outcomes and user experience. The proposed system predicts the risk of Diabetes, Heart Disease, Liver Disease, and Parkinson's Disease by accepting both medical parameters, and symptom descriptions that are written in natural language. K-Nearest Neighbors, Random Forest, XGBoost, Naive Bayes, and Support Vector Machine are algorithms used depending on the disease and data required. The LLM aspect aids in the interpretation of symptoms, the explanation of results in a simple language, and the Humanization of the application itself. The platform is developed as a web app in Python, Streamlit, and Django. The study suggests that a hybrid solution can enhance accessibility, response time and usability during preliminary health-risk assessment.},
        keywords = {Multi-disease prediction, Large Language Models, healthcare AI, machine learning, Streamlit, Django, KNN, Random Forest, XGBoost, disease detection, medical chatbot, predictive analytics.},
        month = {May},
        }