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{180939,
        author = {Sayali Belhe and Pranjali Gadkari and Vaishnavi Kubade and Chetanya Bhadravati},
        title = {MedSwift: Biomedical Knowledge Extraction by Implementing Named Entity Recognition using LLM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {3730-3734},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180939},
        abstract = {The project “Biomedical Knowledge Extraction by Implementing Named Entity Recognition Using LLM” focuses on improving healthcare services by automating the extraction and the structural organization of important medical information from unstructured patient reports. Such a system has the capacity to locate, understand and categorize core medical entities such as diseases, drugs, or procedures with the help of advanced Large Language Models (LLMS) integrated with Named Entity Recognition (NER). This change of holistic information as a result of transforming unstructured reports into structured, and specific scopes enables speedy retrieval of information by the medical practitioners, thereby aiding in decision making and enhancing the overall patient experience. This is also possible due to one of the system's peculiarities, user-friendly interface that enables doctors to view short summarized versions of reports and hence reducing the hours spent looking at convoluted patient histories. It also includes within the project, to create a chatbot allowing patients to ask questions and receive validated answers straight from the LLM yet verified and approved by the doctor, which further increases accessibility and patient engagement.},
        keywords = {BioMedical Data, NER, LLM, GenAI, Llama, HealthCare Question Answering and Validation},
        month = {June},
        }