Copyright © 2025 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{169375,
        author = {Abhi Akshat and Kritika Aggarwal and Sheenam Naaz},
        title = {AI Agent And NLP Based Medical Differential Diagnosis And History Analyzer},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {1223-1232},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169375},
        abstract = {In the era of rapid advancements in Artificial Intelligence (AI) and Large Language Models (LLMs), these technologies are increasingly being applied in the medical field to enhance efficiency and accuracy. One area where LLMs are making a significant impact is in automating tasks like medical history recording and analysis. By leveraging Natural Language Processing (NLP), AI models can streamline the process, reducing the time spent on mundane tasks and improving the overall quality of care provided to patients. This paper proposes a system that utilizes LLMs powered AI Agents, specifically models like Llama, to automate the collection and analysis of patient medical history. The system functions as a virtual assistant, interacting with patients to gather information on their symptoms and medical background. It then provides doctors with a summarized history and a differential diagnosis, ranked in order of likelihood, along with potential causes. The model also considers regional factors, improving diagnostic accuracy by incorporating location-based insights. The goal is to ease the workload of healthcare providers, enabling them to focus more on patient care. The system uses fine-tuning techniques to continuously improve its performance over time. This paper details the system’s architecture, training methodologies, and the results of its implementation. By automating medical history recording and analysis, this AI-driven approach has the potential to enhance diagnostic accuracy, speed up decision-making, and ultimately improve patient outcomes in clinical settings.},
        keywords = {Large Language Models, Natural Language Processing, Artificial Intelligence, Machine Learning, LLaMA},
        month = {November},
        }