AI-Based Fake Media Detection Using Machine Learning and Natural Language Processing

Authors

  • BALE HEMANTH KUMAR,B. Suryanarayana Murthy Author

DOI:

https://doi.org/10.62643/

Keywords:

Keywords:Healthcare Chatbot, Triage System, Django, Artificial Intelligence, Patient Management, Doctor Dashboard, NLP, Medical Decision Support

Abstract

The integration of Artificial Intelligence (AI) in healthcare has significantly improved
patient care, accessibility, and decision-making processes. This project presents an AIBased
Healthcare Chatbot with an integrated Patient-Doctor Management System
designed to provide preliminary medical assistance and streamline communication
between patients and healthcare providers.
The system is developed using the Django web framework and incorporates user
authentication for three roles: patients, doctors, and administrators. Patients can register,
log in, and interact with an AI-powered chatbot that provides medical advice based on
user input. The chatbot utilizes Natural Language Processing (NLP) techniques to
understand patient symptoms and generate appropriate responses.
A key feature of the system is the Intelligent Triage Engine, which evaluates patient input
and classifies cases into severity levels such as EMERGENCY, URGENT, ROUTINE,
and SELF-CARE. This classification helps prioritize patient cases and ensures that
critical conditions receive immediate attention. The chatbot responses, along with
severity levels, are stored in a database as chat logs.Doctors can access a dedicated
dashboard where patient queries are displayed and sorted based on severity. This allows
healthcare providers to focus on high-priority cases first, improving efficiency and
response time. The system also supports real-time interaction through an API-based chat
interface.

Downloads

Published

04-04-2026

How to Cite

AI-Based Fake Media Detection Using Machine Learning and Natural Language Processing. (2026). International Journal of Engineering Research and Science & Technology, 22(2), 624-634. https://doi.org/10.62643/