MediBot An AI-Powered Multi-Disease Diagnostic Web Application

Author(s)	Ms. Aruna N, Mr. Vedhaprakash Guptha S, Mr. Shanmuganandha C S, Mr. Thirumurugan M
Country	India
Abstract	Medibot is a web-based application that uses artificial intelligence (AI) to predict diseases based on symptoms submitted by users. It uses a modern technology stack and incorporates several machine learning models, including Naive Bayes, Random Forest, Logistic Regression, K-Nearest Neighbors (KNN), and XGBoost. Users can choose from different models and receive predictions along with probabilities for each condition. Medibot emphasizes transparency by providing both global and local explanations for its predictions, helping users understand how their symptoms influence results. The dataset for training the models comes from the Mendeley repository and includes over 246,000 rows of medical data. This paper discusses the architecture, model evaluation, and explanation techniques applied in Medibot, concluding with insights on its effectiveness and potential future improvements in AI-assisted healthcare.
Keywords	AI, Disease Prediction, Machine Learning, Medical Diagnostics, React, FastAPI, Web Scraping, Model Explainability, Logistic Regression, Naive Bayes, XGBoost
Field	Engineering
Published In	Volume 7, Issue 6, November-December 2025
Published On	2025-12-10
DOI	https://doi.org/10.36948/ijfmr.2025.v07i06.62916

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research