AI-Powered Medical Chatbot for Predicting Infectious Diseases
Keywords:
Artificial Intelligence, Chatbot, LSTM Algorithm, Machine Learning, Deep Learning, Natural Language Processing, Query ProcessingAbstract
The difficulties in accessing hospital and doctors personally on regular basis there is need for localized people to connect to medical practitioners easily, with the help of machine learning approach. The system combines two powerful technologies: Natural Language Processing (NLP) and Neural Networks, to help you get reliable medical advice anytime you need it. The proposed system leverages a combination of NLP models, including transformers like CNN, BERT (Bidirectional Encoder Representations from Transformers), and neural network architectures like LSTM to interpret and respond to user queries effectively. The chatbot incorporates a user-friendly interface allowing patients to converse naturally about their symptoms, medical history, and concerns, and getting accurate information in a simple and friendly way. To make this possible, we train our system using a wide range of medical texts so it can learn about different health topics. We also use special computer techniques to help it understand and talk like a human. This way, when you ask a question, the system can figure out what you mean and give you a response that makes sense. We prioritize your privacy, ensuring strict rules are followed to safeguard your personal information when using this system. “In the end, we test how well the system works by asking it various medical questions and checking if its answers are accurate and helpful. We want to make sure that the Smart Health Buddy is a reliable source of medical information that you can rely on. This system shows how technology can be used to improve healthcare by giving you a friendly and knowledgeable companion that can assist you with your health- related questions. This system is here to make your health journey easier and more convenient.
Downloads
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.