INTELLIGENT MEDICAL AI CHATBOT

Abstract: Artificial intelligence and natural language processing have opened up new possibilities for healthcare delivery, yet patients in rural and underserved regions still struggle to get timely medical consultations, which often means delayed diagnoses and complications that could have been avoided. This paper presents an Intelligent Medical Chatbot that pairs an interactive 3D human body visualization system with a custom deep learning model, aimed at giving users real-time symptom assessment and preliminary diagnosis support. The framework brings together a fine-tuned Bidirectional Encoder Representations from Transformers (BERT) model for intent classification and entity recognition, a Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) hybrid for multi-label disease prediction, and a WebGL-rendered 3D anatomical interface where users can simply click on the body region that's bothering them. On a curated medical symptom-disease dataset, the system reaches high diagnostic accuracy while keeping response latency under a second. Our experiments show it outperforming existing rule-based and single-modal chatbots on prediction accuracy, user engagement, and clinical relevance. Overall, the work offers a scalable, accessible way to provide preliminary healthcare assistance across web and mobile platforms, with no specialized hardware required.

Keywords: Medical chatbot, deep learning, BERT, CNN-LSTM, 3D human visualization, symptom checker, healthcare AI, natural language processing, real-time diagnosis.