Infectious diseases pose significant challenges to public health systems worldwide, emphasizing the urgent need for innovative tools to aid in early detection and prevention efforts. This study introduces an AI-based medical chatbot model designed for the prediction of infectious diseases. Leveraging natural language processing (NLP) and machine learning techniques, the chatbot analyzes user-provided symptoms and medical history to assess the likelihood of contracting specific infectious diseases. The model integrates a combination of supervised and unsupervised learning algorithms to classify user input, identify relevant patterns, and predict disease outcomes. Additionally, the chatbot employs advanced deep learning architectures, such as recurrent neural networks (RNNs) and transformers, to enhance prediction accuracy and handle complex data structures. Through extensive evaluation on real-world datasets and user interactions, the proposed chatbot demonstrates promising performance in infectious disease prediction, providing valuable insights for early intervention and disease surveillance. This AI-based medical chatbot model offers a scalable and accessible solution for empowering individuals and healthcare providers with timely and accurate infectious disease risk assessment, ultimately contributing to improved public health outcomes and disease management strategies.