This study provides a systematic evaluation and comparative analysis of current research on AI-powered chatbots designed as virtual medical assistants, emphasizing the core technical frameworks and innovations driving their development. While existing literature in this domain is extensive, this study systematically evaluates advancements in healthcare chatbots by classifying methodologies according to their design principles and operational frameworks. The analysis examines experimental approaches, evaluation metrics, and researcher conclusions, as well as documented performance benchmarks. By synthesizing insights from prior studies, the paper identifies enduring challenges, including training data biases, constraints in contextual understanding, and ethical dilemmas in patient engagement. Serving as a comparative resource, this review clarifies distinctions among healthcare chatbot models, which play a growing role in improving remote healthcare access. Building on these findings, the paper introduces a novel AI-driven healthcare chatbot framework that combines natural language processing (NLP), machine learning (ML), and domain-specific medical expertise. The proposed system enables users to check symptoms early and get reliable health advice from home, acting as a first step before visiting a doctor. It’s built to balance three priorities: getting the facts right (accuracy), handling thousands of users at once (scalability), and keeping costs low so even small clinics can afford it. By tackling these areas, the goal is to make healthcare more accessible—whether you’re in a busy city or a remote village. Faster access to guidance means fewer delays in catching serious issues early, which could save lives through smarter use of health data.
Keywords
Artificial Intelligence, Chatbots, healthcare systems, Machine Learning, Natural Language Processing, medical healthcare
