AI-driven healthcare chatbots: a retrieval-augmented large language model framework for revolutionizing patient care
Abstract
The integration of artificial intelligence into clinical workflows has begun to reshape how patients seek information, manage chronic disease, and interact with health systems. Conversational agents built on large language models now offer a practical pathway toward scalable, round the clock patient engagement, yet most existing systems struggle to balance fluent dialogue with verifiable clinical grounding. This chapter develops and evaluates an AI driven healthcare chatbot that couples a retrieval augmented generation pipeline with the Llama 2 7B chat model to produce contextually accurate, evidence linked responses to patient queries. Heterogeneous healthcare resources, including clinical guidelines, patient education material, and de identified records, are decomposed into overlapping text segments, transformed into dense vector embeddings, and indexed using the Pinecone vector database for low latency semantic search. The resulting architecture separates a backend indexing pipeline from a frontend query resolution pipeline, allowing the system to retrieve the most semantically relevant evidence before a response is synthesized. Empirical evaluation across eight hundred simulated clinical queries shows an accuracy of 92.5 percent, a precision of 89.3 percent, a recall of 94.7 percent, and an F1 score of 91.8 percent, with an average response latency of 320 milliseconds. The chapter extends the original study by situating the system within the broader literature on medical…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.