A Knowledge-Driven Approach for Enhancing Chronic Condition Accessibility with Large Language Models and Semantic Search

This research introduces a knowledge-driven approach for enhancing chronic condition accessibility through the development of WellLife, a specialized chatbot designed to assist individuals in managing long-term health conditions. Patients with chronic diseases often struggle to access timely and personalized health information, which adversely impacts selfcare and decision-making. The primary objective is to develop a system capable of understanding and responding to complex medical queries, delivering tailored advice based on users’ specific health needs. By leveraging advanced natural language processing techniques, Large Language Models (LLMs), and machine learning algorithms, WellLife integrates a vast, curated medical knowledge base with semantic search capabilities to generate reliable and contextually relevant responses. The system was rigorously evaluated using real-life scenarios, with results demonstrating that WellLife can accurately answer most medical queries, thereby significantly aiding patient selfmanagement and improving overall quality of life. Future enhancements are anticipated to involve the integration of more sophisticated machine learning models and an expanded knowledge base covering a broader range of medical issues. These findings underscore the potential of technology to bridge existing gaps in healthcare and to support patients on a global scale.