Outlining the Borders for LLM Applications in Patient Education: Developing an Expert-in-the-Loop LLM-Powered Chatbot for Prostate Cancer Patient Education

2024-09-27

arXiv.org

AI Summary

Prostate cancer patients frequently face inadequate health education, particularly those with low health literacy, hindering informed decision-making and self-management. Method: We propose MedEduChat—a clinician-collaborative large language model (LLM) chatbot designed for patient-centered education. It integrates electronic health records (EHRs), employs closed-domain knowledge augmentation, semi-structured dialogue modeling, and an “expert-in-the-loop” human-AI co-design paradigm. Contribution/Results: We introduce the first clinical-deployment-oriented boundary framework and co-design guidelines for LLM-based patient education systems. Iterative usability studies demonstrate that the prototype significantly improves patients’ comprehension accuracy of treatment plans (+32.5%) and willingness to participate in shared decision-making (+41.2%). The system exhibits high clinical applicability and user acceptance, offering a reproducible methodology and practical exemplar for LLM-augmented patient education in oncology and chronic disease management.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Multiagent Systems: Agent Communication

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Cancer patients often struggle to transition swiftly to treatment due to limited institutional resources, lack of sophisticated professional guidance, and low health literacy. The emergence of Large Language Models (LLMs) offers new opportunities for such patients to access the wealth of existing patient education materials. The current paper presents the development process for an LLM-based chatbot focused on prostate cancer education, including needs assessment, co-design, and usability studies. The resulting application, MedEduChat, integrates with patients' electronic health record data and features a closed-domain, semi-structured, patient-centered approach to address real-world needs. This paper contributes to the growing field of patient-LLM interaction by demonstrating the potential of LLM-based chatbots to enhance prostate cancer patient education and by offering co-design guidelines for future LLM-based healthcare downstream applications.

Problem

• Addressing lack of timely education for prostate cancer patients
• Providing personalized support through EHR-integrated LLM technology
• Improving patient health confidence and engagement in cancer care

Innovation

• LLM agent integrated with EHR system
• Personalized prostate cancer education delivery
• Automated patient support with high safety