DiagLink: A Dual-User Diagnostic Assistance System by Synergizing Experts with LLMs and Knowledge Graphs

2026-01-28

AI Summary

This work proposes a collaborative diagnostic assistance framework designed for both patients and physicians to address the uneven distribution of medical resources and limitations in existing intelligent diagnostic systems, particularly their inadequate support for dual-user interaction and dynamic knowledge integration. The system employs guided dialogue to collect patient history, synergistically combines large language models with medical knowledge graphs for reasoning, and incorporates physician feedback to enable continuous validation and evolution of medical knowledge. It innovatively supports adaptive interactions for both clinicians and patients, dynamic visualization of medical histories, and unified presentation of multi-source evidence. User studies and expert interviews demonstrate that the system significantly enhances diagnostic efficiency and user satisfaction, offering a generalizable and practical paradigm for the design of AI-assisted diagnostic systems.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Humans and AI: Intelligent User Interfaces
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

The global shortage and uneven distribution of medical expertise continue to hinder equitable access to accurate diagnostic care. While existing intelligent diagnostic system have shown promise, most struggle with dual-user interaction, and dynamic knowledge integration -- limiting their real-world applicability. In this study, we present DiagLink, a dual-user diagnostic assistance system that synergizes large language models (LLMs), knowledge graphs (KGs), and medical experts to support both patients and physicians. DiagLink uses guided dialogues to elicit patient histories, leverages LLMs and KGs for collaborative reasoning, and incorporates physician oversight for continuous knowledge validation and evolution. The system provides a role-adaptive interface, dynamically visualized history, and unified multi-source evidence to improve both trust and usability. We evaluate DiagLink through user study, use cases and expert interviews, demonstrating its effectiveness in improving user satisfaction and diagnostic efficiency, while offering insights for the design of future AI-assisted diagnostic systems.

Problem

• dual-user interaction
• dynamic knowledge integration
• diagnostic assistance
• medical expertise shortage
• intelligent diagnostic system

Innovation

• dual-user interaction
• large language models
• knowledge graphs
• collaborative reasoning
• dynamic knowledge integration