Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Language Models: Multi-Turn Interaction and Multimodal Treatment Plan Generation

2026-06-04

AI Summary

This study addresses the limitations of existing AI-assisted traditional Chinese medicine (TCM) diagnostic tools—namely, opaque reasoning, passive interaction, and overly simplistic treatment recommendations—by proposing a visualized diagnosis and treatment system that integrates knowledge graphs with large language models. The system employs a four-stage symptom-matching process, an active questioning mechanism optimized via a genetic algorithm constrained by a TCM knowledge graph, and a multimodal treatment generation module incorporating 3D meridian-acupoint models and AI-generated imagery. Experimental results demonstrate a 32% reduction in non-standard outputs, significantly enhanced diagnostic credibility (Cohen’s d = 1.82), reduced cognitive load, and superior clinical utility of treatment recommendations, as evidenced by higher scores in paired evaluations (4.21 vs. 2.95 across 30 cases).

Abstract

Aim: Existing AI-assisted traditional Chinese medicine diagnostic tools suffer from opaque reasoning processes, passive interaction, and limited treatment plan presentation. This study proposes a knowledge-enhanced visual diagnostic system to improve the transparency and interpretability of syndrome differentiation and treatment. Methods: The system is built upon a Neo4j knowledge graph comprising 241 syndromes, 1,263 symptoms, and 2,485 relations. It incorporates a four-stage symptom matching pipeline (exact, semantic, fuzzy, and large language model verification), an information gain-driven proactive questioning strategy optimized with genetic algorithms, and a multimodal treatment presentation integrating artificial intelligence-generated illustrations, three-dimensional meridian-acupoint models, and evidence-based literature. Results: Knowledge graph constraints reduced non-standard outputs by 32%. Case studies validated the effectiveness of the interactive workflow across patient self-assessment, clinician-assisted diagnosis, and traditional Chinese medicine education. Automated paired-comparison evaluation across 30 cases further demonstrated significant improvements in diagnostic trust (Cohen's d = 1.82, p < 0.001), reduced cognitive load (improvements in four of five dimensions), and higher credibility of evidence-based references (4.21 vs. 2.95). Conclusions: The proposed system enhances the transparency of traditional Chinese medicine diagnostic reasoning and the interpretability of treatment plans through knowledge graph-driven visualization and multimodal interaction, offering a practical solution for trustworthy artificial intelligence-assisted traditional Chinese medicine applications.

Problem

• Traditional Chinese Medicine
• AI-assisted diagnosis
• Transparency
• Interpretability
• Treatment plan visualization

Innovation

• knowledge graph
• large language model
• multimodal visualization
• proactive questioning
• evidence-based TCM