Personalized Intelligent Syndrome Differentiation Guided By TCM Consultation Philosophy.

Area of Science:

• Computational Medicine
• Artificial Intelligence in Healthcare
• Traditional Chinese Medicine

Background:

• Traditional Chinese Medicine (TCM) diagnosis relies heavily on patient inquiry.
• Existing AI diagnostic methods lack patient engagement, depth, and validation.
• Abstract TCM knowledge and limited datasets pose challenges for computational approaches.

Purpose of the Study:

• To develop a novel knowledge representation technique for TCM inquiry.
• To create an intelligent consultation model for accurate syndrome differentiation.
• To address limitations in current AI-driven TCM diagnostic tools.

Main Methods:

• Constructed a symptom-syndrome mapping based on TCM diagnostics.
• Developed an inquiry knowledge base using TCM's "Ten Brief Inquiries".
• Proposed an assessment approach for an intelligent consultation model, evaluating question-answer quality, model accuracy, and question count.

Main Results:

• The developed approach demonstrated accurate syndrome differentiation in TCM.
• Generated question-answer pairs for simulated consultations were relevant, accurate, and efficient.
• Manual evaluation by TCM specialists confirmed the model's effectiveness.

Conclusions:

• The novel knowledge representation and intelligent consultation model significantly improve AI-based TCM diagnosis.
• The method enhances patient engagement and provides a more robust validation of TCM diagnostic AI.
• This work offers a promising direction for advancing computational methods in Traditional Chinese Medicine.