A Semantic Knowledge Graph Linking Diseases, Patterns, Symptoms, and Herbs for Traditional Chinese Medicine
Yuanbai Li
Zenodo (CERN European Organization for Nuclear Research)
Problems Identified (4)
Limited TCM efficacy lists: Simple TCM efficacy lists do not provide a full semantic network over etiology, disease, pattern, symptom, efficacy, and herb concepts.
TCM semantic reasoning support: There is a need for a foundational graph structure to support semantic reasoning and efficacy inference in TCM.
Limited TCM efficacy lists: Simple TCM efficacy lists do not provide a full semantic network over etiology, disease, pattern, symptom, efficacy, and herb concepts.
TCM semantic reasoning support: There is a need for a foundational graph structure to support semantic reasoning and efficacy inference in TCM.
Proposed Solutions (5)
TCM efficacy knowledge graph dataset: The work provides a Traditional Chinese Medicine efficacy knowledge graph dataset linking etiologies, diseases, patterns, symptoms, efficacies, and herbs.
Property graph with normalized TCM entities: The dataset is structured as a property graph with standardized entities and semantic relationships extracted and normalized from authoritative TCM textbooks.
Graph-ready CSV resource: The resource provides node and edge CSV files formatted for import into graph databases and network analysis libraries.
TCM efficacy knowledge graph dataset: The work provides a Traditional Chinese Medicine efficacy knowledge graph dataset linking etiologies, diseases, patterns, symptoms, efficacies, and herbs.
Property graph with normalized TCM entities: The dataset is structured as a property graph with standardized entities and semantic relationships extracted and normalized from authoritative TCM textbooks.
Results (3)
TCM graph resource scale:
Clinical reasoning chain coverage:
Semantic consistency:
Research Domain
Traditional Chinese Medicine knowledge graphs