Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Oct 2, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.7K

TCM herbal prescription recommendation model based on multi-graph convolutional network.

Wen Zhao1, Weikai Lu2, Zuoyong Li3

  • 1School of Traditional Chinese Medicine, Fujian University of Traditional Chinese Medicine, Fuzhou, 350122, China.

Journal of Ethnopharmacology
|March 1, 2022
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Deletion of activating transcription factor 3 (Atf3) promotes cardiomyocyte differentiation from embryonic stem cells.

Scientific reports·2026
Same author

Pseudo Anomalies and Hard Sample Mining for Ventricular Arrhythmia Anomaly Detection.

IEEE journal of biomedical and health informatics·2026
Same author

EQA-MDL: Wearable ECG Signal Quality Assessment via Multi-scale Difference Learning.

IEEE journal of biomedical and health informatics·2026
Same author

TCPFMC: Trustworthy Cyclic Progressive Fusion for Multimodal Classification.

IEEE transactions on neural networks and learning systems·2026
Same author

Effects of probiotic supplementation on intestinal microbiota in patients with diabetes/prediabetes: a systematic review and meta-analysis of randomized controlled trials.

The British journal of nutrition·2025
Same author

A Core Outcome Set for Clinical Trials on Post COVID-19 Condition: "What," "When," and "How" to Measure.

Journal of evidence-based medicine·2025

This study introduces a novel AI model, the multigraph convolutional network (MGCN), to improve traditional Chinese medicine (TCM) herbal prescription recommendations by analyzing complex n-ary relationships between symptoms and treatments.

Area of Science:

  • Artificial Intelligence in Medicine
  • Traditional Chinese Medicine (TCM)
  • Computational Pharmacology

Background:

  • Traditional Chinese Medicine (TCM) herbal prescription recommendations are a key research area.
  • Current AI models primarily focus on binary or ternary relationships, neglecting the complex n-ary nature of TCM diagnosis and treatment.
  • Existing models have limitations in capturing the intricate connections between symptoms, state-elements, syndrome-types, and herbs.

Purpose of the Study:

  • To propose a novel prescription recommendation model, the multigraph convolutional network (MGCN), capable of portraying n-ary relationships.
  • To incorporate essential TCM diagnostic components, state-elements and syndrome-types, into the AI model.
  • To enhance the accuracy and practical applicability of AI-driven TCM herbal prescription recommendations.
Keywords:
Artificial intelligenceGraph convolutional networkIntelligent recommendationN-ary relationshipTCM herbal Prescription

More Related Videos

Network Pharmacology Prediction and Experimental Validation of Trichosanthes-Fritillaria thunbergii Action Mechanism Against Lung Adenocarcinoma
13:18

Network Pharmacology Prediction and Experimental Validation of Trichosanthes-Fritillaria thunbergii Action Mechanism Against Lung Adenocarcinoma

Published on: March 3, 2023

1.4K

Related Experiment Videos

Last Updated: Oct 2, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.7K
Network Pharmacology Prediction and Experimental Validation of Trichosanthes-Fritillaria thunbergii Action Mechanism Against Lung Adenocarcinoma
13:18

Network Pharmacology Prediction and Experimental Validation of Trichosanthes-Fritillaria thunbergii Action Mechanism Against Lung Adenocarcinoma

Published on: March 3, 2023

1.4K

Main Methods:

  • Developed a multigraph convolutional network (MGCN) comprising a TCM feature-aggregation module and a herbal medicine prediction module.
  • Constructed symptom-'state element'-symptom (Se) and symptom-'syndrome-type'-symptom (Ts) graphs to simulate n-ary relationships.
  • Utilized a multilayer perceptron (MLP) for predicting herbal prescriptions based on aggregated features from state-elements, syndrome-types, and symptoms.

Main Results:

  • The MGCN model demonstrated superior performance compared to three other algorithms, including Support Vector Machine (SVM).
  • Achieved significant improvements over SVM: 4.51% higher Precision@5, 6.45% higher Recall@5, and 5.31% higher F1-score@5.
  • Qualitative experiments showed high accuracy, with the MGCN correctly predicting all five herbs in one case and four out of five in another.

Conclusions:

  • The MGCN model substantially enhances the accuracy of traditional Chinese medicine herbal prescription recommendations.
  • Offers a more precise and practical AI-driven approach for TCM herbal prescription recommendations.
  • Highlights the potential of AI in capturing complex, multi-faceted relationships within traditional medical systems.