FMCHS: Advancing Traditional Chinese Medicine Herb Recommendation with Fusion of Multiscale Correlations of Herbs and Symptoms

2025-03-07

AI Summary

Existing herbal medicine recommendation models struggle to capture latent associations between herbs and symptoms at the chemical molecular level, thereby limiting multi-scale relational modeling. This paper proposes the first multi-scale joint modeling framework that integrates molecular-level herbal chemical features—such as molecular fingerprints and node-level chemical properties—with clinical symptom representations. Specifically, we design a multi-relational graph Transformer to encode heterogeneous herb–symptom interactions and introduce an attention-driven multi-scale feature fusion mechanism. On benchmark datasets, our approach achieves improvements of 8.85%, 12.30%, and 10.86% in Precision@5, Recall@5, and F1@5 over the state-of-the-art, respectively, significantly enhancing both interpretability and recommendation performance. The core contribution lies in the first deep integration of molecular representations into traditional Chinese medicine (TCM) recommendation modeling, enabling cross-scale (clinical–chemical) semantic alignment.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Traditional Chinese medicine (TCM) exhibits remarkable therapeutic efficacy in disease treatment and healthcare through personalized herb prescriptions. However, current herb recommendation models inadequately capture the multiscale relations between herbs and clinical symptoms, particularly neglecting latent correlations at the chemical-molecular scale. To address these limitations, we propose the Fusion of Multiscale Correlations of Herbs and Symptoms (FMCHS), an innovative framework that synergistically integrates molecular-scale chemical characteristics of herbs with clinical symptoms. The framework employs multi-relational graph transformer layers to generate enriched embeddings that preserve both structural and semantic features within herbs and symptoms. Through systematic incorporation of herb chemical profiles into node embeddings and implementation of attention-based feature fusion, FMCHS effectively utilizes multiscale correlations. Comprehensive evaluations demonstrate FMCHS's superior performance over the state-of-the-art (SOTA) baseline, achieving relative improvements of 8.85% in Precision@5, 12.30% in Recall@5, and 10.86% in F1@5 compared to the SOTA model on benchmark datasets. This work facilitates the practical application of TCM in disease treatment and healthcare.

Problem

• Enhances TCM herb recommendation by capturing multiscale herb-symptom correlations.
• Integrates molecular-scale chemical characteristics with clinical symptom data.
• Improves precision, recall, and F1 scores in herb recommendation models.

Innovation

• Integrates molecular-scale chemical characteristics with symptoms
• Uses multi-relational graph transformer layers for embeddings
• Implements attention-based feature fusion for multiscale correlations