CL-MHAD: Contrastive Learning-based Multi-Hypergraph Aggregation and Diffusion model for prescription recommendation

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Performance gains of 1.27% to 24.67% over representative baseline models

• Primary Outcome: Prescription recommendation accuracy using multi-hypergraph aggregation and diffusion modeling

• Nnt Or Sensitivity: Superior stability demonstrated in data-sparsity robustness tests

• Confidence Interval: Not reported

Clinical Application

Requires computational infrastructure and integration with TCM clinical decision support systems Limited applicability due to TGA restrictions on TCM practice and lack of standardized syndrome classification systems in Australian healthcare TCM practitioners treating patients with complex syndromes requiring personalized herbal prescriptions

Abstract

Multiple syndrome-based prescription recommendations are significant for personalized diagnosis and treatment in Traditional Chinese Medicine (TCM). However, it remains a challenge to effectively extract and fuse multi-dimensional knowledge in herbs for accurate syndrome-based prescription recommendations. To address it, we propose CL-MHAD, a contrastive learning-based multi-hypergraph aggregation and diffusion model for prescription recommendation. Focusing on prescriptions, herbs, properties, and dosages, this model presents a multi-view hypergraph reconstruction mechanism, which employs a consistent Top-K neighbor strategy to generate affinity and feature matrices. Subsequently, a diffusion-enhanced method is proposed, utilizing multi-step propagation and weighted mapping to capture high-order relationships. Then, we propose a cross-view contrastive learning strategy to enhance discrimination and present a topology-aware random walk augmentation approach to alleviate data sparsity. An integrated loss function combining classification, contrastive, and augmentation losses is designed to optimize model performance. We evaluate CL-MHAD in a real-world clinical setting using Gastrointestinal Diseases (GID) as a case study. Extensive experiments, including comparative evaluations, ablation studies, and parameter sensitivity analyses, show that CL-MHAD achieves overall superior performance compared with representative baselines across multiple evaluation metrics. Specifically, the model achieves performance gains of 1.27% to 24.67% over representative baselines across all datasets. We further evaluate the model through dosage-syndrome interaction and data-sparsity robustness tests, with results demonstrating the effectiveness of our weighted fusion strategy and the model's superior stability. This study offers an effective solution and a promising paradigm for accurate syndrome-based prescription recommendations in TCM.

References

1. 1.Zhou, J., Zhang, Y., Hu, F., Zhang, X., & Ho, P. H. (2026). CL-MHAD: Contrastive Learning-based Multi-Hypergraph Aggregation and Diffusion model for prescription recommendation. Artificial Intelligence in Medicine, 103388. https://doi.org/10.1016/j.artmed.2026.103388