HyperRxGen: historical-contextualized hyperbolic framework for herb prescription generation

Abstract

Applying artificial intelligence to Traditional Chinese Medicine (TCM) treatment has enabled the online intelligent diagnosis of TCM. However, TCM faces two critical challenges in AI-driven prescription systems. The first is limited generalizability. Existing methods merely retrieve similar historical prescriptions, failing to generate novel prescriptions for rare symptoms or patients with unique constitutions. The second is the accuracy degradation. This limitation primarily stems from three critical factors including experiential bias in practitioner-dependent decision patterns, neglect of historical patient context critical for personalization, and geometric distortion induced by Euclidean embeddings of scale-free herb interaction networks. To address these issues, we propose HyperRxGen, a historical-contextualized hyperbolic framework for herb prescription generation. The HyperRxGen paradigm is architected with two core components: a Hyperbolic Multi-Graph Neural Network (HMGNN) and an HMGNN-based Prescription Generator (HM-PG). The HMGNN leverages hyperbolic geometry model to encode TCM knowledge graphs, achieving lower distortion than Euclidean GNNs. The HM-PG injects patients’ historical records into prescription generation process, enhancing personalized treatment consistency through adaptive history weighting. Extensive experiments on real-world datasets demonstrate the superior effectiveness and efficiency of HyperRxGen over various baselines. This work bridges hyperbolic deep learning with clinical decision support, offering a potential paradigm shift for personalized healthcare.

Graphical abstract

Keywords

herb prescription generation / hyperbolic multi-graph neural network / contextual knowledge / personalized search / Chinese herb prescription

References

[1] Jin Y, Ji W, Shi Y, Wang X, Yang X . Meta-path guided graph attention network for explainable herb recommendation. Health Information Science and Systems, 2023, 11( 1): 5

[2] Jin Y, Zhang W, He X, Wang X, Wang X. Syndrome-aware herb recommendation with multi-graph convolution network. In: Proceedings of the 36th IEEE International Conference on Data Engineering. 2020, 145–156

[3] Zheng Z, Wang C, Xu T, Shen D, Qin P, Huai B, Liu T, Chen E. Drug package recommendation via interaction-aware graph induction. In: Proceedings of the Web Conference. 2021, 1284–1295

[4] Yang Y, Rao Y, Yu M, Kang Y . Multi-layer information fusion based on graph convolutional network for knowledge-driven herb recommendation. Neural Networks, 2022, 146: 1–10

[5] Chang J, Gao C, He X, Jin D, Li Y. Bundle recommendation with graph convolutional networks. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020, 1673–1676

[6] Zheng Z, Wang C, Xu T, Shen D, Qin P, Zhao X, Huai B, Wu X, Chen E . Interaction-aware drug package recommendation via policy gradient. ACM Transactions on Information Systems, 2023, 41( 1): 3

[7] Li X, Zhang Y, Li X, Wei H, Lu M . DGCL: distance-wise and graph contrastive learning for medication recommendation. Journal of Biomedical Informatics, 2023, 139: 104301

[8] Jin Z, Zhang Y, Miao J, Yang Y, Zhuang Y, Pan Y . A knowledge-guided and traditional Chinese medicine informed approach for herb recommendation. Frontiers of Information Technology & Electronic Engineering, 2023, 24( 10): 1416–1429

[9] Chami I, Ying Z, Re C, Leskovec J. Hyperbolic graph convolutional neural networks. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, 438

[10] Xu K, Hu W, Leskovec J, Jegelka S. How powerful are graph neural networks? In: Proceedings of the 7th International Conference on Learning Representations. 2019

[11] Wu Z, Pan S, Chen F, Long G, Zhang C, Yu P S . A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32( 1): 4–24

[12] Perozzi B, Al-Rfou R, Skiena S. DeepWalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2014, 701–710

[13] Liu Y, Zeng K, Wang H, Song X, Zhou B. Content matters: A GNN-based model combined with text semantics for social network cascade prediction. In: Proceedings of the 25th Pacific-Asia Conference on Knowledge Discovery and Data Mining. 2021, 728–740

[14] Wu S, Tang Y, Zhu Y, Wang L, Xie X, Tan T. Session-based recommendation with graph neural networks. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence. 2019, 346–353

[15] Wang W, Zhang W, Liu S, Liu Q, Zhang B, Lin L, Zha H. Beyond clicks: modeling multi-relational item graph for session-based target behavior prediction. In: Proceedings of the Web Conference. 2020, 3056–3062

[16] Zitnik M, Sosic R, Feldman M, Leskovec J . Evolution of resilience in protein interactomes across the tree of life. Proceedings of the National Academy of Sciences of the United States of America, 2019, 116( 10): 4426–4433

[17] Krioukov D, Papadopoulos F, Kitsak M, Vahdat A, Boguñá M . Hyperbolic geometry of complex networks. Physical Review E, 2010, 82( 3): 036106

[18] Yao L, Zhang Y, Wei B, Zhang W, Jin Z . A topic modeling approach for traditional Chinese medicine prescriptions. IEEE Transactions on Knowledge and Data Engineering, 2018, 30( 6): 1007–1021

[19] Jin Y, Ji W, Zhang W, He X, Wang X, Wang X . A KG-enhanced multi-graph neural network for attentive herb recommendation. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2022, 19( 5): 2560–2571

[20] Zhang Y, Wu X, Fang Q, Qian S, Xu C . Knowledge-enhanced attributed multi-task learning for medicine recommendation. ACM Transactions on Information Systems, 2023, 41( 1): 17

[21] Hou J, Song P, Zhao Z, Qiang Y, Zhao J, Yang Q . TCM prescription generation via knowledge source guidance network combined with herbal candidate mechanism. Computational and Mathematical Methods in Medicine, 2023, 2023( 1): 3301605

[22] Chang J, Gao C, He X, Jin D, Li Y . Bundle recommendation and generation with graph neural networks. IEEE Transactions on Knowledge and Data Engineering, 2023, 35( 3): 2326–2340

[23] Ma Y, He Y, Zhang A, Wang X, Chua T S. CrossCBR: cross-view contrastive learning for bundle recommendation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2022, 1233–1241

[24] Shang J, Xiao C, Ma T, Li H, Sun J. GAMENet: Graph augmented memory networks for recommending medication combination. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence. 2019, 1126–1133

[25] Nickel M, Kiela D. Learning continuous hierarchies in the Lorentz model of hyperbolic geometry. In: Proceedings of the 35th International Conference on Machine Learning. 2018, 3776–3785

[26] Kratsios A, Hong R, de Ocáriz Borde H S . Capacity bounds for hyperbolic neural network representations of latent tree structures. Neural Networks, 2024, 178: 106420

[27] He Y, Wang C, Li N, Zeng Z. Attention and memory-augmented networks for dual-view sequential learning. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2020, 125–134

[28] PENG H R, Dictionary of Traditional Chinese Medicine Prescriptions. Beijing: People Health Press, 1996 (in Chinese)

[29] DING G R, Medical Cases of Ding Ganren. Beijing: People’s Medical Publishing House, 2007 (in Chinese)

[30] FAN X W, XU C Q. Selected Medical Cases of Fan Zhonglin’s Six-Meridian Syndrome Differentiation. Beijing: Xueyuan Press, 2011 (in Chinese)

[31] Velickovic P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y. Graph attention networks. In: Proceedings of the 6th International Conference on Learning Representations. 2018

[32] Dong X, Zhao C, Song X, Zhang L, Liu Y, Wu J, Xu Y, Xu N, Liu J, Yu H, Yang K, Zhou X . PresRecST: a novel herbal prescription recommendation algorithm for real-world patients with integration of syndrome differentiation and treatment planning. Journal of the American Medical Informatics Association, 2024, 31( 6): 1268–1279

RIGHTS & PERMISSIONS

Higher Education Press