Graph-based medicine embedding learning via multiple attentions. (January 2023)

• Record Type: Journal Article
• Authors: Yan, Xingyu; Zhang, Yin; Huang, Mingfang; Yang, Xiaolian; Yan, Yi; Hu, Fang
• Is Part Of: Computers & electrical engineering. Volume 105(2023)
• Publication Date: 2023-01
• Subjects: Graph attention network -- Multi-relation representation -- Spectral clustering -- Neighbor node aggregation -- Multi-head attention mechanism -- Medicine embedding learning; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108494
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Clinical knowledge reasoning provides a new perspective for intelligent diagnosis and therapy. This study constructs a multi-relational medicine-attribute network, which refers to three different types of relationships: inter-medicine, inter-attribute, and medicine-attribute. Then, a multi-relation-based graph attention network (GAT) model combined with the spectral clustering (SC) algorithm, termed MGAT-SC, is presented to train the medicine embeddings and explore the regularity of medicine combinations. Based on real-world clinical data, the GAT model realizes the information aggregation of neighbor nodes and generates the embeddings of medicines and their attributes via a multi-head attention mechanism. Then, the SC method is utilized to divide the medicines and their embeddings. We design and conduct a series of experiments to verify the model's performance. The experimental results show that the MGAT-SC outperforms the representative baselines and their variants in terms of five evaluation metrics and achieves around 6 . 0 % improvement in accuracy compared to the SC algorithm. Graphical abstract: Highlights: A MGAT-SC is proposed to investigate the complex relations underlying medicines. MGAT-SC aggregates neighbor nodes' information for medicine embedding learning. This algorithm can effectively explore the regularity of medicine combinations. It can provide theoretical support for clinical knowledge reasoning.