IEEE J Biomed Health Inform. 2024 Apr;28(4):2294-2303. doi: 10.1109/JBHI.2024.3361552.
Medicine package recommendation aims to assist doctors in clinical decision-making by recommending appropriate packages of medicines for patients. Current methods model this task as a multi-label classification or sequence generation problem, focusing on learning relationships between individual medicines and other medical entities. However, these approaches uniformly overlook the interactions between medicine packages and other medical entities, potentially resulting in a lack of completeness in recommended medicine packages. Furthermore, medicine commonsense knowledge considered by current methods is notably limited, making it challenging to delve into the decision-making processes of doctors. To solve these problems, we propose DIAGNN, a Dual-level Interaction Aware heterogeneous Graph Neural Network for medicine package recommendation. Specifically, DIAGNN explicitly models interactions of medical entities within electronic health records(EHRs) at two levels, individual medicine and medicine package, leveraging a heterogeneous graph. A dual-level interaction aware graph convolutional network is utilized to capture semantic information in the medical heterogeneous graph. Additionally, we incorporate medication indications into the medical heterogeneous graph as medicine commonsense knowledge. Extensive experimental results on real-world datasets validate the effectiveness of the proposed method.
药品推荐旨在通过为患者推荐合适的药品包来辅助医生进行临床决策。当前的方法将这项任务建模为多标签分类或序列生成问题，重点学习单个药品与其他医疗实体之间的关系。然而，这些方法普遍忽略了药品包与其他医疗实体之间的相互作用，可能导致推荐药品包不够完整。此外，当前方法所考虑的药品常识知识明显有限，难以深入了解医生的决策过程。为了解决这些问题，我们提出了 DIAGNN，一种用于药品推荐的双水平交互感知异构图神经网络。具体来说，DIAGNN 明确地在两个层面上对电子病历(EHRs)中的医疗实体交互进行建模，分别是单个药品和药品包，利用了一个异构图。采用双水平交互感知图卷积网络来捕捉医疗异构图中的语义信息。此外，我们将用药指征纳入医疗异构图作为药品常识知识。在真实数据集上的广泛实验结果验证了所提出方法的有效性。
