本文采用神经网络的方式，将graph based信息很好同Memory Network融合到一起。
图模型构建了两两label之间的强弱联系，也就是提前算好的权重矩阵。然后将此矩阵乘以latent matrix，利用相似近邻的思想重新获得latent matrix
Memory Network很好的把历史信息例举出来作为语料库。其中涉及到几个表达：patient(t) representation，medications(t) 观察值。通过计算当前patient的表达和之前patient的表达之间的距离，组合当前patient同各个medication之间的强弱关系。然后再把这种关系用到medication的representation 矩阵当中。
最后文中融入的DDI loss也很有意思。最后估计得到的每个medication的概率之积可以当作两个medication同时发生的概率。再结合已知组合抑制情况，可以降低某些组合的可能性。很有意思。
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combination | |||||||||||
| 文献作者 | Junyuan Shang | ||||||||||
| 文献发表年限 | 2019 | ||||||||||
| 文献关键字 | |||||||||||
| Memory Network; Graph model; RNN; EHR; DDI; longitudinal hidden state; 图模型结合Memory network模型 | |||||||||||
| 摘要描述 | |||||||||||
| Recent progress in deep learning is revolutionizing the health- care domain including providing solutions to medication recommendations, especially recommending medication combination for patients with complex health conditions. Existing approaches either do not customize based on patient health history, or ignore existing knowledge on drug-drug interactions (DDI) that might lead to adverse outcomes. To fill this gap, we propose the Graph Augmented Memory Networks (GAMENet), which integrates the drug-drug interactions knowledge graph by a memory module implemented as a graph convolutional networks, and models longitudinal patient records as the query. It is trained end-to-end to provide safe and personalized recommendation of medication combination. We demonstrate the effectiveness and safety of GAMENet by comparing with several state-of-the-art methods on real EHR data. GAMENet outperformed all baselines in all effectiveness measures, and also achieved 3.60% DDI rate reduction from existing EHR data. | |||||||||||
