醫生為病人看病開藥的目的是治癒病人。有些藥物不能同時服用，因為同時服用可能有副作用。通過瞭解同时服用几种藥物所造成副作用的資訊可以避免這種情況。然而，對於病情複雜的病人，要开出最佳的藥物組合可能有难度。因此，我們採用了自動藥物推薦的方法來推薦副作用最小的藥物组合。自動藥物推薦的方法是通過使用深度學習模型，在藥物數據上訓練模型来推荐药物组合。我们的方法使用一种名為藥物/藥物相互作用（DDI）的圖形來表示藥物以及藥物之间的相互作用。同时，過去開过的藥物組合相关的資訊對於藥物推薦也很重要。这個資訊也可以用圖形來表示，一种稱為藥物併存關係（DCR）的圖形。DDI 和 DCR 圖形可以通過編碼成为深度學習模型的数据輸入。本文提出了一種圖編碼增強Transformer（GEET）來推薦藥物。DDI 和 DCR 圖形通過圖注意網路（GAT）進行編碼。GAT具有多頭注意力，這使得 GEET 模型能從圖形中識別出最重要的 DDI 和 DCR資訊。此外，我们還使用激活函數和正規化方法来合并圖編碼的輸出，以提高性能。我们的模型已在公開的 MIMIC-III 數據集上進行了評估，與現有所有相關研究的論文提出的模型相比，我们的模型在F1、Jaccard 和 PRAUC 评分結果最佳。

Doctors prescribe drugs for the patient with the objective of curing the patient. Some drugs cannot be consumed together since doing so may cause negative effects. This can be avoided by knowing the effects caused by consuming combinations of drugs. However, for complex cases of a patient, it can be difficult to decide the best combination of drugs. Therefore, automatic drug recommendation method was used to recommend drugs with minimal negative effects. It is performed by using a deep learning model which is trained on drug data. A graph called drug-drug interaction (DDI) is used to represent the drugs and effects of consuming one drug with other drugs. Additionally, information about the combination of drugs prescribed in the past for a patient is also important for drug recommendation. It can also be represented as a graph called drug concurrence relation (DCR). The DDI and DCR graphs can be input to the deep learning model through an encoding process. In this paper, we propose a graph encoding-enhanced transformer (GEET) to recommend drugs. The DDI and DCR graphs are encoded by using Graph Attention Network (GAT). The graph encoding model has multi-head attention, which makes the GEET model aware of the most important DDI and DCR from the graphs. Additionally, the encoding outputs are combined, and activation function and normalization methods are used to improve the performance. The model has been evaluated on the publicly available MIMIC-III dataset and has the best results on F1, Jaccard and PRAUC scores compared to the models proposed by the existing related research papers.

[1] R. Wu, Z. Qiu, J. Jiang, G. Qi, and X. Wu, “Conditional Generation Net for Medication Recommendation,” in Proceedings of the ACM Web Conference 2022, Apr. 2022, pp. 935–945. doi: 10.1145/3485447.3511936.
[2] J. Shang, C. Xiao, T. Ma, H. Li, and J. Sun, “GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combination.” arXiv, Mar. 06, 2019. Accessed: Jul. 22, 2023. [Online]. Available: http://arxiv.org/abs/1809.01852
[3] C. Yang, C. Xiao, F. Ma, L. Glass, and J. Sun, “SafeDrug: Dual Molecular Graph Encoders for Recommending Effective and Safe Drug Combinations.” arXiv, Jul. 16, 2022. Accessed: Jul. 22, 2023. [Online]. Available: http://arxiv.org/abs/2105.02711
[4] E. Choi, M. T. Bahadori, J. Sun, J. Kulas, A. Schuetz, and W. Stewart, “Retain: An interpretable predictive model for healthcare using reverse time attention mechanism,” Adv. Neural Inf. Process. Syst., vol. 29, 2016.
[5] L. Ma et al., “ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context.” arXiv, Nov. 27, 2019. doi: 10.48550/arXiv.1911.12216.
[6] X. Zhang et al., “INPREM: An Interpretable and Trustworthy Predictive Model for Healthcare,” in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, in KDD ’20. New York, NY, USA: Association for Computing Machinery, Aug. 2020, pp. 450–460. doi: 10.1145/3394486.3403087.
[7] Y. Li, B. Qian, X. Zhang, and H. Liu, “Graph Neural Network-Based Diagnosis Prediction,” Big Data, vol. 8, no. 5, pp. 379–390, Oct. 2020, doi: 10.1089/big.2020.0070.
[8] F. Ma, R. Chitta, J. Zhou, Q. You, T. Sun, and J. Gao, “Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks,” in Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2017, pp. 1903–1911. doi: 10.1145/3097983.3098088.
[9] L. Ma et al., “AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration,” Proc. AAAI Conf. Artif. Intell., vol. 34, no. 01, Art. no. 01, Apr. 2020, doi: 10.1609/aaai.v34i01.5427.
[10] A. T. Nguyen, H. Jeong, E. Yang, and S. J. Hwang, “Clinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning.” arXiv, Feb. 18, 2021. doi: 10.48550/arXiv.2006.12777.
[11] X. C, C. E, and S. J, “Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review,” J. Am. Med. Inform. Assoc. JAMIA, vol. 25, no. 10, Jan. 2018, doi: 10.1093/jamia/ocy068.
[12] E. Choi, M. T. Bahadori, A. Schuetz, W. F. Stewart, and J. Sun, “Doctor AI: Predicting Clinical Events via Recurrent Neural Networks.” arXiv, Sep. 28, 2016. doi: 10.48550/arXiv.1511.05942.
[13] P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, “Graph Attention Networks.” arXiv, Feb. 04, 2018. doi: 10.48550/arXiv.1710.10903.
[14] T. Ma, C. Xiao, J. Zhou, and F. Wang, “Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders.” arXiv, Apr. 28, 2018. doi: 10.48550/arXiv.1804.10850.
[15] W. Hamilton, Z. Ying, and J. Leskovec, “Inductive Representation Learning on Large Graphs,” in Advances in Neural Information Processing Systems, Curran Associates, Inc., 2017. Accessed: Jul. 22, 2023. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2017/hash/5dd9db5e033da9c6fb5ba83c7a7ebea9-Abstract.html
[16] K. Xu et al., “Show, Attend and Tell: Neural Image Caption Generation with Visual Attention,” in Proceedings of the 32nd International Conference on Machine Learning, PMLR, Jun. 2015, pp. 2048–2057. Accessed: Jul. 22, 2023. [Online]. Available: https://proceedings.mlr.press/v37/xuc15.html
[17] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” in Advances in Neural Information Processing Systems, Curran Associates, Inc., 2012. Accessed: Sep. 28, 2023. [Online]. Available: https://proceedings.neurips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html
[18] H. Lee, R. Grosse, R. Ranganath, and A. Y. Ng, “Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations,” in Proceedings of the 26th Annual International Conference on Machine Learning, Montreal Quebec Canada: ACM, Jun. 2009, pp. 609–616. doi: 10.1145/1553374.1553453.
[19] Y. Zhang, R. Chen, J. Tang, W. F. Stewart, and J. Sun, “LEAP: Learning to Prescribe Effective and Safe Treatment Combinations for Multimorbidity,” in Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, in KDD ’17. New York, NY, USA: Association for Computing Machinery, Aug. 2017, pp. 1315–1324. doi: 10.1145/3097983.3098109.
[20] H. Le, T. Tran, and S. Venkatesh, “Dual Memory Neural Computer for Asynchronous Two-view Sequential Learning,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London United Kingdom: ACM, Jul. 2018, pp. 1637–1645. doi: 10.1145/3219819.3219981.
[21] M. Zitnik, M. Agrawal, and J. Leskovec, “Modeling polypharmacy side effects with graph convolutional networks,” Bioinformatics, vol. 34, no. 13, pp. i457–i466, Jul. 2018, doi: 10.1093/bioinformatics/bty294.
[22] T. N. Kipf and M. Welling, “Semi-Supervised Classification with Graph Convolutional Networks.” arXiv, Feb. 22, 2017. doi: 10.48550/arXiv.1609.02907.
[23] K. Xu, W. Hu, J. Leskovec, and S. Jegelka, “How Powerful are Graph Neural Networks?” arXiv, Feb. 22, 2019. doi: 10.48550/arXiv.1810.00826.
[24] Q. Zhou, N. Yang, F. Wei, C. Tan, H. Bao, and M. Zhou, “Neural Question Generation from Text: A Preliminary Study,” in Natural Language Processing and Chinese Computing, X. Huang, J. Jiang, D. Zhao, Y. Feng, and Y. Hong, Eds., in Lecture Notes in Computer Science. Cham: Springer International Publishing, 2018, pp. 662–671. doi: 10.1007/978-3-319-73618-1_56.
[25] P. Nema, A. K. Mohankumar, M. M. Khapra, B. V. Srinivasan, and B. Ravindran, “Let’s Ask Again: Refine Network for Automatic Question Generation.” arXiv, Aug. 31, 2019. doi: 10.48550/arXiv.1909.05355.
[26] S. Niwattanakul, J. Singthongchai, E. Naenudorn, and S. Wanapu, “Using of Jaccard Coefficient for Keywords Similarity,” Hong Kong, 2013.
[27] J. Davis and M. Goadrich, “The relationship between Precision-Recall and ROC curves,” in Proceedings of the 23rd international conference on Machine learning - ICML ’06, Pittsburgh, Pennsylvania: ACM Press, 2006, pp. 233–240. doi: 10.1145/1143844.1143874.
[28] A. E. W. Johnson et al., “MIMIC-III, a freely accessible critical care database,” Sci. Data, vol. 3, no. 1, Art. no. 1, May 2016, doi: 10.1038/sdata.2016.35.
[29] N. P. Tatonetti, P. P. Ye, R. Daneshjou, and R. B. Altman, “Data-Driven Prediction of Drug Effects and Interactions,” Sci. Transl. Med., vol. 4, no. 125, pp. 125ra31-125ra31, Mar. 2012, doi: 10.1126/scitranslmed.3003377.
[30] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization.” arXiv, Jan. 29, 2017. doi: 10.48550/arXiv.1412.6980.
[31] C. Yang, C. Xiao, L. Glass, and J. Sun, “Change Matters: Medication Change Prediction with Recurrent Residual Networks,” in Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, Montreal, Canada: International Joint Conferences on Artificial Intelligence Organization, Aug. 2021, pp. 3728–3734. doi: 10.24963/ijcai.2021/513.