FastRx: Exploring Fastformer and Memory-Augmented Graph Neural Networks for Personalized Medication Recommendations

Tai Tan Phan1, Ling Chen2, Chun-Hung Chen3, Wen-Chih Peng4
1Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan and College of Information and Communication Technology, Can Tho University, Vietnam
2Institute of Hospital & Health Care Administration, National Yang Ming Chiao Tung University, Taiwan
3School of Medicine, National Yang Ming Chiao Tung University, Taiwan
4Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan

Tóm tắt

Personalized medication recommendations aim to suggest a set of medications based on the clinical conditions of a patient. Not only should the patient's diagnosis, procedure, and medication history be considered, but drug-drug interactions (DDIs) must also be taken into account to prevent adverse drug reactions. Although recent studies on medication recommendation have considered DDIs and patient history, personalized disease progression and prescription have not been explicitly modeled. In this work, we proposed FastRx, a Fastformer-based medication recommendation model to capture longitudinality in patient history, in combination with Graph Convolutional Networks (GCNs) to handle DDIs and co-prescribed medications in Electronic Health Records (EHRs). Our extensive experiments on the MIMIC-III dataset demonstrated superior performance of the proposed FastRx over existing state-of-the-art models for medication recommendation. The source code and data used in the experiments are available at https://github.com/pnmthaoct/FastRx .

Từ khóa


Tài liệu tham khảo

10.1002/sim.4512

Karl Johan Åström and Tore Hägglund. 1995. PID Controllers: Theory, Design, and Tuning. ISA- The Instrumentation, Systems and Automation Society, Pennsylvania, United States. ISBN: 1-55617-516-7.

10.1145/3219819.3219904

Jacek M. Bajor and Thomas A. Lasko. 2017. Predicting Medications from Diagnostic Codes with Recurrent Neural Networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. Toulon, France, 19 pages. https://openreview.net/forum?id=rJEgeXFex

10.1145/3097983.3097997

Jie Chen, Tengfei Ma, and Cao Xiao. 2018. Fastgcn: fast learning with graph convolutional networks via importance sampling. arXiv preprint arXiv:1801.10247 (2018).

10.1017/s1471068416000429

10.5555/3157382.3157490

Alexey Dosovitskiy and Josip Djolonga. 2020. You Only Train Once: Loss-Conditional Training of Deep Networks. In International Conference on Learning Representations. OpenReview.net Addis Ababa Ethiopia 17 pages. https://api.semanticscholar.org/CorpusID:214278158

10.1016/s0140-6736(00)02799-9

10.1016/j.bdr.2020.100174

10.1080/15374416.2015.1015133

Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017), 11 pages.

10.1038/sdata.2016.35

10.1001/jama.289.13.1652

Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). http://arxiv.org/abs/1412.6980

Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016), 14 pages. https://openreview.net/forum?id=SJU4ayYgl

Himabindu Lakkaraju and Cynthia Rudin. 2017. Learning cost-effective and interpretable treatment regimes. In Artificial intelligence and statistics. PMLR 166–175.

10.1145/3219819.3219981

10.1016/j.knosys.2023.111239

10.1093/jamia

10.1001/jama.1995.03530010049034

Chengsheng Mao, Liang Yao, and Yuan Luo. 2022. Imagegcn: Multi-relational image graph convolutional networks for disease identification with chest x-rays. IEEE transactions on medical imaging 41, 8 (2022), 1990–2003.

10.1016/j.jbi.2022.104000

10.1056/nejmp1606181

10.1371/journal.pone.0135947

10.1007/978-3-642-04174-7_17

10.24963/ijcai.2019

10.1609/aaai.v33i01.33011126

Hongda Sun, Shufang Xie, Shuqi Li, Yuhan Chen, Ji-Rong Wen, and Rui Yan. 2022. Debiased, longitudinal and coordinated drug recommendation through multi-visit clinic records. Advances in Neural Information Processing Systems 35 (2022), 27837–27849.

10.1145/3534678.3539089

Nicholas P. Tatonetti, Patrick Ye, Roxana Daneshjou, and Russ B. Altman. 2012. Data-Driven Prediction of Drug Effects and Interactions. Science Translational Medicine 4 (2012), 125ra31 – 125ra31. https://api.semanticscholar.org/CorpusID:2716426

10.1145/3219819.3219961

10.1145/3357384.3357965

Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang, and Xing Xie. 2021. Fastformer: Additive Attention Can Be All You Need. arXiv preprint arXiv:2108.09084 (2021), 11 pages. https://arxiv.org/abs/2108.09084

10.1145/3485447.3511936

10.1109/TNNLS.2020.2978386

10.1093/jamia

10.24963/ijcai.2021

Chaoqi Yang, Cao Xiao, Fenglong Ma, Lucas Glass, and Jimeng Sun. 2021. Safedrug: Dual molecular graph encoders for recommending effective and safe drug combinations. arXiv preprint arXiv:2105.02711 (2021). https://arxiv.org/abs/2105.02711

10.1145/3543507.3583872

10.1609/aaai.v33i01.33017370

10.1145/3097983.3098109

10.1145/3178876.3186116