Stroke is an acute cerebrovasrular disease. It has a long recovery period and a complicated recovery mechanism, which brings a great burden to the family and society. In order to make up for the shortcomings of traditional treatment methods and provide effective clinical auxiliary decision support for inexperienced doctors, this paper proposed a hybrid attention mechanism model for electronic medical records (EMRs) to recommend the rehabilitation treatment program for stroke patients. First, the model takes advantage of rehabilitation items semantic information to mine the semantic connection between rehabilitation items and medical records; meanwhile, the self-attention mechanism is used to identify the medical records representation from the medical record content information. Then, the two parts are organically fused to generate the final medical record representation; Finally, a multi-label classifier is constructed for top-N recommendation for rehabilitation items. Experiments are carried out on a real EMRs data set from the department of Neurology and rehabilitation medicine of a first class hospital to verify the effectiveness of the model.
电子病历系统(electronic medical records,EMRs)是医疗活动中重要的数据资料,产生于临床治疗过程,是医务人员医疗知识的集中体现,也是患者个性化治疗的集中体现,充分挖掘这些数据可以有效地支持临床医学的研究[4,5]。在此基础上,相关领域学者对其展开一系列的研究工作,并在医疗知识图谱、医学影像分析、用药推荐等多个方面取得了良好的效果。对患者来说,通过分析病历中的数据,可以方便其了解身体健康状况;对医生来说,通过挖掘分析海量病历内容,采用医学类比推理的方法寻找相似患者,可以为疾病诊断提供参考依据。面向病历文本的临床决策支持能够克服医生经验欠缺和患者个体差异大的问题,在个性化治疗方案、用药推荐等方面给予医生决策支持,从而做出最合理的诊断及治疗方案。但是由于脑卒中患者康复周期长,康复机制复杂,鲜有针对脑卒中患者康复进行辅助决策的研究。而目前脑卒中患者人数逐年增加,针对脑卒中康复的辅助治疗已成为当下关注的热点问题。
WANGY J, LIZ X, GUH Q, et al. China stroke statistics 2019: A report from the national center for healthcare quality management in neurological diseases [J]. Stroke & Vascular Neurology, 2020 (5): e000457. DOI:10.1136/svn-2020-000457 .
SUNH X, WANGW Z. A nationwide epidemiological sample survey on cerebrovascular disease in China [J]. Chinese Journal of Contemporary Neurology and Neurosurgery, 2018, 18(2): 83-88. DOI:10.3969/j.issn.1672-6731.2018.02.002(Ch ).
YANGF, ZHANGJ J. The study of CD4+CD25+ treg and carotid atherosclerosis [J]. Chinese Journal of Clinical Neurosciences, 2012, 20(5): 584-588. DOI:10.3969/j.issn.1008-0678.2012.05.022(Ch ).
YANGJ F, YUQ B, GUANY, et al. An overview of research on electronic medical record oriented named entity recognition and entity relation extraction [J]. Acta Automatica Sinica, 2014, 40(8): 1537-1562. DOI:10.3724/SP.J.1004.2014.01537(Ch ).
YANGJ F, GUANY, HEB, et al. Corpus construction for named entities and entity relations on Chinese electronic medical records [J]. Journal of Software, 2016, 27(11): 2725-2746. DOI:10.13328/j.cnki.jos.004880(Ch ).
[10]
MCMEEKINP, FLYNND, FORDG A, et al. Development of a decision analytic model to support decision making and risk communication about thrombolytic treatment [J]. BMC Medical Informatics and Decision Making, 2015, 15: 90. DOI:10.1186/s12911-015-0213-z .
[11]
BENTLEYP, GANESALINGAMJ, CARLTON JONESA L, et al. Prediction of stroke thrombolysis outcome using CT brain machine learning [J]. NeuroImage: Clinical, 2014, 4: 635-640. DOI:10.1016/j.nicl.2014.02.003 .
[12]
ZHAOY F, LIUB, HEL Y, et al. A novel classification method for aid decision of traditional Chinese patent medicines for stroke treatment [J]. Frontiers of Medicine, 2017, 11(3): 432-439. DOI:10.1007/s11684-017-0511-1 .
[13]
ACCARDOA, CUSENZAM, MONTIF. Linear and non-linear parameterization of EEG during monitoring of carotid endarterectomy [J]. Computers in Biology and Medicine, 2009, 39(6): 512-518. DOI: 10.1016/j.compbiomed.2009.03.003 .
[14]
ZHAOW B, REINTHALM A, ESPYD D, et al. Rule-based human motion tracking for rehabilitation exercises: Realtime assessment, feedback, and guidance [J]. IEEE Access, 2017, 5: 21382-21394. DOI:10.1109/ACCESS.2017.2759801 .
[15]
MALEŠEVIĆJ, DEDIJER DUJOVIĆS, SAVIĆA M, et al. A decision support system for electrode shaping in multi-pad FES foot drop correction [J]. Journal of Neuro Engineering and Rehabilitation, 2017, 14(1): 1-14. DOI:10.1186/s12984-017-0275-5 .
[16]
SOLANAJ, CÁCERESC, GARCÍA-MOLINAA, et al. Improving brain injury cognitive rehabilitation by personalized telerehabilitation services: Guttmann neuropersonal trainer [J]. IEEE Journal of Biomedical and Health Informatics, 2015, 19(1): 124-131. DOI:10.1109/JBHI.2014.2354537 .
[17]
XIAOL, HUANGX, CHENB L, et al. Label-specific document representation for multi-label text classification[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Stroudsburg:Association for Computational Linguistics, 2019: 466-475. DOI: 10.18653/v1/D19-1044 .
[18]
LIUJ Z, CHANGW C, WUY X, et al. Deep learning for extreme multi-label text classification[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2017: 115-124. DOI:10.1145/3077136.3080834 .
[19]
YANGZ C, YANGD Y, DYERC, et al. Hierarchical attention networks for document classification[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2016: 1480-1489. DOI:10.18653/v1/n16-1174 .
[20]
CHENG B, YED H, XINGZ C, et al. Ensemble application of convolutional and recurrent neural networks for multi-label text categorization[C]//2017 International Joint Conference on Neural Networks (IJCNN). New York: IEEE Press, 2017: 2377-2383. DOI:10.1109/IJCNN.2017.7966144 .
[21]
KURATAG, XIANGB, ZHOUB W. Improved neural Network-based Multi-label classification with better initialization leveraging label co-occurrence [C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2016: 521-526. DOI:10.18653/v1/n16-1063 .
[22]
ZHANGW J, YANJ C, WANGX F, et al. Deep extreme multi-label learning [C]//Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval. New York: ACM, 2018: 100-107. DOI:10.1145/3206025.3206030 .
[23]
YANGP C, SUNX, LIW, et al. SGM: Sequence Generation Model for Multi-Label Classification [EB/OL]. [2021-05-06]. https://arxiv.org/abs/1806.04822. DOI: 10.1109/access.2019.2948855 .
[24]
DUC X, CHENZ Z, FENGF L, et al. Explicit interaction model towards text classification [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33: 6359-6366. DOI:10.1609/aaai.v33i01.33016359 .
[25]
PAPPASN, HENDERSONJ. GILE: A generalized input-label embedding for text classification[J]. Transactions of the Association for Computational Linguistics, 2019, 7: 139-155. DOI:10.1162/tacl_a_00259 .
[26]
LIX Y, ZHANGH, ZHOUX H. Chinese clinical named entity recognition with variant neural structures based on BERT methods [J]. Journal of Biomedical Informatics, 2020, 107: 103422. DOI:10.1016/j.jbi.2020.103422 .
[27]
LINZ H, FENGM W, SANTOSC N D, et al. A Structured Self-Attentive Sentence Embedding [DB/OL]. [2021-04-02]. DOI: 10.1109/icassp40776.2020.9054274 .
[28]
ROSEN-ZVIM, GRIFFITHST, STEYVERSM, et al. The author-topic model for authors and documents[EB/OL]. [2021-07-08]. https://arxiv.org/abs/1207.4169. DOI: 10.1145/1014052.1014087 .
ZHENGZ, XUT, QINC, et al. Multi-source contextual collaborative recommendation for medicine [J]. Journal of Computer Research and Development, 2020, 57(8): 1741-1754. DOI:10.7544/issn1000-1239.2020.20200149(Ch ).
[31]
WANGY, QUJ S, LIUJ, et al. What to tag your microblog: Hashtag recommendation based on topic analysis and collaborative filtering [C]//Web Technologies and Applications (LNCS 8709). Cham:Springer,2014: 610-618. DOI:10.1007/978-3-319-11116-2_58 .
[32]
RAMAGED, HALLD, NALLAPATIR, et al. Labeled LDA: A supervised topic model for credit attribution in multi-labeled corpora [C]//Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing Volume 1―EMNLP '09. Stroudsburg: Association for Computational Linguistics, 2009: 248-256. DOI:10.3115/1699510.1699543 .
CHENGH T, KOCL, HARMSENJ, et al. Wide & deep learning for recommender systems [C]//Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. New York: ACM, 2016: 7-10. DOI:10.1145/2988450.2988454 .