计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 221100232-6.doi: 10.11896/jsjkx.221100232
杨仙明, 詹贤春, 程恒亮, 丁海燕
YANG Xianming, ZHAN Xianchun, CHEN Hengliang, DING Haiyan
摘要： 诊断预测是医疗保健中一项重要的预测任务,其目的是根据患者的历史健康记录预测其未来的诊断。基于注意力机制和循环神经网络的预测模型被广泛应用于解决这一任务,但容易受到数据不足的影响。此外,医学领域知识在改进诊断预测模型性能上已经显示出重要作用,但现有方法还不能充分利用这些领域知识。因此,设计了一种基于图卷积网络和注意力机制的诊断预测模型。具体而言,首先利用医学本体对医学概念之间的相关性进行建模,并将患者就诊信息构建为一个图;其次,通过图卷积模块在图结构上获取患者每次就诊中各医学代码之间的空间特征;最后利用多头注意力机制来对就诊特征和多级医学知识之间的相互关系进行建模,从而对患者的未来健康状况进行预测。在两个公开的医疗数据集上的实验结果表明,该模型的诊断预测性能优于已有诊断预测模型,可以更有效地利用医学知识图中的潜在信息。
中图分类号:
| [1]YADAV P,STEINBACH M,KUMAR V,et al.Mining Elec-tronic Health Records(EHRs):A Survey[J].ACM Comput.Surv.,2018,50(6):85. [2]BOTSI T,HARTVIGSENG G,CHEN F,et al.Secondary use of EHR:data quality issues and informatics opportunitie[J/OL].https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3041534/. [3]JENSEN P B,JENSEN L J,BRUNAK S.Mining electronichealth records:towards better research applications and clinical care[J].Nature Reviews Genetics,2012,13(6):395-405. [4]KRUSE C S,STEIN A,THOMAS H,et al.The use of Elec-tronic Health Records to Support Population Health:A Systematic Review of the Literature[J].Journal of Medical Systems,2018,42(11):214. [5]CHOI E,BAHADORI M T,SCHUETZA,et al.Doctor ai:Predicting clinical events via recurrent neural networks[C]//Machine Learning for Healthcare Conference.PMLR,2016:301-318. [6]CHOI E,BAHADORI M T,SUN J,et al.Retain:An interpretable predictive model for healthcare using reverse time attention mechanism[J].arXiv:1608.05745,2016. [7]MA F,CHITTA R,ZHOU J,et al.Dipole:Diagnosis prediction in healthcare via attention-based bidirectional recurrent neural networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2017:1903-1911. [8]CHOI E,BAHADORI M T,SONG L,et al.GRAM:graph-based attention model for healthcare representation learning[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2017:787-795. [9]MA F,YOU Q,XIAO H,et al.Kame:Knowledge-based attention model for diagnosis prediction in healthcare[C]//Procee-dings of the 27th ACM International Conference on Information and Knowledge Management.2018:743-752. [10]GAO J,WANG X,WANG Y,et al.Camp:Co-attention memory networks for diagnosis prediction in healthcare[C]//2019 IEEE International Conference on Data Mining(ICDM).IEEE,2019:1036-1041. [11]LI H,LI W H,CHEN W,et al.Diagnostic prediction based on Node2vec and knowledge attention mechanisms[J].Computer Science,2021,48(S2):630-637. [12]LI Y,QIAN B,ZHANG X,et al.Knowledge guided diagnosisprediction via graph spatial-temporal network[C]//Proceedings of the 2020 SIAM International Conference on Data Mining.2020:19-27. [13]TROTT P.International classification of diseases for oncology[J].Journal of Clinical Pathology,1977,30(8):782. [14]COST H,PROJECT U.Clinical classifications software(CCS) for ICD-9-CM[J].www hcup-us.ahrq.gov/toolssoftware/ccs/ccs.jsp. [15]BENGIO Y,COURVILLE A,VINCENT P.RepresentationLearning:A Review and New Perspectives[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(8):1798-1828. [16]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016. [17]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[J].arXiv:1706.03762,2017. [18]JOHNSON A E W,POLLARD T J,SHEN L,et al.MIMIC-III,a freely accessible critical care database[J].Scientific Data,2016,3(1):1-9. [19]JOHNSON A,BULGARELLI L,POLLARD T,et al.MIMIC-IV,a freely accessible electronic health record dataset[J/OL].https://physionet.org/content/mimiciv/1.0/. [20]SRIVASTAVA N,HINTON G,KRIZHEVSKY A,et al.Dropout:a simple way to prevent neural networks from overfitting[J].The journal of machine learning research,2014,15(1):1929-1958. [21]KINGMA D P,BA J.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014. [22]LI M,ZHANG T,CHEN Y,et al.Efficient mini-batch training for stochastic optimization[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2014:661-670. |
|
||
首页