刘道文,阮彤,张晨童,邱家辉,翟洁,何萍,葛小玲. 基于多源知识图谱融合的智能导诊算法[J]. 中文信息学报, 2021, 35(1): 125-134.
LIU Daowen, RUAN Tong, ZHANG Chentong, QIU Jiahui, ZHAI Jie, HE Ping, GE Xiaoling. Clinical Departments Recommendation by Fusing Knowledge Graphs from Electronic Healthcare Records and Medical Websites. , 2021, 35(1): 125-134.
Clinical Departments Recommendation by Fusing Knowledge Graphs from Electronic Healthcare Records and Medical Websites
LIU Daowen1, RUAN Tong1, ZHANG Chentong1, QIU Jiahui1, ZHAI Jie1, HE Ping2, GE Xiaoling3
1.School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China;2.Shanghai Hospital Development Center, Shanghai 200120, China; 3.Information Centre, Children's Hospital of Fudan University, Shanghai 201102, China
摘要患者网上挂号时常有挂错科室的现象,因此需要科室推荐应用,功能类似线下医院的护士台预诊。然而,由于医院科室设置不尽相同,患者各项特征和科室之间的关系也不明确,给自动科室推荐带来挑战。因此,该文首先定义了带权重的知识图谱,用于描述症状、疾病以及性别等特征与科室和医院之间复杂的量化关系。其次,利用区域信息平台的电子健康档案(electronic health records,EHR)数据,获取多家医院的疾病—科室信息。在融合国际疾病编码(international classification of diseases,ICD)、医疗网站中的症状—疾病数据后,用搜索引擎结果补充权重关系,形成可用的知识图谱。图谱目前包含了38家医院,6 110个科室,6 220个症状,60 736个症状相关疾病关系。当患者输入基于自然语言描述的症状与疾病后,通过该文设计的预滤噪的BERT实体识别模型与部位制导的医疗实体归一化算法,识别并归一化患者主诉中的症状词、疾病词和部位词。最后,基于该文设计的基于权重的联合症状预测疾病概率算法(weight-based disease prediction algorithm based on multiple symptoms,WBDPMS),联合多个症状预测可能的相关疾病,以此来实现通过主诉推荐最合适的医院及科室。实验结果表明,准确率达到0.88。
Abstract:The clinical department recommendation is a challenging task since the settings of department are different among hospitals. Meanwhile the relationships between symptoms and departments are also unclear. In this paper, weighted knowledge graph is defined and constructed from local EHR data, ICD (International Classification of Diseases) and online medical websites to establish the quantitative relationship among symptoms, diseases and departments. The constructed knowledge graph contains 38 hospitals, 6 110 departments, 6 220 symptoms and 60 736 symptoms-related diseases. The proposed recommendation system recognizes the symptoms words, disease words and body part words in patients’ chief complaint by a Bert entity recognition model. Finally, a weight-based disease prediction algorithm based on multiple symptoms (WBDPMS) is designed to identify the candidate diseases and thus recommend the most suitable hospitals and departments. The experimental results show that the accuracy reaches 0.88.
[1] 马钰,张岩,王宏志,等. 面对智能导诊的个性化推荐算法[J]. 智能系统学报, 2018, 13(3): 352-358. [2] 梁璐. 基于 VSM 权重改进算法的智能导医系统研究[D]. 郑州: 郑州大学硕士学位论文, 2014. [3] 徐奕枫, 刘利军, 黄青松, 等. 智能导医系统中 TF-IDF 权重改进算法研究[J]. 计算机工程与应用, 2017,23(4): 238-243. [4] Niu X, Sun X, Wang H, et al. Zhishi.me-weaving Chinese linking open data[C]//Proceedings of the 10th International Semantic Web Conference. Springer, Berlin, Heidelberg, 2011: 205-220. [5] Wang Z, Li J, Wang Z, et al. XLore: A large-scale English-Chinese bilingual knowledge graph[C]//Proceedings of the 12th International Semantic Web Conference (Posters & Demos), 2013, 1035: 121-124. [6] 于彤,苏大明,尹仁芳,等. 中医药知识服务平台构建的研究[J].中国医学创新,2014(15):120-123. [7] Yu T, Li J, Yu Q, et al. Knowledge graph for TCM health preservation: Design, construction, and applications[J]. Artificial Intelligence in Medicine, 2017, 77: 48-52. [8] Qiu J, Zhou Y, Wang Q, et al. Chinese clinical named entity recognition using residual dilated convolutional neural network with conditional random field[J].IEEE Transactions on NanoBioscience, 2019, 18(3): 306-315. [9] Wang Q, Zhou Y, Ruan T, et al. Incorporating dictionaries into deep neural networks for the Chinese clinical named entity recognition[J]. Journal of Biomedical Informatics, 2019, 92: 103133. [10] Gong C, Tang J, Zhou S, et al. Chinese named entity recognition with Bert[J]. DEStech Transactions on Computer Science and Engineering, 2019:33299. [11] Wang Q, Wang T, Xu C. Using a knowledge graph for hypernymy detection between chinese symptoms[C]//Proceedings of the 10th International Conference on Advanced Computational Intelligence. IEEE, 2018: 601-606. [12] Zhang J, Wang Q, Zhang Z, et al. An effective standardization method for the lab indicators in regional medical health platform using n-grams and stacking[C]//Proceedings of the 2018 IEEE International Conference on Bioinformatics and Biomedicine. IEEE, 2018: 1602-1609. [13] Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018. [14] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6000-6010. [15] Huang Z, Lu X, Duan H, et al. Collaboration-based medical knowledge recommendation[J]. Artificial Intelligence in Medicine, 2012, 55(1): 13-24. [16] Thong N T. Intuitionistic fuzzy recommender systems: An effective tool for medical diagnosis[J]. Knowledge Based Systems, 2015, 74: 133-150. [17] 阮彤, 孙程琳, 王昊奋, 等. 中医药知识图谱构建与应用[J]. 医学信息学杂志, 2016, 37(4): 8-13. [18] 阮彤, 王昊奋. 基于本体的医疗健康语义知识库构建[J]. 中国信息界 (e 医疗), 2014 (6): 47.