Please wait a minute...
Advanced Search
数据分析与知识发现  2019, Vol. 3 Issue (6): 99-108    DOI: 10.11925/infotech.2096-3467.2018.0824
  应用论文 本期目录 | 过刊浏览 | 高级检索 |
中南财经政法大学信息与安全工程学院 武汉 430073
Deep Neural Network Learning for Medical Triage
Kan Liu(),Lu Chen
School of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan 430073, China
全文: PDF(953 KB)   HTML ( 11
输出: BibTeX | EndNote (RIS)      

目的】基于患者的主诉和病史, 利用深度学习模型辅助解决医院预检分诊中准确分配科室问题。【方法】将卷积神经网络模型应用于医疗领域的短文本分类问题, 从非结构化的患者主诉文本中学习医疗术语之间的相关性, 进行预训练, 然后将预训练模型的结构、参数及其权重用于含主诉和病史文本的网络中进行调整, 从而得到最终的学习结果。【结果】该算法在数据集上F值达到88%, 超过当前最好的基线模型6个百分点, 同时发现在数据集内容和样本量大小相似的情况下, 使用预训练模型能够明显提高模型训练效率。【局限】本研究基于电子病历数据展开, 与直接使用分诊台患者自述数据相比可能存在差异, 对此有待进一步探讨。【结论】提出的分诊模型有较强分类能力, 能够辅助提高医疗分诊的效率, 推动精准医疗发展。

E-mail Alert
关键词 医疗分诊电子病历卷积神经网络预训练    

[Objective] This paper proposes an algorithm to accurately assign specialists for outpatients based on their major complaints and medical histories. [Methods] We applied the convolutional neural network model to classify the medical short texts, and learn the correlation between medical terms, which were the tasks for pre-training. Then, we examined the structure, parameters and weights of the pre-trained model with actual texts of main complaint and medical history. Finally, we modified the network to obtain the final learning outcome. [Results] The F-score of the proposed approach reached 88% with the sample dataset, which was 6% higher than that of the current best baseline model. The pre-trained model significantly improved the training efficiency. [Limitations] We did not directly work with the patient’s actual complaints at the triage desk. We only used their electronic medical records, which might yield inaccurate results. [Conclusions] The proposed triage model improves the efficiency of medical triage, and promote precision medical treatment for patients.

Key wordsMedical Triage    Electronic Medical Records    Convolutional Neural Network    Pre-training
收稿日期: 2018-07-25     
基金资助:*本文系国家自然科学基金项目“基于个性化知识地图的交互式信息检索系统研究”(项目编号: 71573196)的研究成果之一
刘勘,陈露. 面向医疗分诊的深度神经网络学习*[J]. 数据分析与知识发现, 2019, 3(6): 99-108.
Kan Liu,Lu Chen. Deep Neural Network Learning for Medical Triage. Data Analysis and Knowledge Discovery, DOI:10.11925/infotech.2096-3467.2018.0824.
[1] 梁静云, 陈远华. 影响大型医院门诊分诊准确率的因素及对策探讨[J]. 中国临床护理, 2014, 6(6): 525-526.
[1] (Liang Jingyun, Chen Yuanhua.Factors Affecting Accuracy Rate of Outpatient Triage in the Large Hospital and the Countermeasures[J]. Chinese Clinical Nursing, 2014, 6(6): 525-526.)
[2] 苏玲敏, 张茂. 急诊预检分诊的现状与展望[J]. 中华急诊医学杂志, 2012, 21(12): 1406-1408.
[2] (Su Lingmin, Zhang Mao.The Status Quo and Prospect of Emergency Triage[J]. Chinese Journal of Emergency Medicine, 2012, 21(12): 1406-1408.)
[3] 石燕, 姜广荣, 程云芳. 基层医院门诊预检分诊流程的改进[J]. 护理学杂志, 2016, 31(19): 62-64.
[3] (Shi Yan, Jiang Guangrong, Cheng Yunfang.Improvement of Triage Process in County-Level Hospital[J]. Journal of Nursing Science, 2016, 31(19): 62-64.)
[4] 刘颖, 陈建荣, 张鹏. 急诊分诊现状与展望[J]. 护理学杂志, 2015, 30(6): 110-112.
[4] (Liu Ying, Chen Jianrong, Zhang Peng.The Status Quo and Prospect of Emergency Triage[J]. Journal of Nursing Science, 2015, 30(6): 110-112.)
[5] 吕鸿蒙, 赵地, 迟学斌. 基于增强AlexNet的深度学习的阿尔茨海默病的早期诊断[J]. 计算机科学, 2017, 44(S1): 50-60.
[5] (Lv Hongmeng, Zhao Di, Chi Xuebin.Deep Learning for Early Diagnosis of Alzheimer’s Disease Based on Intensive AlexNet[J]. Computer Science, 2017, 44(S1): 50-60.)
[6] 苏枫, 张少衡, 陈楠楠, 等. 基于机器学习分类判断算法构建心力衰竭疾病分期模型[J]. 中国组织工程研究, 2014, 18(49): 7938-7942.
[6] (Su Feng, Zhang Shaoheng, Chen Nannan, et al.A Heart Failure Staging Model Based on Machine Learning Classification Algorithms[J]. Chinese Journal of Tissue Engineering Research, 2014, 18(49): 7938-7942.)
[7] 陈德华, 周东阳, 乐嘉锦. 基于深度学习的甲状腺结节良恶性预测方法研究[J]. 微型机与应用, 2017, 36(12): 13-15.
[7] (Chen Dehua, Zhou Dongyang, Le Jiajin.Thyroid Nodule Benign and Malignant Prediction Based on Deep Learning[J]. Microcomputer & Its Applications, 2017, 36(12): 13-15.)
[8] Choi E, Bahadori M T, Schuetz A, et al.Doctor Ai: Predicting Clinical Events via Recurrent Neural Networks[C]// Proceedings of the 1st Machine Learning for Healthcare Conference. 2016: 301-318.
[9] Avati A, Jung K, Harman S, et al.Improving Palliative Care with Deep Learning[J]. BMC Medical Informatics and Decision Making, 2018, 18(4): 122.
[10] Liu S, Liu S, Cai W, et al.Early Diagnosis of Alzheimer’s Disease with Deep Learning[C]// Proceedings of the IEEE 11th International Symposium on Biomedical Imaging. 2014: 1015-1018.
[11] 吴枰, 潘海为, 高琳琳, 等. 基于KAP有向图模型的医学图像分类算法[J]. 模式识别与人工智能, 2016, 29(5): 427-438.
[11] (Wu Ping, Pan Haiwei, Gao Linlin, et al.Medical Image Classification Algorithm Based on KAP Directed Graph Model[J]. Pattern Recognition and Artificial Intelligence, 2016, 29(5): 427-438.)
[12] Yu Y, Lin H, Meng J, et al.Deep Transfer Learning for Modality Classification of Medical Images[J]. Information, 2017, 8(3): 91.
[13] Lipton Z C, Kale D C, Elkan C, et al.Learning to Diagnose with LSTM Recurrent Neural Networks[OL]. arXiv Preprint, arXiv: 1511.03677.
[14] Yang Y, Xie P, Gao X, et al.Predicting Discharge Medications at Admission Time Based on Deep Learning[J]. arXiv Preprint, arXiv: 1711.01386.
[15] 常炳国, 李玉琴, 冯智超, 等. 基于主成分机器学习算法的慢性肝病的智能预测新方法[J]. 计算机科学, 2017, 44(11A): 65-67, 91.
[15] (Chang Bingguo, Li Yuqin, Feng Zhichao, et al.New Intelligent Prediction of Chronic Liver Disease Based on Principal Component Machine Learning Algorithm[J]. Computer Science, 2017, 44(11A): 65-67, 91.)
[16] Tang B, Cao H, Wu Y, et al.Recognizing Clinical Entities in Hospital Discharge Summaries Using Structural Support Vector Machines with Word Representation Features[C]// Proceedings of the ACM 6th International Workshop on Data and Text Mining in Biomedical Informatics (DTMBio 2012). 2012.
[17] Jagannatha A N, Yu H.Bidirectional RNN for Medical Event Detection in Electronic Health Records[C]// Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016: 473-482.
[18] 牟冬梅, 任珂. 三种数据挖掘算法在电子病历知识发现中的比较[J]. 现代图书情报技术, 2016(6): 102-109.
[18] (Mu Dongmei, Ren Ke.Discovering Knowledge from Electronic Medical Records with Three Data Mining Algorithms[J]. New Technology of Library and Information Service, 2016(6): 102-109.)
[19] Wang Y, Luo J, Hao S, et al.NLP Based Congestive Heart Failure Case Finding: A Prospective Analysis on Statewide Electronic Medical Records[J]. International Journal of Medical Informatics, 2015, 84(12): 1039-1047.
[20] Turner C A, Jacobs A D, Marques C K, et al.Word2Vec Inversion and Traditional Text Classifiers for Phenotyping Lupus[J]. BMC Medical Informatics and Decision Making, 2017, 17(1): 126.
[21] 王啸宇, 郭代红, 徐元杰. 基于文本分类技术的住院患者药源性变态反应自动监测模块研究[J]. 中国药物应用与监测, 2016, 13(2): 117-120.
[21] (Wang Xiaoyu, Guo Daihong, Xu Yuanjie.Study on Automatic Monitoring Module of Inpatient Drug-induced Allergy Based on Text Categorization Technology[J]. Chinese Journal of Drug Application and Monitoring, 2016, 13(2): 117-120.)
[22] Wankhade N V, Patey M A.Transfer Learning Approach for Learning of Unstructured Data from Structured Data in Medical Domain[C]// Proceedings of the 2nd International Conference on Information Management in the Knowledge Economy. IEEE, 2013: 86-91.
[23] 医学. 医学词库. 搜狗输入法词库[OL]. [2018-05-10]..
[23] (Medi-cine. Medical Thesaurus.Sogou Input Method Library[OL]. [2018-05-10]. .)
[24] Kim Y.Convolutional Neural Networks for Sentence Classification[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. 2014: 1746-1751.
[25] Zhang X, Zhao J, LeCun Y. Character-level Convolutional Networks for Text Classification[C]// Proceedings of the 28th International Conference on Neural Information Processing Systems. 2015: 649-657.
[26] Pan S J, Yang Q.A Survey on Transfer Learning[J]. IEEE Transactions on Knowledge & Data Engineering, 2010, 22(10): 1345-1359.
[27] 庄福振, 罗平, 何清, 等. 迁移学习研究进展[J]. 软件学报, 2015, 26(1): 26-39.
[27] (Zhuang Fuzhen, Luo Ping, He Qing, et al.Survey on Transfer Learning Research[J]. Journal of Software, 2015, 26(1): 26-39.)
[1] 胡佳慧,方安,赵琬清,杨晨柳,任慧玲. 面向知识发现的中文电子病历标注方法
研究 *
[J]. 数据分析与知识发现, 2019, 3(7): 123-132.
[2] 徐月梅,吕思凝,蔡连侨,张小娅. 结合卷积神经网络和Topic2Vec的新闻主题演变分析*[J]. 数据分析与知识发现, 2018, 2(9): 31-41.
[3] 黄孝喜,李晗雨,王荣波,王小华,谌志群. 基于卷积神经网络与SVM分类器的隐喻识别*[J]. 数据分析与知识发现, 2018, 2(10): 77-83.
[4] 牟冬梅,王萍,赵丹宁. 高维电子病历的数据降维策略与实证研究*[J]. 数据分析与知识发现, 2018, 2(1): 88-98.
[5] 牟冬梅,任珂. 三种数据挖掘算法在电子病历知识发现中的比较*[J]. 现代图书情报技术, 2016, 32(6): 102-109.
[6] 李国垒, 陈先来, 夏冬, 杨荣. 面向临床决策的电子病历文本潜在语义分析*[J]. 数据分析与知识发现, 2016, 32(3): 50-57.
Full text



版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190