Please wait a minute...
Data Analysis and Knowledge Discovery  2019, Vol. 3 Issue (9): 88-97    DOI: 10.11925/infotech.2096-3467.2019.0147
Current Issue | Archive | Adv Search |
Automatic Triage of Online Doctor Services Based on Machine Learning
Ruojia Wang1,2,Lu Zhang1,Jimin Wang1()
1 Department of Information Management, Peking University, Beijing 100871, China
2 Institute of Ocean Research, Peking University, Beijing 100871, China
Download: PDF(710 KB)   HTML ( 11 ) 
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper compares the performance of various machine learning algorithms for automatic triage, aiming to improve their effectiveness through analyzing mis-classification data. [Methods] First, we retrieved 33,073 real patients’ questions from a website named “chunyu doctor”. Then, we compared the accuracy of two text vectorization methods and six classification models. Finally, we analyzed the mis-classification data and extracted new features to improve the performance of models. [Results] The best automatic triage model used TF-IDF as text vectorization method and support vector machine as classification algorithm. After adding age and gender characteristics, the classification accuracy rate reached 76.3%. The classifier had the lowest accuracy rate for surgery department due to the setting of this platform’s categories. [Limitations] We assumed that the department selection of the patient was correct. [Conclusions] Machine learning techniques could improve the performance of automatic triage services of the online health consulting platforms.
Key words： Ask the Doctor Service      Automatic Triage      Machine Learning      Support Vector Machine     
Received: 11 February 2019      Published: 23 October 2019
:  TP393 G35  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Ruojia Wang
Lu Zhang
Jimin Wang

Cite this article:

Ruojia Wang,Lu Zhang,Jimin Wang. Automatic Triage of Online Doctor Services Based on Machine Learning. Data Analysis and Knowledge Discovery, 2019, 3(9): 88-97.

URL:

http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2019.0147     OR     http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2019/V3/I9/88

科室 示例 样本数(个)
内科 我的心跳最近跳的次数在九十跳左右算正常吗 3 405
外科 60岁老人脚后跟摔了里面有小碎片, 怎么治疗 2 362
妇科 盆腔炎会肚子隐隐痛吗, 没异味, 白带特别粘 4 205
产科 怀孕四个月喝酒抽烟熬夜对胎儿有影响吗 1 937
儿科 7天新生儿综合评分36分踏步反射0分是脑瘫吗 2 294
男科 睾丸紧缩好像变小了, 是怎么回事呢? 2 553
骨伤科 手肘关节处肿胀, 可以不用打石膏固定吗 1 914
营养科 为什么有一种人每天暴饮暴食都不会胖的呢 3 691
肿瘤科 59岁老人宫颈癌放化疗后尿失禁带点血怎么回事 2 103
眼科 62岁青光眼晚期如何治疗 2 822
耳鼻咽喉科 鼻子塞得很严重, 擦了油和通鼻贴完全没有效果, 怎么办 2 036
口腔颌面科 最近这几天刷牙流血越来越厉害了怎么回事 1 926
皮肤性病科 尖锐湿疣有什么特征 1 825
总计 33 073
分类算法 Count TF-IDF
支持向量机 73.4% 75.1%
随机森林 68.6% 70.0%
多项式贝叶斯 71.8% 69.1%
逻辑回归 74.2% 74.0%
k近邻 48.4% 54.9%
集成分类 74.5% 74.4%
科室 数据量 分诊准确率
眼科 565 94.9%
营养科 738 85.0%
口腔颌面科 385 84.2%
耳鼻喉科 407 82.6%
肿瘤科 421 82.2%
妇科 841 82.2%
骨伤科 383 72.6%
内科 681 72.2%
男科 511 72.2%
产科 387 66.1%
儿科 459 64.3%
皮肤性病科 365 62.5%
外科 472 40.9%
原始科室 预测科室 错误率
外科 男科 25%
产科 妇科 22%
儿科 内科 10%
男科 外科 10%
妇科 产科 7%
内科 儿科 6%
骨伤科 皮肤性病科 5%
皮肤性病科 内科 5%
营养科 儿科 5%
肿瘤科 妇科 5%
耳鼻喉科 内科 4%
口腔颌面科 内科 3%
眼科 皮肤性病科 1%
科室 常见高频易混词举例
外科-男科 龟头、阴茎、手淫、勃起、早泄、包皮、尿、睾丸、
疼、精子、性生活、前列腺炎、痒、手术、龟头炎
产科-妇科 月经、怀孕、流产、检查、子宫、出血、严重、疼、
自然流产、分泌物、流血、孩子
儿科-内科 发烧、咳嗽、治疗、感冒、药、反复、症状、大便、
吐、检查、拉肚子、痰
科室 年龄平均值 男性比例 女性比例
妇科 27.2 3.5% 96.5%
产科 27.0 4.1% 95.9%
营养科 23.6 35.1% 64.9%
儿科 10.9 43.1% 56.9%
口腔颌面科 26.6 43.5% 56.5%
皮肤性病科 25.8 44.1% 55.9%
眼科 28.3 45.0% 55.0%
肿瘤科 47.3 45.5% 54.5%
耳鼻喉科 27.8 47.8% 52.2%
内科 34.8 48.9% 51.1%
骨伤科 34.0 51.3% 48.7%
外科 31.3 64.0% 36.0%
男科 26.9 94.4% 5.6%
总体 28.6 43.9% 56.1%
科室 增加特征前准确率 增加特征后准确率 提升率
妇科 82.7% 83.2% 0.5%
产科 67.4% 67.9% 0.5%
营养科 86.7% 87.5% 0.8%
儿科 58.3% 61.8% 3.5%
口腔颌面科 81.6% 82.1% 0.4%
皮肤性病科 60.6% 60.6% 0.0%
眼科 99.4% 99.4% 0.0%
肿瘤科 75.5% 76.6% 1.0%
耳鼻喉科 85.8% 84.7% -1.1%
内科 73.2% 73.8% 0.5%
骨伤科 70.4% 71.1% 0.7%
外科 45.8% 46.4% 0.6%
男科 70.0% 73.5% 3.5%
总体 75.5% 76.3% 0.8%
[1] Pineda A L, Ye Y, Visweswaran S , et al. Comparison of Machine Learning Classifiers for Influenza Detection from Emergency Department Free-text Reports[J]. Journal of Biomedical Informatics, 2015,58:60-69.
[2] 孔倩, 王杜娟, 王延章 , 等. 基于多目标神经网络的前列腺癌诊断方法[J]. 系统工程理论与实践, 2018,38(2):532-544.
[2] ( Kong Qian, Wang Dujuan, Wang Yanzhang , et al. Multi-Objective Neural Network-Based Diagnostic Model of Prostatic Cancer[J]. Systems Engineering - Theory & Practice, 2018,38(2):532-544.)
[3] Nikfarjam A, Sarker A, O’connor K , et al. Pharmacovigilance from Social Media: Mining Adverse Drug Reaction Mentions Using Sequence Labeling with Word Embedding Cluster Features[J]. Journal of the American Medical Informatics Association, 2015,22(3):671-681.
[4] Kose I, Gokturk M, Kilic K . An Interactive Machine- Learning-Based Electronic Fraud and Abuse Detection System in Healthcare Insurance[J]. Applied Soft Computing, 2015,36:283-299.
[5] 李嘉, 唐洁, 蒋玲 , 等. 在线健康咨询市场中的价格溢价研究[J]. 管理科学, 2018,31(1):15-32.
[5] ( Li Jia, Tang Jie, Jiang Ling , et al. Price Premiums in the Online Health Consultation Market[J]. Journal of Management Science, 2018,31(1):15-32.)
[6] 刘笑笑 . 在线医生信誉和医生努力对咨询量的影响研究[D]. 哈尔滨: 哈尔滨工业大学, 2014.
[6] ( Liu Xiaoxiao . The Impact of Online Doctor Reputation and Doctor Effort on Consultation Amount[D]. Harbin: Harbin Institute of Technology, 2014.)
[7] 薛书峰 . 互联网医疗的定价影响因素研究[D]. 南京: 南京大学, 2016.
[7] ( Xue Shufeng . Research on the Factors Affecting the Pricing of Online Healthcare Community[D]. Nanjing: Nanjing University, 2016.)
[8] 邓朝华, 洪紫映 . 在线医疗健康服务医患信任影响因素实证研究[J]. 管理科学, 2017,30(1):43-52.
[8] ( Deng Zhaohua, Hong Ziying . An Empirical Study of Patient-physician Trust Impact Factors in Online Healthcare Services[J]. Journal of Management Science, 2017,30(1):43-52.)
[9] 范晓妞, 艾时钟 . 在线医疗社区参与双方行为对知识交换效果影响的实证研究[J]. 情报杂志, 2016,35(7):173-178.
[9] ( Fan Xiaoniu, Ai Shizhong . An Empirical Study on the Relationship Between Online Medical Community Participants’ Behaviors and Knowledge Exchange Effect[J]. Journal of Intelligence, 2016,35(7):173-178.)
[10] Björk A B, Hillborg H, Augutis M , et al. Evolving Techniques in Text-Based Medical Consultation-Physicians’ Long-Term Experiences at an Ask the Doctor Service[J]. International Journal of Medical Informatics, 2017,105:83-88.
[11] Umefjord G, Petersson G, Hamberg K . Reasons for Consulting a Doctor on the Internet: Web Survey of Users of an Ask the Doctor Service[J]. Journal of Medical Internet Research, 2003,5(4):e26.
[12] Umefjord G, Sandström H, Malker H , et al. Medical Text-Based Consultations on the Internet: A 4-Year Study[J]. International Journal of Medical Informatics, 2008,77(2):114-121.
[13] Ma X, Gui X, Fan J , et al. Professional Medical Advice at Your Fingertips: An Empirical Study of an Online[J]. Proceedings of the ACM on Human-Computer Interaction, 2018, 2: Article No. 116.
[14] 吴江, 周露莎 . 在线医疗社区中知识共享网络及知识互动行为研究[J]. 情报科学, 2017,35(3):144-151.
[14] ( Wu Jiang, Zhou Lusha . The Study of Knowledge Sharing Network and Users’ Knowledge Interaction in Online Health Community[J]. Information Science, 2017,35(3):144-151.)
[15] 吴江, 施立 . 基于社会网络分析的在线医疗社区用户交互行为研究[J]. 情报科学, 2017,35(7):120-125.
[15] ( Wu Jiang, Shi Li . Study of the User Interaction Behavior in Online Health Community Based on Social Network Analysis[J]. Information Science, 2017,35(7):120-125.)
[16] 吴江, 李姗姗, 周露莎 , 等. 基于随机行动者模型的在线医疗社区用户关系网络动态演化研究[J]. 情报学报, 2017,36(2):213-220.
[16] ( Wu Jiang, Li Shanshan, Zhou Lusha , et al. Research on Dynamic Evolution of Users’ Relationship Network in Online Health Community Based on Stochastic Actor-oriented Model[J]. Journal of the China Society for Scientific and Technical Information, 2017,36(2):213-220.)
[17] 吴江, 侯绍新, 靳萌萌 , 等. 基于LDA模型特征选择的在线医疗社区文本分类及用户聚类研究[J]. 情报学报, 2017,36(11):1183-1191.
[17] ( Wu Jiang, Hou Shaoxin, Jin Mengmeng , et al. LDA Feature Selection Based Text Classification and User Clustering in Chinese Online Health Community[J]. Journal of the China Society for Scientific and Technical Information, 2017,36(11):1183-1191.)
[18] 刘通, 杨敬成 . 基于信号传播算法的在线医疗咨询反馈内容评估方法[J]. 数据分析与知识发现, 2017,1(11):29-36.
[18] ( Liu Tong, Yang Jingcheng . Evaluating Online Healthcare Consultation Feedbacks Based on Signal Transmission Algorithm[J]. Data Analysis and Knowledge Discovery, 2017,1(11):29-36.)
[19] Himmel W, Reincke U, Michelmann H W . Text Mining and Natural Language Processing Approaches for Automatic Categorization of Lay Requests to Web-Based Expert Forums[J]. Journal of Medical Internet Research, 2009,11(3):e25.
[20] Abdaoui A, Azé J, Bringay S , et al. Assisting E-patients in an Ask the Doctor Service[J]. Studies in Health Technology and Informatics, 2015,210:572-576.
[21] 刁必颂 . 基于在线患者咨询数据的在线医生推荐系统研究[D]. 北京: 北京理工大学, 2016.
[21] ( Diao Bisong . Online Patient Counseling Data Based Online Doctor Recommend System Research[D]. Beijing: Beijing Institute of Technology, 2016.)
[22] 王静 . 在线问诊平台相似病例推荐[D]. 哈尔滨: 哈尔滨理工大学, 2017.
[22] ( Wang Jing . Similar Cases Recommendation on Online Medical Diagnose Platform[D]. Harbin: Harbin University of Science and Technology, 2017.)
[23] 刘通 . 基于在线咨询记录的医生自动匹配算法应用研究[J]. 情报理论与实践, 2018,41(6):147-152.
[23] ( Liu Tong . An Application Research of Automatic Physician Matching Algorithm Based on Online Healthcare Consultation Records[J]. Information Studies: Theory & Application, 2018,41(6):147-152.)
[24] Scikit-learn. One-Vs-The-Rest[EB/OL].[2018-02-02]. https:// scikit-learn.org/stable/modules/multiclass.html#one-vs-the-rest.
[25] Kibriya A M, Frank E, Pfahringer B, et al. Multinomial Naive Bayes for Text Categorization Revisited [C]// Proceedings of the Australasian Joint Conference on Artificial Intelligence. 2004: 488-499.
[26] Scikit-learn. Logistic Regression[EB/OL].[2018-02-02]. https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression.
[27] Scikit-learn. Random Forests[EB/OL].[2018-02-02]. https://scikit-learn.org/stable/modules/ensemble.html#random-forests.
[28] Scikit-learn. Nearest Neighbors Classification[EB/OL].[2018-02-02]. https://scikit-learn.org/stable/modules/neighbors.html#nearest-neighbors-classification.
[29] 王昊, 叶鹏, 邓三鸿 . 机器学习在中文期刊论文自动分类研究中的应用[J]. 现代图书情报技术, 2014(3):80-87.
[29] ( Wang Hao, Ye Peng, Deng Sanhong . The Application of Machine- Learning in the Research on Automatic Categorization of Chinese Periodical Articles[J]. New Technology of Library and Information Service, 2014(3):80-87.)
[30] 刘浏, 王东波 . 基于论文自动分类的社科类学科跨学科性研究[J]. 数据分析与知识发现, 2018,2(3):30-38.
[30] ( Liu Liu, Wang Dongbo . Identifying Interdisciplinary Social Science Research Based on Article Classification[J]. Data Analysis and Knowledge Discovery, 2018,2(3):30-38.)
[31] Ishikawa H, Hashimoto H, Kiuchi T . The Evolving Concept of “Patient-Centeredness” in Patient-Physician Communication Research[J]. Social Science & Medicine, 2013,96:147-153.
[32] 赵明, 杜会芳, 董翠翠 , 等. 基于Word2Vec和LSTM的饮食健康文本分类研究[J]. 农业机械学报, 2017,48(10):202-208.
[32] ( Zhao Ming, Du Huifang, Dong Cuicui , et al. Diet Health Text Classification Based on Word2Vec and LSTM[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017,48(10):202-208.)
[1] Heran Qin,Liu Liu,Bin Li,Dongbo Wang. Automatic Classification of Ancient Classics with Entity Features[J]. 数据分析与知识发现, 2019, 3(9): 68-76.
[2] Gang Li,Huayang Zhou,Jin Mao,Sijing Chen. Classifying Social Media Users with Machine Learning[J]. 数据分析与知识发现, 2019, 3(8): 1-9.
[3] Jiahui Hu,An Fang,Wanqing Zhao,Chenliu Yang,Huiling Ren. Annotating Chinese E-Medical Record for Knowledge Discovery[J]. 数据分析与知识发现, 2019, 3(7): 123-132.
[4] Qingtian Zeng,Mingdi Dai,Chao Li,Hua Duan,Zhongying Zhao. Discovering Important Locations with User Representation and Trace Data[J]. 数据分析与知识发现, 2019, 3(6): 75-82.
[5] Cheng Zhou,Hongqin Wei. Evaluating and Classifying Patent Values Based on Self-Organizing Maps and Support Vector Machine[J]. 数据分析与知识发现, 2019, 3(5): 117-124.
[6] Jinzhu Zhang,Yiming Hu. Extracting Titles from Scientific References in Patents with Fusion of Representation Learning and Machine Learning[J]. 数据分析与知识发现, 2019, 3(5): 68-76.
[7] Zhiqiang Liu,Yuncheng Du,Shuicai Shi. Extraction of Key Information in Web News Based on Improved Hidden Markov Model[J]. 数据分析与知识发现, 2019, 3(3): 120-128.
[8] Hongxia Xu,Chunwang Li. Review of Knowledge Extraction of Scientific Literature[J]. 数据分析与知识发现, 2019, 3(3): 14-24.
[9] Zixuan Zhang,Hao Wang,Liping Zhu,Sanhong eng. Identifying Risks of HS Codes by China Customs[J]. 数据分析与知识发现, 2019, 3(1): 72-84.
[10] Lina Liu,Jiayin Qi,Zhenping Zhang,Dan Zeng. Analyzing Impacts of Brand Reputation on Online Sales Based on Massive Commodity Reviews and Brand[J]. 数据分析与知识发现, 2018, 2(9): 10-21.
[11] Longjia Jia,Bangzuo Zhang. Classifying Topics of Internet Public Opinion from College Students: Case Study of Sina Weibo[J]. 数据分析与知识发现, 2018, 2(7): 55-62.
[12] Wei Lu,Mengqi Luo,Heng Ding,Xin Li. Image Annotation Tags by Deep Learning and Real Users: A Comparative Study[J]. 数据分析与知识发现, 2018, 2(5): 1-10.
[13] Li Wang,Lixue Zou,Xiwen Liu. Visualizing Document Correlation Based on LDA Model[J]. 数据分析与知识发现, 2018, 2(3): 98-106.
[14] Xinyue Fan,Lei Cui. Predicting Antineoplastic Drug Targets Based on Network Properties[J]. 数据分析与知识发现, 2018, 2(12): 98-108.
[15] Yang Zhao,Xini Yuan,Yawen Chen,Liqiang Wu. Predicting Conversion Rate of APP Advertising with Machine Learning[J]. 数据分析与知识发现, 2018, 2(11): 2-9.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626，82624938   E-mail:jishu@mail.las.ac.cn