Please wait a minute...
Data Analysis and Knowledge Discovery  2020, Vol. 4 Issue (8): 130-142    DOI: 10.11925/infotech.2096-3467.2019.1038
Current Issue | Archive | Adv Search |
Recommending Doctors Online Based on Combined Conditions
Li Yueyan,Xiong Huixiang(),Li Xiaomin
School of Information Management, Central China Normal University, Wuhan 430079, China
Download: PDF (988 KB)   HTML ( 19
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper integrates multiple recommendation strategies to discover high-quality doctor services, aiming to improve the recommendation results from medical consultation websites. [Methods] We built a doctor recommendation model based on combined conditions, which included three models for similar patients, medical fields and doctor performance. Then, we used a linear weighted hybrid strategy to merge these results to create a final list. We retrieved data from "Good Doctor Online" to evaluate the proposed model. [Results] Up to 86% of the doctors seen by the patients were identified by our new model. [Limitations] The choice of users might be affected by random factors and the weight setting of each strategy needs to be improved. [Conclusions] The proposed model could effectively recommend high-quality doctors for patients.

Key wordsOnline Inquiry Platform      Word2Vec      Doctor Recommendation      Combination Conditions     
Received: 16 September 2019      Published: 05 June 2020
ZTFLH:  G206  
Corresponding Authors: Xiong Huixiang     E-mail: hxxiong@mail.ccnu.edu.cn

Cite this article:

Li Yueyan,Xiong Huixiang,Li Xiaomin. Recommending Doctors Online Based on Combined Conditions. Data Analysis and Knowledge Discovery, 2020, 4(8): 130-142.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2019.1038     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2020/V4/I8/130

Overall Architecture of Doctor Recommendation Model
医生编号 相似患者咨询文本 患者相似度 Scorepatient 排序
26 精神分裂症忧郁症头晕偶尔低烧心情烦躁 0.891 065 0.777 354 1
失眠焦虑害怕心烦 0.820 992
头疼恐惧症焦虑症害怕不能睡 0.700 822
117 焦虑抑郁症焦虑抑郁耳鸣易怒爱发脾气 0.801 047 0.772 214 2
失眠胸闷呼吸困难头痛头晕听觉下降 0.750 092
31 焦虑抑郁状态失眠半多的心慌气短 0.798 982 0.761 342 3
焦虑恐慌心烦食欲不振 0.790 205

288
焦虑抑郁经常头晕头痛乏力 0.870 419 10
0.729 587
情绪障碍控制不住紧张害怕心慌觉得生活灰暗 0.701 250
The Set of Similar Doctors for Target Patient h
新注册医生

候选医生
26 117 31 35 6 8 1 63 210 288
66 0.500 0 0.466 7 0.545 5 0.138 9 0.470 6 0.571 4 0.533 3 0.250 0 0.217 4 0.454 6
78 0.384 6 0.266 7 0.400 0 0.151 5 0.375 0 0.357 1 0.333 3 0.222 2 0.250 0 0.444 4
96 0.466 7 0.437 5 0.500 0 0.076 9 0.368 4 0.352 9 0.411 8 0.130 4 0.160 0 0.545 5
209 0.333 3 0.307 7 0.333 3 0.125 0 0.250 0 0.307 7 0.285 7 0.176 5 0.210 5 0.222 2
47 0.352 9 0.333 3 0.357 1 0.194 4 0.500 0 0.411 8 0.388 9 0.227 3 0.250 0 0.285 7
6 0.555 6 0.381 0 0.333 3 0.297 3 * 0.611 1 0.579 0 0.333 3 0.400 0 0.352 9
229 0.384 6 0.357 1 0.400 0 0.085 7 0.294 1 0.357 1 0.333 3 0.157 9 0.190 5 0.444 4
174 0.466 7 0.437 5 0.500 0 0.200 0 0.625 0 0.642 9 0.500 0 0.238 1 0.318 2 0.416 7
The Knowledge Structure Similarity
新注册医生

候选医生
26 117 31 35 6 8 1 63 210 288
66 0 0 0 0 0 0 0 0 0 0
78 0 0 0 0 0 0 0 0 0 0
96 1 0 0.333 3 0 0 0.333 3 0 0 0 0
209 0 1 0 0 0 0 1 0 0 0
47 0 0 0 0 0 0 0 0 0 0
6 0 0 0 0 * 0 0 0.333 3 0 0
229 0 0 0 0 0 0 0 0 0 0
174 0 0 0 0 1 0 0 0.333 3 0 0
The Behavioral Network Similarity
新注册医生

候选医生
26 117 31 35 6 8 1 63 210 288 Scorefield
66 0.724 1 0.659 8 0.811 9 0.026 8 0.667 3 0.861 9 0.620 6 0.241 4 0.178 4 0.636 4 0.542 9
78 0.501 3 0.273 6 0.531 0 0.051 2 0.482 7 0.448 2 0.206 8 0.187 7 0.241 4 0.616 8 0.354 1
96 1.659 8 0.603 4 1.057 4 -0.092 9 0.470 0 0.773 3 0.198 7 0.010 4 0.067 6 0.811 9 0.556 0
209 0.402 2 1.352 8 0.402 2 0.000 0 0.241 4 0.352 8 1.111 4 0.099 4 0.165 1 0.187 7 0.431 5
47 0.440 0 0.402 2 0.448 2 0.134 0 0.724 1 0.553 8 0.312 4 0.197 5 0.241 4 0.310 3 0.376 4
6 0.831 4 0.494 3 0.402 3 0.332 7 * 0.938 6 0.697 2 0.735 5 0.531 0 0.440 0 0.600 3
229 0.501 3 0.448 2 0.531 0 -0.075 9 0.326 5 0.448 2 0.206 8 0.063 5 0.126 5 0.616 7 0.319 3
174 0.659 8 0.603 4 0.724 1 0.144 8 1.930 9 1.000 0 0.758 6 0.551 7 0.373 0 0.563 2 0.731 0
The Domain Similarity
指标 C1 C2 C3 C4 C5 A M H T R L G P RH
相关系数 0.993** 0.618** 0.639** 0.771** 0.791** 0.356** 0.371** 0.049 0.154* -0.112 0.692** 0.616** 0.728** 0.430**
The Correlation Coefficient Between Doctor Performance Evaluation Index and Total Patients
成分 初始特征值 提取平方和载入
合计 方差(%) 累计(%) 合计 方差(%) 累计(%)
1 6.764 61.254 61.254 6.764 61.254 61.254
2 1.166 10.559 71.813 1.166 10.559 71.813
3 1.060 9.597 81.410 1.060 9.597 81.410
4 0.665 6.020 87.430 0.665 6.020 87.430
5 0.568 5.146 92.576
6 0.346 3.130 95.705
7 0.262 2.371 98.076
8 0.143 1.296 99.372
9 0.061 0.553 99.925
10 0.004 0.040 99.966
11 0.004 0.034 100.00
The Total Variance
模型 非标准化系数 标准化系数
Beta
t P Collinearity Statistics
B Std.Erroe Tolerance VIF
1 常数 0.002 0.038 0.051 0.960
F1 0.322 0.015 0.835 22.126 0.000 1.000 1.000
F2 0.178 0.035 0.191 5.062 0.000 1.000 1.000
F3 0.147 0.037 0.150 3.988 0.000 1.000 1.000
F4 -0.095 0.046 -0.077 -2.039 0.043 1.000 1.000
The Regression Coefficients
推荐医生

指标
C1 C2 C3 C4 C5 A M L G P RH Scorequality 排名
1 12 601 6 816 6 972 846 545 46 1 446 297 5 241 1 682 5 14 196.46 1
210 5 916 3 999 4 026 840 442 2 1 374 394 777 777 5 7 896.70 2
35 5 278 2 530 2 543 643 290 26 3 770 352 533 533 4.8 7 379.36 3
26 6 894 447 607 278 137 24 3 575 129 533 533 4.8 4 993.78 4
117 5 492 2 363 2 442 257 153 81 1 544 100 714 714 4.7 4 822.01 5
31 2 510 655 687 153 82 25 3 742 64 257 257 4.6 3 254.47 6
288 1 188 7 37 108 57 196 3 427 43 253 111 4.2 3 203.96 7
174 504 500 501 99 40 1 239 54 23 23 4.3 -48.99(2 258.57) 8
8 1 005 416 441 156 58 19 2 439 97 140 83 4.7 1 848.46 9
6 1 656 1 449 1 450 271 104 3 297 168 115 93 4.8 1 533.98 10
63 1 339 1 210 1 210 164 66 0 908 98 99 99 4.6 1 202.40 11
The Performance Score and Ranking of Recommended Doctors for Target Patient h
推荐医生

得分
Score 排名
1 0.136 3 1
210 0.097 6 2
35 0.095 5 3
26 0.082 0 4
117 0.080 6 5
31 0.070 3 6
288 0.067 9 7
8 0.061 2 8
6 0.059 4 9
63 0.056 8 10
174 0.045 0 11
The Score and Ranking of Recommended Doctors
The Results of Three Sets of Experiments
[1] Huang Y F, Liu P, Pan Q, et al. A Doctor Recommendation Algorithm Based on Doctor Performances and Patient Preferences[C]// Proceedings of 2012 International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP). IEEE, 2012: 92-95.
[2] 刘彭. 基于组合模型的医生推荐系统研究与实现[D]. 上海:东华大学, 2013.
[2] ( Liu Peng. Research and Implementation of Doctors Recommendation System Based on Hybrid Model[D]. Shanghai: Donghua University, 2013.)
[3] Jiang H X, Xu W. How to Find Your Appropriate Doctor: An Integrated Recommendation Framework in Big Data Context[C]// Proceedings of 2014 IEEE Symposium on Computational Intelligence in Healthcare and E-health (CICARE). IEEE, 2014: 154-158.
[4] 徐守坤, 吴伟伟. 基于语义的医疗资源均衡推荐算法[J]. 计算机工程, 2015,41(9):74-79.
doi: 10.3969/j.issn.1000-3428.2015.09.013
[4] ( Xu Shoukun, Wu Weiwei. Balance Recommendation Algorithm for Medical Resources Based on Semantic[J]. Computer Engineering, 2015,41(9):74-79.)
doi: 10.3969/j.issn.1000-3428.2015.09.013
[5] Zhang Y, Chen M, Huang D J, et al. iDoctor: Personalized and Professionalized Medical Recommendations Based on Hybrid Matrix Factorization[J]. Future Generation Computer Systems, 2017,66:30-35.
doi: 10.1016/j.future.2015.12.001
[6] 李勇, 黄俊. 一种混合医生推荐算法的研究[J]. 信息通信, 2018(2):67-70.
[6] ( Li Yong, Huang Jun. A Search of Personalized Doctor Recommendation Algorithm[J]. Information & Communications, 2018(2):67-70.)
[7] López-Nores M, Blanco-Fernández Y, Pazos-Arias J J, et al. Property-based Collaborative Filtering for Health-aware Recommender Systems[J]. Expert Systems with Applications, 2012,39(8):7451-7457.
doi: 10.1016/j.eswa.2012.01.112
[8] Kim J H, Lee D S, Chung K Y. Item Recommendation Based on Context-aware Model for Personalized U-healthcare Service[J]. Multimedia Tools and Applications, 2014,71(2):855-872.
doi: 10.1007/s11042-011-0920-0
[9] 孙崇林. 基于多标签分类和协同过滤的医生推荐系统的研究与实现[D]. 大连:大连理工大学, 2015.
[9] ( Sun Chonglin. Research and Implementation on Doctor Recommender System Based on Multi-label Classification and Collaborative Filtering[D]. Dalian: Dalian University of Technology, 2015.)
[10] 高山, 刘炜, 崔勇, 等. 一种融合多种用户行为的协同过滤推荐算法[J]. 计算机科学, 2016,43(9):227-231.
[10] ( Gao Shan, Liu Wei, Cui Yong, et al. Collaborative Filtering Algorithm Integrating Multiple User Behaviors[J]. Computer Science, 2016,43(9):227-231.)
[11] 李诗羽. 基于协同过滤算法的个性化推荐系统的设计与实现[J]. 信息与电脑(理论版), 2018(11):53-54.
[11] ( Li Shiyu. Design and Implementation of Personalized Recommendation System Based on Collaborative Filtering Algorithm[J]. China Computer & Communication(Theoretical Edition), 2018(11):53-54.)
[12] 范灿华. 基于知识图谱的精准导医系统[D]. 广州:华南理工大学, 2017.
[12] ( Fan Canhua. A Knowledge Graph Based System on the Accurate Doctors' Recommendation[D]. Guangzhou: South China University of Technology, 2017.)
[13] 刘玉文, 王凯, 徐济成. 基于概念格的本体医疗资源语义推荐方法[J]. 湖州师范学院学报, 2017,39(2):47-56.
[13] ( Liu Yuwen, Wang Kai, Xu Jicheng. Semantic Recommendation Method of Ontology Based on Concept Lattice[J]. Journal of Huzhou University, 2017,39(2):47-56.)
[14] Huang Z X, Lu X D, Duan H L, et al. Collaboration-based Medical Knowledge Recommendation[J]. Artificial Intelligence in Medicine, 2012,55(10):13-24.
doi: 10.1016/j.artmed.2011.10.002
[15] Mikolov T, Sutskever I, Chen K, et al. Distributed Representations of Words and Phrases and their Compositionality[C]// Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2 . 2013: 3111-3119.
[16] 熊富林, 邓怡豪, 唐晓晟. Word2vec的核心架构及其应用[J]. 南京师范大学学报(工程技术版), 2015,15(1):43-48.
[16] ( Xiong Fulin, Deng Yihao, Tang Xiaosheng. The Architecture of Word2vec and Its Applications[J]. Journal of Nanjing Normal University(Engineering and Technology Edition), 2015,15(1):43-48.)
[17] 李心蕾, 王昊, 刘小敏, 等. 面向微博短文本分类的文本向量化方法比较研究[J]. 数据分析与知识发现, 2018,2(8):41-50.
[17] ( Li Xinlei, Wang Hao, Liu Xiaomin, et al. Comparing Text Vector Generators for Weibo Short Text Classification[J]. Data Analysis and Knowledge Discovery, 2018,2(8):41-50.)
[18] Cmic J. Introdcction to Modem Information Retrieval[M]. McGraw-Hill, 2011.
[19] 杨雪萍. 科研社交网站中的学者推荐研究[D]. 武汉: 华中师范大学, 2017.
[19] ( Yang Xueping. Research on Researcher Recommendation in Scientific Social Website[D]. Wuhan: Central China Normal University, 2017.)
[20] Arazy O, Kumar N, Shapira. Improving Social Recommender Systems[J]. IT Professional, 2009,11(4):38-44
[21] Fox E A, Shaw J A. Combination of Multiple Searches[J]. NIST Special Publication, 1994: 243-243.
[22] 叶存辉. 在线医疗平台医师受访量影响因素分析——以好大夫在线为例[D]. 北京: 北京外国语大学, 2017.
[22] ( Ye Cunhui. An Examination of Affecting Factors on Consultation Rates on Online Medical Platforms: The Case of Hao Dai Fu Online[D]. Beijing: Beijing Foreign Studies University, 2017.)
[23] 孙晓曦. 协同过滤推荐在医疗领域的应用研究[D]. 合肥: 合肥工业大学, 2014.
[23] Sun Xiaoxi. Research on Collaborative Filtering and Application of Recommendation System in the Medical Field[D]. Hefei: Hefei University of Technology, 2014.
[24] 好大夫在线[EB/OL]. [2019-02-28]. https://www.haodf.com/jibing/jingshenxinlike/list.htm.
[24] ( Hao Dai Fu Online[EB/OL]. [2019-02-28]. https://www.haodf.com/jibing/jingshenxinlike/list.htm.
[25] Word2Vec训练语料库[EB/OL]. (2018-06-08). https://pan.baidu.com/s/1TZ8GII0CEX32ydjsfMc0zw.
[25] ( A Corpus of Word2Vec[EB/OL]. (2018-06-08). https://pan.baidu.com/s/1TZ8GII0CEX32ydjsfMc0zw.
[26] 郭呈全, 陈希镇. 主成分回归的SPSS实现[J]. 统计与决策, 2011(5):157-159.
[26] ( Guo Chengquan, Chen Xizhen. SPSS Implementation of Principal Component Regression Analysis[J]. Statistics and Decision, 2011(5):157-159.)
[1] Tang Xiaobo,Gao Hexuan. Classification of Health Questions Based on Vector Extension of Keywords[J]. 数据分析与知识发现, 2020, 4(7): 66-75.
[2] Ye Jiaxin,Xiong Huixiang,Tong Zhaoli,Meng Qiuqing. Collaborative Tagging for Doctors in Online Medical Community[J]. 数据分析与知识发现, 2020, 4(6): 118-128.
[3] Yue Lixin,Liu Ziqiang,Hu Zhengyin. Evolution Analysis of Hot Topics with Trend-Prediction[J]. 数据分析与知识发现, 2020, 4(6): 22-34.
[4] Tao Xing,Zhang Xiangxian,Guo Shunli,Zhang Liman. Automatic Summarization of User-Generated Content in Academic Q&A Community Based on Word2Vec and MMR[J]. 数据分析与知识发现, 2020, 4(4): 109-118.
[5] Ye Jiaxin,Xiong Huixiang,Jiang Wuxuan. A Physician Recommendation Algorithm Integrating Inquiries and Decisions of Patients[J]. 数据分析与知识发现, 2020, 4(2/3): 153-164.
[6] Xue Fuliang,Liu Lifang. Fine-Grained Sentiment Analysis with CRF and ATAE-LSTM[J]. 数据分析与知识发现, 2020, 4(2/3): 207-213.
[7] Gong Lijuan,Wang Hao,Zhang Zixuan,Zhu Liping. Reducing Dimensions of Custom Declaration Texts with Word2Vec[J]. 数据分析与知识发现, 2020, 4(2/3): 89-100.
[8] Cuiqing Jiang,Yibo Guo,Yao Liu. Constructing a Domain Sentiment Lexicon Based on Chinese Social Media Text[J]. 数据分析与知识发现, 2019, 3(2): 98-107.
[9] Li Xinlei,Wang Hao,Liu Xiaomin,Deng Sanhong. Comparing Text Vector Generators for Weibo Short Text Classification[J]. 数据分析与知识发现, 2018, 2(8): 41-50.
[10] Gao Yongbing,Yang Guipeng,Zhang Di,Ma Zhanfei. Detecting Events from Official Weibo Profiles Based on Post Clustering with Burst Words[J]. 数据分析与知识发现, 2017, 1(9): 57-64.
[11] Zhang Qin,Guo Hongmei,Zhang Zhixiong. Extracting Entity Relationship with Word Embedding Representation Features[J]. 数据分析与知识发现, 2017, 1(9): 8-15.
[12] Xia Tian. Extracting Keywords with Modified TextRank Model[J]. 数据分析与知识发现, 2017, 1(2): 28-34.
[13] Liu Ruilun,Ye Wenhao,Gao Ruiqing,Tang Mengjia,Wang Dongbo. Research on Text Clustering Based on Requirements of Big Data Jobs[J]. 数据分析与知识发现, 2017, 1(12): 32-40.
[14] Luo Wenxin,Chen Chong,Deng Siyi. Detecting Disease Associations with Word2Vec from Consumer Health Information[J]. 现代图书情报技术, 2016, 32(9): 78-87.
[15] Ning Jianfei,Liu Jiangzhen. Using Word2vec with TextRank to Extract Keywords[J]. 现代图书情报技术, 2016, 32(6): 20-27.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn