Please wait a minute...
Advanced Search
数据分析与知识发现  2018, Vol. 2 Issue (1): 88-98    DOI: 10.11925/infotech.2096-3467.2017.1053
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
高维电子病历的数据降维策略与实证研究*
牟冬梅(),王萍,赵丹宁
吉林大学公共卫生学院 长春 130021
Reducing Data Dimension of Electronic Medical Records: An Empirical Study
Dongmei Mu(),Ping Wang,Danning Zhao
School of Public Health, Jilin University, Changchun 130021, China
全文: PDF(1630 KB)   HTML
输出: BibTeX | EndNote (RIS)      
摘要 

目的】以高维的结构化电子病历数据为研究对象, 探究数据降维的策略, 为电子病历知识发现提供参考。【方法】通过文献调研进行初步约简, 再分别利用主成分分析法提取特征根大于1的因子、提取累计贡献率大于85%的因子, 利用Logistic回归方法提取有显著差异性的因子进行降维; 根据实证研究定性定量评价三种方法提取的属性结果。【结果】三种降维方法分别提取8个、17个和14个属性, 经过定性和定量评价发现, 利用主成分分析方法提取特征根大于1的因子的降维效果相对较好。【局限】数据样本量有限, 未能搜集一定时间跨度的数据进行深入分析。【结论】本研究制定的数据降维策略有效, 可以在保留目标数据原始特征的同时, 对高维空间数据进行识别、定位、分析, 用较少的属性特征代替整体数据集, 解决电子病历数据维度过高带来的数据挖掘灾难, 提高数据挖掘的效率和分析结果的准确性。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
牟冬梅
王萍
赵丹宁
关键词 降维数据挖掘知识发现电子病历    
Abstract

[Objective] This paper explores the strategy of reducing the data dimension of electronic medical records, aiming to improve the knowledge discovery. [Methods] First, we conducted preliminary dimension reduction through literature review. Then, we used three methods to finish the second round of dimension reduction. We extracted the factors with the eigenvalue greater than 1, with the cumulative contribution rate greater than 85%, as well as factors of significant differences. Finally, we compared results of the three methods with empirical research. [Results] The dimensional reduction methods extracted 8, 17 and 14 attributes respectively. After qualitative and quantitative evaluation, the principal component analysis method yielded the best result, whose dimension of the feature root was larger than 1. [Limitations] The sample size needs to be expanded for more in-depth analysis. [Conclusions] The proposed method could effectively reduce the data dimension of electronic medical records.

Key wordsDimension Reduction    Data Mining    Knowledge Discovery    Electronic Medical Record
收稿日期: 2017-10-23     
基金资助:*本文系国家自然科学基金面上项目“嵌入式知识服务驱动下的领域多维知识库构建”(项目编号: 71573102)和吉林省教育厅社会科学项目“虚拟健康社区知识发现与实证研究”(项目编号: JJKH20170881SK)的研究成果之一
引用本文:   
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.
Dongmei Mu,Ping Wang,Danning Zhao. Reducing Data Dimension of Electronic Medical Records: An Empirical Study. Data Analysis and Knowledge Discovery, DOI:10.11925/infotech.2096-3467.2017.1053.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2017.1053
图1  高维电子病历的数据降维策略
表格类型 表格数 数据量 属性简介
诊断表 1 16 508 patient ID、visit ID、diagnosis、诊断时间、诊断内容、治疗时间、治疗结果
基本信息表 1 10 791 patient ID、birth place、data of birth、sex
病人ID表 2 10 791 patient ID
生理指标表 1 65 536 patient ID、visit ID、record data、体重、体温、脉搏、呼吸、血压
生化指标表 12 45 803 主题词、申请序号、病人ID号、性别、诊断、检验时间、费用类型、血液样本类型、样本记录说明、检查时间及各种生化指标: 总胆固醇、高密度脂蛋白、低密度脂蛋白、甘油三酯、乳酸脱氢酶、载脂蛋白A、载脂蛋白B等
用药表 1 65 536 病人ID号、药品名称、起止时间、用法与用量、用药频次、费用等
糖化指标表 12 5 230 主题词(全血糖化血红蛋白)、申请序号、病人ID、性别、年龄、费别、血液样本类型、标本说明、时间、全血糖化血红蛋白测定量
表1  数据内容及特征简介
序号 主成分 英文缩写 旋转后因子载荷 特征根
1 直接胆红素 DBIL 0.959 2.743
2 Ca 0.820 2.563
3 Na 0.857 2.339
4 载脂蛋白B apoB 0.786 2.190
5 总胆固醇 TC 0.866 1.826
6 K 0.686 1.738
7 全血糖化血红蛋白 Hb 0.790 1.507
8 高密度脂蛋白 HDL 0.731 1.119
表2  旋转后各主成分因子载荷(提取特征根大于1因子)
图2  原始数据诊断表和生化表截图(部分)
图3  电子病历数据降维流程
图4  各组分特征值碎石图
序号 主成分 英文缩写 旋转后
因子载荷
累计贡献率
1 直接胆红素 DBIL 0.961 10.158
2 血清白蛋白 ALB 0.873 19.650
3 总胆固醇 TC 0.944 28.314
4 氯化物 Cl 0.914 36.427
5 甘油三酯 TG 0.890 43.191
6 全血糖化血红蛋白 Hb 0.834 49.627
7 载脂蛋白A1 apoA1 0.786 55.207
8 年龄 age 0.870 59.350
9 二氧化碳 CO2 0.912 63.033
10 K 0.952 66.525
11 游离钙 f-Ca 0.964 69.908
12 血清尿酸 SUA 0.942 73.159
13 性别 sex 0.888 76.242
14 Mg 0.971 79.214
15 乳酸脱氢酶 LDH 0.972 81.920
16 血清脂蛋白 LP(a) 0.973 84.609
17 糖化血清蛋白 GSP 0.934 87.023
表3  旋转后各主成分因子载荷(提取特累计贡献率大于85%因子)
序号 属性 B sig. Exp(B)
1 葡萄糖(GS) 0.103 0.000 1.108
2 总胆固醇(TC) 0.441 0.000 1.554
3 乳酸脱氢酶(LDH) 0.005 0.000 1.005
4 低密度脂蛋白(LDL) -0.544 0.000 0.580
5 全血糖化血红蛋白(Hb) -0.128 0.005 0.880
6 总胆红素(STB) -0.030 0.008 0.970
7 直接胆红素(DBIL) 0.246 0.000 1.279
8 总胆汁酸(TBA) 0.048 0.004 1.049
9 钾(K) -0.670 0.000 0.512
10 氯化物(Cl) -0.105 0.000 0.901
11 无机磷(P) -1.215 0.000 2.97
12 镁(Mg) 2.948 0.000 19.071
13 游离钙(f-Ca) 3.009 0.035 20.265
14 二氧化碳(CO2) -0.176 0.000 0.839
表4  Logistic回归分析结果(提取差异有显著性的因子)
项目 降维方法1 降维方法2 降维方法3
降维原理 特征向量
特征根
特征向量累
计贡献率
特征向量患病
差异显著性
降维方法 主成分分析 主成分分析 逻辑回归
降维条件 特征根大于1 累计贡献率大于85% P值小于0.05
提取因子数量 8个 17个 14个
提取因子百分比 29.63% 62.96% 51.85%
表5  三种降维方法的比较
方法 TP FP Precision Recall F-Measure ROC Area Kappa
未降维 0.935 0.096 0.935 0.935 0.935 0.925 0.838
降维方法1 0.975 0.045 0.974 0.975 0.974 0.975 0.936
降维方法2 0.933 0.093 0.934 0.933 0.934 0.925 0.836
降维方法3 0.941 0.088 0.941 0.941 0.941 0.937 0.879
表6  基线精度及J48算法构建模型的结果
[1] 罗旭, 刘友江. 医疗大数据研究现状及其临床应用[J]. 医学信息学杂志, 2015, 36(5): 10-14.
(Luo Xu, Liu Youjiang.Medical Big Data Research Status and Its Clinical Application[J]. Journal of Medical Informatics, 2015, 36(5): 10-14.)
[2] Godinho T M, Costa C, Oliveira J L.Intelligent Generator of Big Data Medical Imaging Repositories[J]. IET Software, 2017, 11(3): 100-104.
doi: 10.1049/iet-sen.2016.0191
[3] 毕达天, 邱长波, 张晗. 数据降维技术研究现状及其进展[J]. 情报理论与实践, 2013, 36(2): 125-128.
(Bi Datian, Qiu Changbo, Zhang Han.Research Status and Progress of Data Dimensionality Reduction Technology[J]. Information Studies: Theory & Application, 2013, 36(2): 125-128.)
[4] 雷健波. 电子病历的核心价值与临床决策支持[J]. 中国数字医学, 2008, 3(3): 26-30.
doi: 10.3969/j.issn.1673-7571.2008.03.009
(Lei Jianbo.Clinical Decision Support and the Core Value of Electronic Medical Record[J].China Digital Medicine, 2008, 3(3): 26-30.)
[5] Byrd R J, Steinhubl S R, Sun J, et al.Automatic Identification of Heart Failure Diagnostic Criteria, Using Text Analysis of Clinical Notes from Electronic Health Records[J]. International Journal of Medical Informatics, 2014, 83(12): 983-992.
doi: 10.1016/j.ijmedinf.2012.12.005 pmid: 23317809
[6] Ye J, Farnum M, Yang E, et al.Sparse Learning and Stability Selection for Predicting MCI to AD Conversion Using Baseline ADNI Data[J]. BMC Neurology, 2012, 12: 46.
doi: 10.1186/1471-2377-12-46 pmid: 22731740
[7] Kawata T, Daimon M, Miyazaki S, et al.Coronary Microvascular Function is Independently Associated with Left Ventricular Filling Pressure in Patients with Type 2 Diabetes Mellitus[J]. Cardiovascular Diabetology, 2015, 14: 98.
doi: 10.1186/s12933-015-0263-7 pmid: 4525728
[8] 郭珉江. 数据挖掘技术在疾病诊断相关分组中的应用[D]. 长沙: 中南大学, 2009.
(Guo Minjiang.Research on the Application of Data Mining Technology in Disease Related Groups[D]. Changsha: Central South University, 2009.)
[9] Alvarez C A, Clark C A, Zhang S, et al.Predicting out of Intensive Care Unit Cardiopulmonary Arrest or Death Using Electronic Medical Record Data[J]. BMC Medical Informatics and Decision Making, 2013, 13: 28.
doi: 10.1186/1472-6947-13-28 pmid: 23442316
[10] Matheny M E, Fitzhenry F, Speroff T, et al.Detection of Infectious Symptoms from VA Emergency Department and Primary Care Clinical Documentation[J]. International Journal of Medical Informatics, 2012, 81(3): 143-156.
doi: 10.1016/j.ijmedinf.2011.11.005 pmid: 22244191
[11] Ciecholewski M.Ischemic Heart Disease Detection Using Selected Machine Learning Methods[J]. International Journal of Computer Mathematics, 2013, 90(8): 1734-1759.
doi: 10.1080/00207160.2012.742189
[12] Ramírez J, Górriz J M, Salas-Gonzalez D, et al.Computer- aided Diagnosis of Alzheimer’s Type Dementia Combining Support Vector Machines and Discriminant Set of Features[J]. Information Sciences, 2013, 237: 59-72.
doi: 10.1016/j.ins.2009.05.012
[13] Pierson E, Yau C.ZIFA: Dimensionality Reduction for Zero- inflated Single-cell Gene Expression Analysis[J]. Genome Biology, 2015, 16: 241.
doi: 10.1186/s13059-015-0805-z pmid: 4630968
[14] Yao F, Coquery J, Cao K A L. Independent Principal Component Analysis for Biologically Meaningful Dimension Reduction of Large Biological Data Sets[J]. BMC Bioinformatics, 2012, 13: 24.
doi: 10.1186/1471-2105-13-24 pmid: 22305354
[15] Gui J, Moore J H, Williams S M, et al.A Simple and Computationally Efficient Approach to Multifactor Dimensionality Reduction Analysis of Gene-Gene Interactions for Quantitative Traits[J]. PLOS One, 2013, 8(6): e66545.
doi: 10.1371/journal.pone.0066545 pmid: 3689797
[16] 周威光. 粗糙集理论处理海量电子病历的研究与应用[D].杭州: 浙江理工大学, 2017.
(Zhou Weiguang.Research and Application of Rough Set Theory in Dealing with Massive Electronic Medical Records [D]. Hangzhou: Zhejiang Sci-Tech University, 2017.)
[17] 田宇驰, 胡亮. 基于SVM的一种医疗数据分析模型[J].东北师大学报 : 自然科学版, 2015, 47(1): 77-82.
doi: 10.16163/j.cnki.22-1123/n.2015.01.015
(Tian Yuchi, Hu Liang.A Medical Data Analysis Model Based on SVM[J]. Journal of Northeast Normal University, 2015, 47(1): 77-82.)
[18] 佘侃侃, 胡孔法, 王珍. 基于变精度容差粗糙集模型及属性敏感度约简的方剂配伍研究[J]. 世界科学技术: 中医药现代化, 2014(6): 1222-1228.
doi: 10.11842/wst.2014.06.003
(She Kankan, Hu Kongfa, Wang Zhen.Research on Chinese Prescription Compatibility Based on Variable Precision Tolerance Model and Attribute Sensitivity Reduction[J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology, 2014(6): 1222-1228.)
[19] Carter J T.Electronic Medical Records and Quality Improvement[J]. Neurosurgery Clinics of North America, 2015, 26(2): 245-251.
doi: 10.1016/j.nec.2014.11.018
[20] 中华人民共和国国家卫生和计划生育委员会.关于发布《电子病历基本数据集第1部分: 病例概要》等20项卫生行业标准的通告(国卫通〔2014〕5号)[EB/OL]. (2014-06-19). [2017-04-15]. .
(National Health and Family Planning Commission of the People’s Republic of China. Notice on Publishing 20 Health Industry Standards such as Basic Medical Data Record Part 1: Case Summary and Other Health Industry Standards [EB/OL]. (2014-06-19). [2017-04-15]. .)
[21] Grauer R, Barber M, Scheeren J.Exploring Microsoft Office Excel 2007[M]. Prentice Hall, 2007.
[22] Moore B.Principal Component Analysis in Linear Systems: Controllability, Observability, and Model Reduction[J]. IEEE Transactions on Automatic Control, 1981, 26(1): 17-32.
doi: 10.1109/TAC.1981.1102568
[23] Hosmer D W, Lemeshow S.Applied Logistic Regression[M]. Wiley, 2000.
[24] 张冬慧, 唐智柳, 李岚, 等. 我国21世纪初糖尿病患病率系统综述[J]. 上海预防医学, 2012, 24(9): 492-495.
doi: 10.3969/j.issn.1004-9231.2012.09.009
(Zhang Donghui, Tang Zhiliu, Li Lan, et al.A Systematic Review on Prevalence Rate of Diabetes in 2001-2010 in China[J]. Shanghai Journal of Preventive Medicine, 2012, 24(9): 492-495.)
[25] 国家人口与健康科学数据共享服务平台. 糖尿病数据集[EB/OL]. (2015-06-13). [2017-04-15]. .
(National Scientific Data Sharing Platform for Population and Health.Diabetes Data Set [EB/OL]. (2015- 06-13). [2017-04-15].
[26] 百度百科. 新年龄分段 [EB/OL]. [2016-05-14]..
(Baidu Encyclopedia.New Age Segmentation [EB/OL]. [2016-05-14]..)
[27] 王庭俊, 严孙杰, 陈纯娴. 不同性别2型糖尿病患者血脂、血压与骨质疏松的关系[J]. 中华高血压杂志, 2012, 20(12): 1152-1156.
(Wang Tingjun, Yan Sunjie, Chen Chunxian.Relationship Between Blood Lipid, Blood Pressure and Osteoporosis in Male and Female Patients with Type 2 Diabetes[J]. Chinese Journal of Hypertension, 2012, 20(12): 1152-1156.)
[28] 黄琼刁, 邓万溪, 黄钦展, 等.糖尿病主要并发症年龄与体质之相关性研究[J]. 世界中医药, 2013, 8(3): 288-290.
doi: 10.3969/j.issn.1673-7202.2013.03.014
(Huang Qiongdiao, Deng Wanxi, Huang Qinzhan, et al.Study on Correlation of Age and Constitution in Patients with Major Diabetes Complications[J]. World Chinese Medicine, 2013, 8(3): 288-290.)
[29] 石珂, 张悦之, 谢琳, 等. 负性调节葡萄糖转运对糖尿病小鼠视网膜微血管病变的抑制作用[J]. 第二军医大学学报, 2015, 36(2): 147-154.
doi: 10.3724/SP.J.1008.2015.00147
(Shi Ke, Zhang Yuezhi, Xie Lin, et al.Negative Regulation of Glucose Transport Alleciates Microvasculature Pathological Changes of Retinopathy in Diabetic Mice[J]. Academic Journal of Second Military Medical University, 2015, 36(2): 147-154.)
[30] 张媛媛, 张日华, 杜新丽, 等. 血清尿酸水平与糖尿病各代谢因子的相关性研究[J]. 南京医科大学学报: 自然科学版, 2013(1): 62-67.
(Zhang Yuanyuan, Zhang Rihua, Du Xinli, et al.Association Between Serum Eric Acid Concentration and the Metabolic Factors of Diabetes[J]. Acta Universitatis Medicinalis Nanjing, 2013(1): 62-67.)
[31] Scanlon G, Connell P, Ratzlaff M, et al.Macular Pigment Optical Density is Lower in Type 2 Diabetes, Compared with Type 1 Diabetes and Normal Controls[J].Retina, 2015, 35(9): 1808-1816.
doi: 10.1097/IAE.0000000000000551 pmid: 25932554
[32] 杨维娜, 王璇, 蓝茜, 等. 2型糖尿病并发周围血管病变的临床流行病学分析[J]. 西安交通大学学报: 医学版, 2013, 34(1): 73-76.
doi: 10.3969/j.issn.1671-8259.2013.01.017
(Yang Weina, Wang Xuan, Lan Qian, et al.Clinical Epidemiological Analysis of Type 2 Diabetes Patients with Peripheral Vascular Disease[J].Journal of Xi’an Jiaotong University: Medical Sciences, 2013, 34(1): 73-76.)
[33] Das R, Kerr R, Chakravarthy U, et al.Dyslipidemia and Diabetic Macular Edema: A Systematic Review and Meta- Analysis[J]. Ophthalmology, 2015, 122(9): 1820-1827.
doi: 10.1016/j.ophtha.2015.05.011
[34] 魏忠燕, 谢立科, 镇华, 等. 同型半胱氨酸、尿酸、乳酸脱氢酶及肌酸激酶与糖尿病视网膜病变的关系[J]. 眼科新进展, 2011, 31(9): 846-848.
(Wei Zhongyan, Xie Like, Zhen Hua, et al.Correlation of Homocysteine, Uric Acid, Lac-tate Dehydrogenase and Creatine Kinase with Diabetic Retinopathy[J]. Recent Advances in Ophthalmology, 2011, 31(9): 846-848.)
[35] 白洲霞. 2型糖尿病血清载脂蛋白A1、B、脂蛋白(a)水平观察分析[J]. 国际检验医学杂志, 2010, 31(10): 1146-1147.
doi: 10.3969/j.issn.1673-4130.2010.10.041
(Bai Zhouxia.Observation and Analysis of Serum Apolipoprotein A1, B and Lipoprotein (a) Levels in Type 2 Diabetes Mellitus[J]. International Journal of Laboratory Medicine, 2010, 31(10): 1146-1147.)
[36] 王晶晶, 田晨光. 糖化血红蛋白、糖化血清蛋白、血细胞参数在老年糖尿病微血管病变患者中的应用价值[J]. 中华实用诊断与治疗杂志, 2010, 24(2): 143-145.
(Wang Jingjing, Tian Chenguang.Application of Glycosylated Hemoglobin, Glycosylated Serum Protein and Peripheral Blood Cell Parametersin Senile Patients with Diabetic Microangiopathy[J]. Journal of Chinese Practical Diagnosis and Therapy, 2010, 24(2): 143-145.)
[37] Takahara M, Katakami N, Osonoi T, et al.Different Impacts of Cardiovascular Risk Factors on Arterial Stiffness Versus Arterial Wall Thickness in Japanese Patients with Type 2 Diabetes Mellitus[J]. Journal of Atherosclerosis and Thrombosis, 2015, 22(9): 971-980.
doi: 10.5551/jat.29090 pmid: 25864887
[38] Kaidonis G, Burdon K P, Gillies M C, et al.Common Sequence Variation in the VEGFC Gene is Associated with Diabetic Retinopathy and Diabetic Macular Edema[J]. Ophthalmology, 2015, 122(9): 1828-1836.
doi: 10.1016/j.ophtha.2015.05.004
[39] 杜玮, 刘子扬, 周艳艳, 等. 糖尿病视网膜病变与血清胆红素水平的关系[J]. 眼科新进展, 2012, 32(5): 484-485.
doi: 10.3969/j.issn.1006-7795.2010.01.027
(Du Wei, Liu Ziyang, Zhou Yanyan, et al.Relationship Between Diabetic Retinopathy and Serum Bilirubin Level[J]. Recent Advances in Ophthalmology, 2012, 32(5): 484-485.)
[40] 项旻, 杨虹, 叶成夫, 等. 女性2型糖尿病视网膜病变患者血微量元素水平及其相关因素分析[J]. 中国医药导报, 2014, 11(13): 9-11.
(Xiang Min, Yang Hong, Ye Chengfu, et al.Level of Blood Trace Elements in Female Patients with Type 2 Diabetic Retinopathy and Its Related Factors Analysis[J]. China Medical Herald, 2014, 11(13): 9-11.)
[1] 张志强,范少萍,陈秀娟. 面向精准医学知识发现的生物医学信息学发展*[J]. 数据分析与知识发现, 2018, 2(1): 1-8.
[2] 胡忠义,王超群,吴江. 融合多源网络评估数据及URL特征的钓鱼网站识别技术研究*[J]. 数据分析与知识发现, 2017, 1(6): 47-55.
[3] 江思伟,谢振平,陈梅婕,蔡明. 混合特征数据的自解释归约建模方法*[J]. 数据分析与知识发现, 2017, 1(12): 92-100.
[4] 刘冰瑶,马静,李晓峰. 一种“特征降维”文本复杂网络的话题表示模型*[J]. 数据分析与知识发现, 2017, 1(11): 53-61.
[5] 谢秀芳,张晓林. 针对科技路线图的文本挖掘研究: 集成分析及可视化*[J]. 数据分析与知识发现, 2017, 1(1): 16-25.
[6] 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.
[7] 李峰,李书宁,于静. 面向院系的高校毕业生图书馆记忆系统[J]. 现代图书情报技术, 2016, 32(5): 99-103.
[8] 刘红煦,曲建升. 主流Meta分析软件功能及其在领域知识发现的拓展应用研究*[J]. 现代图书情报技术, 2016, 32(5): 9-21.
[9] 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.
[10] 赵静娴. 基于决策树的网络伪舆情识别研究[J]. 现代图书情报技术, 2015, 31(6): 78-84.
[11] 何建民, 王哲. 社交网络话题信息传播影响簇发现谱系挖掘方法[J]. 现代图书情报技术, 2015, 31(5): 65-72.
[12] 黄文彬, 徐山川, 马龙, 王军. 利用通信数据的移动用户行为分析[J]. 现代图书情报技术, 2015, 31(5): 80-87.
[13] 郝玫, 王道平. 面向供应链的产品评论中客户关注特征挖掘方法研究[J]. 现代图书情报技术, 2014, 30(4): 65-70.
[14] 孙鸿飞, 侯伟. 改进TFIDF算法在潜在合作关系挖掘中的应用研究[J]. 现代图书情报技术, 2014, 30(10): 84-92.
[15] 顾立平. 论文级别计量研究:应用案例分析[J]. 现代图书情报技术, 2013, 29(11): 1-7.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
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
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn