基于异构星型网络分析的药物推荐改进算法HIC-MedRank

doi:10.11772/j.issn.1001-9081.2017.08.2368

计算机应用 ›› 2017, Vol. 37 ›› Issue (8): 2368-2373.DOI: 10.11772/j.issn.1001-9081.2017.08.2368

基于异构星型网络分析的药物推荐改进算法HIC-MedRank

邹林霖¹, 李学明^1,2, 李雪³, 袁洪⁴, 刘星⁴

1. 重庆大学计算机学院, 重庆 400044;
2. 重庆大学信息物理社会可信服务计算教育部重点实验室, 重庆 400044;
3. 昆士兰大学信息技术与电子工程学院, 澳大利亚布里斯班 4072;
4. 中南大学湘雅三医院心内科, 长沙 410013

收稿日期:2017-02-10 修回日期:2017-03-15 出版日期:2017-08-10 发布日期:2017-08-12
作者简介:邹林霖(1990-),女,四川内江人,硕士研究生,主要研究方向:机器学习、数据挖掘;李学明(1967-),男,重庆人,教授,博士,主要研究方向:数据挖掘、大数据、高性能计算;李雪(1956-),男,重庆人,教授,博士,主要研究方向:数据挖掘、社会计算、智能信息系统;袁洪(1957-),男,湖南长沙人,主任医师,教授,博士,主要研究方向:高血压个体化治疗、临床心血管药理;刘星(1989-),女,湖南长沙人,医师,博士研究生,主要研究方向:高血压大数据。
基金资助:
国家863计划项目（2015AA015308）；国家自然科学基金资助项目（81273594）；国家科技重大专项（2012ZX09303014001）。

HIC-MedRank:improved drug recommendation algorithm based on heterogeneous information network

ZOU Linlin¹, LI Xueming[Author]) AND 1[Journal]) AND year[Order])" target="_blank">LI Xueming^1,2, LI Xue³, YUAN Hong⁴, LIU Xing⁴

1. College of Computer Science, Chongqing University, Chongqing 400044, China;
2. Key Laboratory of Dependable Service Computing in Cyber Physical Society, Ministry of Education, Chongqing University, Chongqing 400044, China;
3. School of Information Technology and Electrical Engineering, University of Queensland, Brisbane 4072, Australia;
4. Department of Cardiology, the Third Xiangya Hospital, Central South University, Changsha Hunan 410013, China

Received:2017-02-10 Revised:2017-03-15 Online:2017-08-10 Published:2017-08-12
Supported by:
This work is partially supported by the National High Technology Research and Development Program (863 Program) of China (2015AA015308),the National Science Foundation of China (81273594),the National Science and Technology Major Project (2012ZX09303014001).

摘要/Abstract

摘要： 伴随着医疗文献数据库的快速增长，缺乏经验的初级医师在为患者开处方时难以阅读大量的医疗文献来获得科学的决策辅助。2013年提出的MedRank算法从Medline数据库中提取医学信息异构星型网络，基于"有疗效的药物是由好的文章提及的，好的文章是由优秀的作者写的并刊登在高水平的期刊上"的假设，旨在为各类疾病的患者推荐最具有疗效的药物。该算法仍然存在几个问题：1）模型输入的疾病不是独立的疾病；2）推荐的结果不是具体的药物；3）没有考虑文章的发表时间等其他因素；4）没有定义判定作者、期刊、文章是"好的"的标准。对以上问题进行了研究并提出HIC-MedRank算法，该算法纳入作者的H指数、期刊的影响因子、文章的引用数作为评判作者、期刊、文章是否优秀的指标，并综合考虑文章的发表时间、支持机构、发表类型等因素，为高血压合并慢性肾脏病（CKD）患者推荐最佳的降压药物。在Medline数据集上的实验结果显示HIC-MedRank推荐的药物比MedRank算法推荐的药物更为精准，与主治医师投票选择的药物较为一致，与美国成人高血压治疗指南（JNC）推荐的药物一致性达到80%。

关键词: 异构信息网络, 数据挖掘, 临床决策支持, H指数, 高血压, 慢性肾脏病, 药物推荐

Abstract: With the rapid growth of medical literature, it is difficult for physicians to maintain up-to-date knowledge by reading biomedical literatures. An algorithm named MedRank can be used to recommend influential medications from literature by analyzing information network, based on the assumption that "a good treatment is likely to be found in a good medical article published in a good journal, written by good author(s)", recomending the most effective drugs for all types of disease patients. But the algorithm still has several problems:1) the diseases, as the inputs, are not independent; 2) the outputs are not specific drugs; 3) some other factors such as the publication time of the article are not considered; 4) there is no definition of "good" for the articles, journals and authors. An improved algorithm named HIC-MedRank was proposed by introducing H-index of authors, impact factor of journals and citation count of articles as criterion for defining good authors, journals and articles, and recommended antihypertensive agents for the patients suffered from Hypertension with Chronic Kidney Disease (CKD) by considering published time, support institutions, publishing type and some other factors of articles. The experimental results on Medline datasets show that the recommendation drugs of HIC-MedRank algorithm are more precise than those of MedRank, and are more recognized by attending physicians. The consistency rate is up to 80% by comparing with the JNC guidelines.

Key words: heterogeneous information network, data mining, clinical decision support, H-index, hypertension, Chronic Kidney Disease (CKD), drug recommendation

中图分类号:

邹林霖, 李学明, 李雪, 袁洪, 刘星. 基于异构星型网络分析的药物推荐改进算法HIC-MedRank[J]. 计算机应用, 2017, 37(8): 2368-2373.

ZOU Linlin, LI Xueming, LI Xue, YUAN Hong, LIU Xing. HIC-MedRank:improved drug recommendation algorithm based on heterogeneous information network[J]. Journal of Computer Applications, 2017, 37(8): 2368-2373.

参考文献

[1] 丁香园调查派. 医疗决策支持:文献经久不衰[EB/OL].[2016-01-25]. http://vote.dxy.cn/report/dxy/id/67390. (www.dxy.cn. Clinical decision support:literatures last a long time[EB/OL].[2016-01-25]. http://vote.dxy.cn/report/dxy/id/67390.)
[2] AGHAZADEH S, ALIYEV A Q, EBRAHIMNEJAD M. The role of computerizing physician orders entry (CPOE) and implementing decision support system (CDSS) for decreasing medical errors[C]//AICT 2011:Proceedings of the 20115th International Conference on Application of Information and Communication Technologies. Piscataway, NJ:IEEE, 2011:1-3.
[3] ELDER N C, DOVEY S M. Classification of medical errors and preventable adverse events in primary care:a synthesis of the literature[J]. Journal of Family Practice, 2002, 51(11):927-932.
[4] BOM H S, PARK S H, CHOI J W, et al. Effects of clinical decision support system on reduction of adverse drug events:a meta-analysis[J]. Journal of Korean Society of Medical Informatics, 2002, 8(3):55-60.
[5] REICHRATH J, BENS G, BONOWITZ A, et al. Treatment recommendations for pyoderma gangrenosum:an evidence-based review of the literature based on more than 350 patients[J]. Journal of the American Academy of Dermatology, 2005, 53(2):273-283.
[6] AGARWAL P, SEARLS D B. Literature mining in support of drug discovery[J]. Briefings in Bioinformatics, 2008, 9(6):479-492.
[7] CHEN L, LI X, HAN J. MedRank:discovering influential medical treatments from literature by information network analysis[C]//ADC 2013:Proceedings of the Twenty-Fourth Australasian Database Conference. Darlinghurst, Australia:Australian Computer Society, 2013:3-12.
[8] LANCET T. Chronic kidney disease:refining diagnosis and management[J]. The Lancet, 2014, 384(9941):378.
[9] LINDSEY D. Using citation counts as a measure of quality in science measuring what's measurable rather than what's valid[J]. Scientometrics, 1989, 15(3/4):189-203.
[10] GARFIELD E. Journal impact factor:a brief review[J]. Canadian Medical Association Journal, 1999, 161(8):979-980.
[11] HIRSCH J E. An index to quantify an individual's scientific research output[J]. Proceedings of the National Academy of Sciences of the United States of America, 2005, 102(46):16569-16572.
[12] BALL P. Index aims for fair ranking of scientists[J]. Nature, 2005, 436(7053):900.
[13] SUN Y, HAN J, ZHAO P, et al. RankClus: integrating clustering with ranking for heterogeneous information network analysis [C]// EDBT 2009: Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology. New York: ACM, 2009: 565-576.
[14] SUN Y, YU Y, HAN J. Ranking-based clustering of heterogeneous information networks with star network schema [C]// KDD 2009: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2009: 797-806.
[15] 陈伟伟,高润霖,刘力生,等.中国心血管病报告2013概要[J].中国循环杂志,2014(7):487-491. (CHEN W W, GAO R L, LIU L S, et al. Outline of 2013 China cardiovascular disease report [J]. Chinese Circulation Journal, 2014(7): 487-491.)
[16] HUSAIN A, AZIM M S, MITRA M, et al. A review of pharmacological and pharmaceutical profile of Irbesartan [J]. Pharmacophore, 2011, 2(6): 276-86.
[17] FAGIN R, KUMAR R, SIVAKUMAR D. Comparing top k lists [J]. SIAM Journal on Discrete Mathematics, 2003, 17(1): 134-160.
[18] EGGHE L. Theory and practice of the G-index [J]. Scientometrics, 2006, 69(1): 131-152.

基于异构星型网络分析的药物推荐改进算法HIC-MedRank

HIC-MedRank:improved drug recommendation algorithm based on heterogeneous information network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	刘世泽, 秦艳君, 王晨星, 苏琳, 柯其学, 罗海勇, 孙艺, 王宝会. 基于深度残差长短记忆网络交通流量预测算法[J]. 计算机应用, 2021, 41(6): 1566-1572.
[2]	李旭娟, 皮建勇, 黄飞翔, 贾海朋. 基于自生成深度神经网络的4D航迹预测[J]. 计算机应用, 2021, 41(5): 1492-1499.
[3]	林怿星, 唐华. 基于异构信息网络的混合推荐模型[J]. 计算机应用, 2021, 41(5): 1348-1355.
[4]	陈凯, 于彦伟, 赵金东, 宋鹏. 基于城市交通监控大数据的工作位置推理方法[J]. 计算机应用, 2021, 41(1): 177-184.
[5]	龙洋洋, 陈玉玲, 辛阳, 豆慧. 基于联盟区块链的安全能源交易方案[J]. 计算机应用, 2020, 40(6): 1668-1673.
[6]	徐周波, 杨健, 刘华东, 黄文文. 基于XGBoost与拓扑结构信息的蛋白质复合物识别算法[J]. 计算机应用, 2020, 40(5): 1510-1514.
[7]	杜旭升, 于炯, 叶乐乐, 陈嘉颖. 基于图上随机游走的离群点检测算法[J]. 计算机应用, 2020, 40(5): 1322-1328.
[8]	陈曦, 梅广, 张金金, 许维胜. 融合知识图谱和协同过滤的学生成绩预测方法[J]. 计算机应用, 2020, 40(2): 595-601.
[9]	马董, 陈红梅, 王丽珍, 肖清. 空间亚频繁co-location模式的主导特征挖掘[J]. 计算机应用, 2020, 40(2): 465-472.
[10]	李莎莎, 梁冬阳, 余杰, 纪斌, 马俊, 谭郁松, 吴庆波. 基于师门关系的研究团队挖掘算法[J]. 计算机应用, 2020, 40(11): 3198-3202.
[11]	孙鹤立, 张优优, 杨洲, 何亮, 贾晓琳. 基于时间线段树的城市可达区域搜索[J]. 计算机应用, 2020, 40(10): 2936-2941.
[12]	邵豪, 王伦文, 邓健. 基于H运算的动态网络重要节点识别方法[J]. 计算机应用, 2019, 39(9): 2669-2674.
[13]	李博, 张晓, 颜靖艺, 李可威, 李恒, 凌玉龙, 张勇. 基于值差度量和聚类优化的K最近邻算法在银行客户行为预测中的应用[J]. 计算机应用, 2019, 39(9): 2784-2788.
[14]	刘晶, 吴英飞, 袁贞明, 孙晓燕. 基于多因素线索长短期记忆模型的血压分析预测[J]. 计算机应用, 2019, 39(5): 1551-1556.
[15]	纪丽娜, 陈凯, 于彦伟, 宋鹏, 王淑莹, 王成锐. 基于城市交通大数据的车辆类别挖掘及应用分析[J]. 计算机应用, 2019, 39(5): 1343-1350.