[1]王 斌),冯慧芬),黄 平),等.随机森林模型在重症手足口病预测中的应用价值[J].郑州大学学报(医学版),2018,(06):747-751.[doi:10.13705/j.issn.1671-6825.2018.03.135]
 WANG Bin),FENG Huifen),HUANG Ping),et al.Application value of random forest model in prediction of severe hand-foot-mouth disease[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2018,(06):747-751.[doi:10.13705/j.issn.1671-6825.2018.03.135]
点击复制

随机森林模型在重症手足口病预测中的应用价值()
分享到:

《郑州大学学报(医学版)》[ISSN:1671-6825/CN:41-1340/R]

卷:
期数:
2018年06期
页码:
747-751
栏目:
应用研究
出版日期:
2018-11-20

文章信息/Info

Title:
Application value of random forest model in prediction of severe hand-foot-mouth disease
作者:
王 斌1)冯慧芬2)黄 平1)赵 敬1)易佳音1)
1)郑州大学第五附属医院消化内科 郑州450052;2)郑州大学第五附属医院感染科 郑州450052
Author(s):
WANG Bin1) FENG Huifen2) HUANG Ping1) ZHAO Jing1) YI Jiayin1)
1)Department of Gastroenterology, the Fifth Affiliated Hospital, Zhengzhou University, Zhengzhou 450052; 2)Department of Infectious Disease, the Fifth Affiliated Hospital, Zhengzhou University, Zhengzhou 450052
关键词:
手足口病 随机森林模型 预测
Keywords:
hand-foot-mouth disease random forest model prediction
分类号:
R183
DOI:
10.13705/j.issn.1671-6825.2018.03.135
摘要:
目的:探究随机森林模型在重症手足口病预测中的应用价值。方法:收集郑州大学附属儿童医院感染科2016年8月至2017年11月诊治的手足口病患儿病例资料。选用R 3.4.4软件进行数据处理,构建随机森林模型和logistic模型,以logistic模型作为参照,对随机森林模型预测重症手足口病的性能进行评价。结果:通过随机森林模型的构建,最终筛选出的重要预测变量中,前3个依次为白细胞计数、血糖和EV71。随机森林模型对重症手足口病的总体预测正确率为82.5%,AUC为0.87,敏感度为65.9%,特异度为94.5%。结论:随机森林模型在预测重症手足口病方面具有较大价值,其模型预测性能表现较佳。
Abstract:
Aim:To explore the value of random forest model in the prediction of severe hand-foot-mouth disease(HFMD).Methods:The relevant data of children with HFMD admitted from August 2016 to November 2017 in Children's Hospital Affiliated to Zhengzhou University were collected. The R software version 3.4.4 was used to analyze all the data. Random forest model and logistic regression model were built respectively and compared for the performance.Results:Through the construction of random forest model, the first three important predictive variables followed by white blood cell count, blood glucose and EV71. The overall prediction accuracy of the random forest model for severe HFMD was 82.5%, the area under the ROC curve was 0.87, the sensitivity was 65.9%,and the specificity was 94.5%.Conclusion:The random forest model is of great value in predicting severe HFMD with better performance.

参考文献/References:

[1] WU X,HU S,KWAKU AB,et al.Spatio-temporal clustering analysis and its determinants of hand, foot and mouth disease in Hunan, China, 2009-2015[J].BMC Infect Dis,2017,17(1):645
[2] XING W,LIAO Q,VIBOUD C,et al.Hand, foot, and mouth disease in China, 2008-12: an epidemiological study[J].Lancet Infect Dis,2014,14(4):308
[3] SOLOMON T,LEWTHWAITE P,PERERA D,et al.Virology, epidemiology, pathogenesis, and control of enterovirus 71[J].Lancet Infect Dis,2010,10(11):778
[4] 董师师,黄哲学.随机森林理论浅析[J].集成技术,2013,2(1):1
[5] 马景义,谢邦昌.用于分类的随机森林和Bagging分类树比较[J].统计与信息论坛,2010,25(10):18
[6] 中华人民共和国卫生部.手足口病诊疗指南:2010年版 [J].国际呼吸杂志,2010,30(24):1473
[7] 黄文,王正林.数据挖掘:R语言实战[M].北京:电子工业出版社,2014.
[8] 刘丹,苏豪浩,王建红,等.手足口病重症病例的流行特征及危险因素[J].实用医学杂志,2013,29(6):995
[9] 胡跃华,肖革新,郭莹,等.2008-2011年中国大陆手足口病流行特征分析[J].中华疾病控制杂志,2014,18(8):693
[10]陈璐,任静朝,段广才,等.手足口病重症化影响因素分析及预测模型的建立[J].中华实用儿科临床杂志,2017,32(6):469
[11]方匡南,吴见彬,朱建平,等.随机森林方法研究综述[J].统计与信息论坛,2011,26(3):32
[12]LIU G,XU Y,WANG X,et al.Developing a machine learning system for identification of severe hand, foot, and mouth disease from electronic medical record data[J].Sci Rep,2017,7(1):16341
[13]林克武,李昌崇.手足口病合并脑炎相关风险因素分析[J].实用医学杂志,2015,31(15):2532
[14]CHEW SP,CHONG SL,BARBIER S,et al.Risk factors for severe hand foot mouth disease in Singapore: a case control study[J].BMC Infect Dis,2015,15:486
[15]冯慧芬,赵秋民,段广才,等.重症手足口病心肺衰竭危险因素筛选及其预测模型的建立[J].郑州大学学报(医学版),2015,50(4):469
[16]郑亚明,常昭瑞,姜黎黎,等.手足口病重症病例分析:基于全国手足口病监测试点数据[J].中华流行病学杂志,2017,38(6):759
[17]朱杰辉,段广才,郗园林,等.郑州市2015年轻、重症手足口病患儿的临床体征、实验室指标动态分析[J].郑州大学学报(医学版),2017,52(5):625
[18]ZHENG G,CAO J,YU J,et al.Risk factors for death in children with critical and severe hand-foot-and-mouth disease in Chongqing, China: an observational study[J].Medicine(Baltimore),2017,96(49):e8934

相似文献/References:

[1]茹维平△,王彦霞,康锴,等.危重型手足口病临床症状及预警因素分析[J].郑州大学学报(医学版),2011,(04):608.
 RU Weiping,WANG Yanxia,KANG Kai,et al.Analysis on risk factors for critical hand,foot and mouth disease[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2011,(06):608.
[2]李幸乐,许玉玲,黄学勇,等.河南省2010年肠道病毒EV71型分离株全基因组序列分析*[J].郑州大学学报(医学版),2011,(05):699.
 LI Xingle,XU Yuling,HUANG Xueyong,et al.Complete sequence analysis of Enterovirus 71 strain from a fatal case of handfootmouth disease during an epidemic of Henan province in 2010[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2011,(06):699.
[3]冷弘),卢欣),刘慧涛),等.肠道病毒71型河南分离株2株全基因组序列分析*[J].郑州大学学报(医学版),2012,(02):170.
 LENG Hong),LU Xin),LIU Huitao),et al.Analysis of complete genome sequence of two enterovirus 71 strains isolated from Henan[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2012,(06):170.
[4]冯慧芬),段广才)#,张卫东).郑州市二七区2008~2012年住院手足口病患者病原、临床特征及流行因素调查*[J].郑州大学学报(医学版),2014,(02):184.
 FENG Huifen,DUAN Guangcai,ZHANG Weidong.Study on pathogenic monitoring and clinical characteristics of handfootmouth disease 2008-2012 in Erqi district of Zhengzhou city[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2014,(06):184.
[5]窦萍△,何蔚新,张栓虎.安阳市2009年至2012年手足口病疫情特征[J].郑州大学学报(医学版),2014,(03):440.
[6]宋春兰,郭燕军#,成怡冰,等.合并神经损害的危重型手足口病患儿临床特征及预后分析*[J].郑州大学学报(医学版),2015,(01):128.
 SONG Chunlan,GUO Yanjun,CHENG Yibing,et al.Analysis of clinical features and prognosis of children with severe handfoodmouth disease combined with nerve damage[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2015,(06):128.
[7]冯慧芬)△,赵秋民),段广才),等.应用时间序列分析气象因素对手足口病流行的影响*[J].郑州大学学报(医学版),2015,(02):171.
 FENG Huifen),ZHAO Qiumin),DUAN Guangcai),et al.Effects of meteorological factors on occurrence of HFMD using time series analysis[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2015,(06):171.
[8]冯慧芬△,赵秋民,段广才,等.重症手足口病心肺衰竭危险因素筛选及其预测模型的建立[J].郑州大学学报(医学版),2015,(04):469.
 FENG Huifen,ZHAO Qiumin,DUAN Guangcai,et al.Screening of risk factors of severe handfootmouth disease with cardiopulmonary failure and establishment of forecasting model[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2015,(06):469.
[9]朱杰辉,段广才#,郗园林,等.郑州市2015年轻、重症手足口病患儿的临床体征、实验室指标动态分析*[J].郑州大学学报(医学版),2017,(05):625.[doi:10.13705/j.issn.1671-6825.2017.05.027]
 ZHU Jiehui,DUAN Guangcai,XI Yuanlin,et al.Dynamic analysis of clinical characters and laboratory indicators of mild and severe children with hand,foot and mouth disease of Zhengzhou, 2015[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2017,(06):625.[doi:10.13705/j.issn.1671-6825.2017.05.027]
[10]赵 敬),冯慧芬),王 芳),等.基于2008至2017年郑州市二七区手足口病监测数据的时间序列建模分析[J].郑州大学学报(医学版),2019,(01):97.[doi:10.13705/j.issn.1671-6825.2018.05.039]
 ZHAO Jing),FENG Huifen),WANG Fang),et al.Time series modeling analysis of hand-foot-mouth disease surveillance data in Erqi District of Zhengzhou City from 2008 to 2017[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2019,(06):97.[doi:10.13705/j.issn.1671-6825.2018.05.039]

备注/Memo

备注/Memo:
【基金项目】国家自然科学基金资助项目(81473030); 河南省卫生系统出国研修项目(2015065)
【作者简介】冯慧芬,通信作者,女,1972年11月生,博士,主任医师,研究方向: 传染病流行病学,E-mail:huifen.feng@163.com
更新日期/Last Update: 2018-11-20