|本期目录/Table of Contents|

[1]黄江,陈剑锋△.基于BP神经网络建立的川崎病早期诊断模型[J].生物医学工程研究,2011,04:207-210.
　HUANG Jiang,CHEN Jianfeng.BP Neural Network Model for Early Diagnosis of Kawasaki Disease[J].Journal of Biomedical Engineering Research,2011,04:207-210.
点击复制

基于BP神经网络建立的川崎病早期诊断模型(PDF)

《生物医学工程研究》[ISSN:1006-6977/CN:61-1281/TN]

期数:
2011年04期
页码:
207-210
栏目:
论著
出版日期:
2011-12-30

文章信息/Info

Title:
BP Neural Network Model for Early Diagnosis of Kawasaki Disease
作者:
黄江1;  陈剑锋2△
1.广西大学机械工程学院，南宁 530004；2.南方医科大学珠江医院儿科中心，广州 510282
Author(s):
HUANG Jiang1; CHEN Jianfeng2
1.College of Mechanical Engineering,Guangxi University,Nanning 530004,China;2.Department of Pediatrics,Zhujiang Hospital,Southern Medical University,Guangzhou 510282,China
关键词:
BP神经网络; 川崎病; 诊断
Keywords:
BP neural network; Kawasaki disease; Diagnosis
分类号:
R318；TP391.5
DOI:
-
文献标识码:
A
摘要:
为早期诊断川崎病，应用BP神经网络原理建立川崎病的诊断模型。以156例川崎病与非川崎病患者的体温、皮疹、口腔黏膜改变、实验室检查结果等9项指标等作为BP神经网络的输入参数，在MATLAB7程序中对其中随机抽取的90例学习样本进行训练并建模。以剩余的66例作为测试样本进行预测，结果表明该模型对川崎病和非川崎病的预测准确率分别为97.4%、92.9%，提示此模型可有效地判别出川崎病与非川崎病，可用于川崎病的早期辅助诊断。
Abstract:
In order to diagnose Kawasaki Disease during early phase, clinical symptoms (temperature, rash, conjunctival injection, erythema of thelips, and oral mucosal changes) and laboratory data (white blood cell, neutrophil, platelet, c-reactive protein, and erythrocyte sedimentation rate) of 156 children with Kawasaki disease or infectious diseases were used to develop a BP neural network model. 90 random cases were trained using MATLAB software for setting up the BP neural network model. The other 66 cases were analyzed to predict diagnosis of Kawasaki disease using this model. Results showed that the predict accuracy in patients with Kawasaki disease and children with infectious diseases were 97.4% and 92.9%, respectively. Our result indicates that the BP neural network model is likely to provide an accurate test for early diagnosis of Kawasaki disease.

参考文献/References

［1］Yeung RSM.Kawasaki disease:update on pathogenesis［J］.Current Opinion in Rheumatology,2010,22(2):551-560.
［2］高隽.人工神经网络原理及仿真实例［M］.北京:机械工业出版社,2003:1-20.
［3］McCandless TC,Haupt SE,Young GS.The effects of imputing missing data on ensemble temperature forecasts［J］. Journal of Computers, 2011, 6(2):162-171.
［4］邹凌云,王正志.基于主成分分析-神经网络的非编码RNA预测［J］.生物医学工程研究, 2007,26(2):6-9.
［5］于擎,杨基海,陈香,张旭.基于BP神经网络的手势动作表面肌电信号的模式识别［J］. 生物医学工程研究,2009,28(1):6-10.
［6］Gunturkun R.Estimation of medicine amount used anesthesia by an artificial neural network［J］.Journal of Medical Systems,2010,34(5):941-946.
［7］Freeman AF,Shulman ST.Kawasaki disease:summary of the American Heart Association guidelines［J］.American Family Physician,2006,74(7):1141-1148.
［8］飞思科技产品研发中心.神经网络理论与MATLAB7实现［M］.北京:电子工业出版社,2005:30-100.
［9］颜虹,徐勇勇,赵耐青.医学统计学［M］.第2版.北京:人民卫生出版社,2010：366-367.

备注/Memo

备注/Memo:
收稿日期：2011-11-10 广东省自然科学基金资助项目(S2011040003573) △通信作者Email:adjfchen@yahoo.com.cn
更新日期/Last Update: 2011-12-30