我们的网站为什么显示成这样？

可能因为您的浏览器不支持样式，您可以更新您的浏览器到最新版本，以获取对此功能的支持，访问下面的网站，获取关于浏览器的信息：

|本期目录/Table of Contents|

应用BP神经网络模型分析冠心病相关因素及其临床意义(PDF)

《心脏杂志》[ISSN:1009-7236/CN:61-1268/R]

期数:
2011年第4期
页码:
530
栏目:
临床研究
出版日期:
2011-08-25

文章信息/Info

Title:
Prediction of coronary artery disease and evaluation of relative risk factors using artificial neural networks
作者:
李万莎1; 唐小芳2; 何健1; 胡志睿3; 龚海鹏3
中国医学科学院、北京协和医学院：1.检验医学研发中心，北京 102206，2.阜外心血管病医院冠心病诊治中心，北京 100037； 3.清华大学生命科学学院计算生物学实验室，北京 100084
Author(s):
LI Wan-sha1;  TANG Xiao-fang2;  HE Jian1;  HU Zhi-rui3;  GONG Hai-peng3
1.Center for Clinical Laboratory Development, Chinese Academy of Medical Sciences & Peking Union College, Beijing 102206, China; 2.Department of Cardiology, Cardiovascular Institute & Fuwai Hospital, Chinese Academy of Medical Sciences & Peking Union Coll
关键词:
冠状动脉疾病; 神经网络; 预测模型; 危险因素
Keywords:
coronary artery disease;  artificial neural network;  prediction;  risk factor
分类号:
R541.4
DOI:
61-1268/R.20110503.1700.029
文献标识码:
A
摘要:
目的:应用BP神经网络模型对冠心病相关因素影响值大小进行评估。方法： 分别对265例冠心病患者和102例非冠心病患者（对照组），进行8项血液指标、3项生理检查和8项个人史的检测、调查及统计分析。对各个指标进行单因素分析，对有统计学意义的指标作为神经网络参数进行分析。对神经网络采用不同的传递函数、训练函数和隐含层节点数建立405种组合，对每种组合分别进行训练和测试，筛选出最佳组合，建立模型。并通过神经网络的平均影响值（MIV）评价各个自变量对于冠心病影响的重要性大小。结果： 对有统计意义的18项指标进行BP神经网络模型分析，筛选出均方误差最小的最佳组合，其测试准确率、灵敏度、特异性均达到100%。应用人工神经网络对18项变量进行影响值大小的判断，结果表明总胆固醇、低密度脂蛋白胆固醇、高密度脂蛋白胆固醇和收缩压4个变量对冠心病的影响最大。结论： BP神经网络可准确评估冠心病危险因素的影响值，对于冠心病的诊断和和早期筛查冠心病高危人群有一定意义。
Abstract:
AIM:To establish the hazard model of coronary artery disease (CAD) using artificial neural networks (ANN) and to evaluate the relative risk factors. METHODS: A retrospective case-control study was conducted in 265 patients diagnosed with CAD by coronary angiography (at least one coronary artery stenosis >50% in major epicardial arteries) and 102 subjects with normal coronary arteries were used as control. ANN models trained with different algorithms were performed in 367 records, divided into training (n=300) and testing (n=67) data sets randomly. The performance of prediction was evaluated by accuracy, sensitivity and specificity values based on standard definitions. RESULTS: The results demonstrated the ANN models trained with the 12 smallest mean-square-error algorithms were promising. Accuracy, sensitivity and specificity values varied, respectively, between 98.51 and 100%, 98.04 and 100% and 87.5 and 100% for testing. The best ANN model showed the value of 100% for accuracy, sensitivity and specificity. Using mean impact value of the ANN, total cholesterol, LDL cholesterol, HDL cholesterol and systolic blood pressure were found to be the most important risk factors for CAD. CONCLUSION: The proposed ANN models trained with the algorithms can be used as a promising approach for predicting CAD without the need for invasive diagnostic methods and for making prognostic clinical decisions.

参考文献/References

[1]Khot UN,Khot MB,Bajzer CT,et al.Prevalence of conventional risk factors in patients with coronary heart disease[J].JAMA,2003,290(7):898-904.
[2]华贻军.人工神经网络在临床医学中的应用[J].实用医学杂志,2005,21(3):330-332.
[3]Colak MC,Colak C,Kocatürk H,et al.Predicting coronary artery disease using different artificial neural network maodels[J].Anadolu kardiyol Derg, 2008,8(4):249-254.
[4]Wilson PW,D'Agostino RB,Levy D,et al.Prediction of coronary heart disease using risk factor categories[J].Circulation,1998, 97(18):1837-1847.
[5]Beale MH, Hagan MT,Demuth HB.Neural Network Tool boxTM7 user’s guide[M].the Math works Inc.U.S,2010:32-328.
[6]魏玲,杨丽霞,王先梅,等.冠心病患者外周血红蛋白含量变化的临床意义[J].中国微循环, 2004,8(1):30-34.
[7]Lisboa PJ,Taktak AF.The use of artificial neural networks in decision support in cancer:a systematic review[J].Neural Netw, 2006,19(4):408-415.
[8]Green M,Bjrk J,Forberg J,et al.Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room[J].Artif Intell Med,2006,38(3):305-318.
[9]蒲春,孙政顺,赵世敏.Matlab神经网络工具箱BP算法比较[J].计算机仿真，2006,23(5):142-144.
[10]Anselmino M,Malmberg K,Rydén L,et al.A gluco-metabolic risk with cardiovascular risk stratification potential in patients with coronary artery disease[J].Diab Vasc Dis Res,2009,6(2):62-72.

备注/Memo

备注/Memo:
收稿日期：2010-09-26.通讯作者：何健，教授,主要从事临床检验疾病诊断研究Email：jjianho@gmail.com 作者简介：李万莎，技师，硕士生Email：lwstfb@126.com
更新日期/Last Update: 2011-06-02