基于BP神经网络的围产儿出生缺陷患病率预测

王玮; 许伟; 郑亚军; 周宝森

Abstract

王玮,许伟,郑亚军,周宝森.基于BP神经网络的围产儿出生缺陷患病率预测[J].Chinese journal of Epidemiology,2007,28(5):507-509

基于BP神经网络的围产儿出生缺陷患病率预测

Study on a back propogation neural network-based predictive model for prevalence of birth defect

Received:December 21, 2006

DOI：

KeyWord: 出生缺陷疾病预测 BP神经网络模型患病率

English Key Word: Birth defect Disease prediction Back propogation network Prevalence rate

FundProject:

Author Name	Affiliation
WANG Wei	Department of Epidemiology, China Medical University, Shenyang 110001, China
XU Wei	沈阳市卫生局基层卫生与妇幼保健处
ZHENG Ya-jun	沈阳市卫生局基层卫生与妇幼保健处
ZHOU Bao-sen	Department of Epidemiology, China Medical University, Shenyang 110001, China

Hits: 3227

Download times: 1474

Abstract:

目的评价BP神经网络模型在围产儿出生缺陷预测中的应用价值。方法选择沈阳市1995-2005年围产儿出生缺陷患病率数据，利用MATLAB 6。5软件的神经网络工具箱构建BP神经网络模型，训练与模拟网络，预测2006-2007年沈阳市围产儿出生缺陷的流行趋势，并与传统的预测方法进行比较。结果以1995-2003年资料建立模型预测2004-2005年流行水平和趋势，结果患病率回代平均误差率和RNL分别为1。34%和0。9874，外推预测平均误差率为1。78%;以1995-2005年资料建立模型预测2006-2007年流行趋势，结果患病率回代平均误差率和RNL分别为0。33%和0。9954，2006-2007年出生缺陷患病率预测值分别为11。00‰和11。29‰。结论利用BP神经网络进行疾病预测，不仅能获得更好的预测效果，而且对资料的类型、分布不作任何限制，是一种很好的流行病学预测方法。

English Abstract:

Objective To evaluate the value of a back propogation(BP) network on prediction of birth defect and to give clues on its prevention. Methods Data of birth defect in Shenyang from 1995 to 2005 were used as a training set to predict the prevalence rate of birth defect. Neural network tools box of Software MATLAB 6. 5 was used to train and simulate BP Artificial Neural Network. Results When using data of the year 1995一2003 to predict the prevalence rate of birth defect in 2004一2005，the Results showed that: the fitting average error of prevalence rate was 1.34%，RNL was 0. 9874，and the prediction of average error was 1. 78%Using data of the year 1995一2005 to predict the prevalence rate of birth defect in 2006一2007，the Results showed that: the fitting average error was 0. 33 0.6, RNL was 0. 9954, the prevalence rates of birth defect in 2006一2007 were 11.00 %o and 11.29'/.. Conclusion Compared to the conventional statistics method，BP not only showed better prediction precision, but had no limit to the type or distribution of relevant data, thus providing a powerful method in epidemiological prediction.

View Fulltext Html FullText View/Add Comment Download reader