应用人工神经网络预测胎儿体重的研究

目的:探讨人工神经网络预测新生儿出生体重的价值。方法:将226例足月、单胎、无妊娠合并症及并发症的初产妇分为训练组(100例,男女胎儿各50例)和验证组(126例,男女胎儿各63例),训练组分别选取不同参数构建3个神经网络,(1)联合参数法:用孕妇身高、体重、腹围、宫高及B超下胎儿双顶径、股骨长和羊水池最大深度作为输入节点;(2)孕妇参数法,用孕妇身高、体重、腹围和宫高作为输入节点;(3)胎儿参数法,用B超下胎儿双顶径、股骨长和羊水池最大深度作为输入节点。神经网络构建完成后以126例验证组来分别测试3种网络的准确性和误差。结果:联合参数法准确率最高为84.94%,母亲参数法为83.45%,胎儿参数法为80.80%。结论:人工神经网络预测胎儿体重有很好的应用前景。选取合适的孕妇及胎儿参数建立网络可提高预测的准确性。

A study on estimating fetal weight using artificial neural networks

Objective：To investigate the effect of artificial neural networks in predicting fetal weight. Methods：The 226 cases of full-term singleton pregnancy without comphcation were divided into two groups ,100 samples （female and male fetuses each 50） for training and 126 samples （ female and male fetuses each 63） for testing. Three methods of neural networks are composed： （ 1 ） joint parameter method using the height,weight,abdominal circumference and uterine fundal height of pregnant women as well as the biparietal diameter（BPD） ,femur length（FL） and amniotic fluid pool depth （ AFD ） of fetuses under B-ultrasonography; （ 2 ） maternal pararneter method using the height,weight,abdominal circumference and uterine fundal height of pregnant women; （3）fetal parameter method using the BPD, FL and AFD of fetuses;the neural networks were then trained and tested upon the above samples. Results：Among the three methods, the joint parameter method had the highest predicting accuracy of 84.94% ,the accuracy of maternal parameter method and the fetal parameter method were 83.45% and 80. 80% respectively. Conclusion：The fetal weight estimation using artificial neural networks shows a potential prospect of application. A subtle combination of maternal and fetal parameters is critical to build up an effective network.