|
|
|
| Prediction model of fetal meconium-stained amniotic fluid in re-pregnant women with intrahepatic cholestasis of pregnancy |
| HE Ling-fei, ZHAO Yun, WANG Zheng-ping |
| Department of Obstetrics, Women's Hospital, Zhejiang University School of Medicine, Hangzhou 310006, China |
|
|
|
Abstract Objective: To establish a prediction model of fetal meconium-stained amniotic fluid in re-pregnant women with intrahepatic cholestasis of pregnancy(ICP). Methods: Clinical data of 180 re-pregnant women with ICP delivering in Women's Hospital, Zhejiang University School of Medicine between January 2009 to August 2014 were collected. An artificial neural network model(ANN) for risk evaluation of fetal meconium-stained fluid was established and assessed. Results: The sensitivity, specificity and accuracy of ANN for predicting fetal meconium-stained fluid were 68.0%, 85.0% and 80.3%, respectively. The risk factors with effect weight >10% were pregnancy complications, serum cholyglycine level,maternal age. Conclusion: The established ANN model can be used for predicting fetal meconium-stained amniotic fluid in re-pregnant women with ICP.
|
|
Received: 17 February 2015
Published: 25 May 2015
|
|
|
应用人工神经网络预测再次妊娠肝内胆汁淤积症孕妇发生羊水浑浊的风险
目的:构建再次妊娠妊娠期肝内胆汁淤积症(ICP)孕妇羊水混浊的预测模型,探讨相关指标的预测价值。方法:收集2009年1月至2014年8月在浙江大学医学院附属妇产科医院再次妊娠住院分娩的ICP孕妇的临床资料及胎儿风险相关资料,应用人工神经网络构建羊水混浊预测模型,分析相关指标对羊水混浊的预测结果和影响权重。结果:应用人工神经网络模型预测ICP孕妇羊水混浊灵敏度为68.0%,特异性为85.0%,准确率为80.3%。参数权重在10%以上的因素有妊娠合并症、孕妇分娩前血清甘胆酸浓度和孕妇年龄。结论:人工神经网络可用于构建ICP孕妇胎儿宫内环境即羊水混浊的预测模型;影响再次妊娠ICP孕妇胎儿宫内安全的危险因素有孕妇年龄、妊娠合并症、孕妇分娩前血清甘胆酸浓度等。
关键词：
神经网络(计算机),
妊娠,
胎儿监测,
胆汁淤积,
肝内,
羊水,
预测
|
|
| [1] DIKEN Z, USTA I M, NASSAR A H. A clinical approach to intrahepatic cholestasis of pregnancy[J]. Am J Perinatol, 2014,31(1):1-8.
[2] GEENES V, WILLIAMSON C. Intrahepatic cholestasis of pregnancy[J]. World J Gastroenterol, 2009,15(17):2049-2066.
[3] BACQ Y, SENTIHES L. Intrahepatic cholestasis of pregnancy: diagnosis and management[J]. Clinical Liver Disease, 2014,4(3):58-61.
[4] 中华医学会妇产科学分会产科学组.妊娠期肝内胆汁淤积症诊疗指南[J].中华妇产科杂志, 2011,46(5):391-394. The Subspecialty Group of Obstetrics, Society of Gynecology and Obstetrics, Chinese Medical Association.The guidelines of intrahepatic cholestasis of pregancy[J]. Chinese Journal of Obstetrics and Gynecology, 2011,46(5):391-394.(in Chinese)
[5] BASHEER I A, HAJMEER M. Artificial neural networks: fundamentals, computing, design, and application[J]. J Microbiol Methods, 2000,43(1):3-31.
[6] HAN H G, WANG L D, QIAO J F. Efficient self-organizing multilayer neural network for nonlinear system modeling[J]. Neural Netw, 2013,43:22-32.
[7] MATSUDA Y, KAWAMICHI Y, HAYASHI K, et al. Impact of maternal age on the incidence of obstetrical complications in Japan[J]. J Obstet Gynaecol Res, 2011,37(10):1409-1414.
[8] CAROLAN M, DAVEY M A, BIRO M A, et al. Maternal age, ethnicity and gestational diabetes mellitus[J]. Midwifery, 2012,28(6):778-783.
[9] JAIN R, SURI V, CHOPRA S, et al. Obstetric cholestasis: outcome with active management[J]. J Obstet Gynaecol Res, 2013,39(5):953-959.
[10] WIKSTROM SHEMER E, MARSCHALL H U, LUDVIGSSON J F, et al. Intrahepatic cholestasis of pregnancy and associated adverse pregnancy and fetal outcomes: a 12-year population-based cohort study[J]. BJOG, 2013,120(6):717-723.
[11] SIRISTATIDIS C S, CHRELIAS C, POULIAKIS A, et al. Artificial neural networks in gynaecological diseases: current and potential future applications[J]. Med Sci Monit, 2010,16(10):RA231-236.
[12] CLEOPHAS T J, CLEOPHAS T F. Artificial intelligence for diagnostic purposes: principles, procedures and limitations[J]. Clin Chem Lab Med, 2010,48(2):159-165.
[13] LU J, QI H. Sudden fetal death in a patient with intrahepatic cholestasis of pregnancy complicated with gestational diabetes mellitus[J]. Arch Gynecol Obstet, 2013,287(1):179-182.
[14] MARTINEAU M, RAKER C, POWRIE R, et al. Intrahepatic cholestasis of pregnancy is associated with an increased risk of gestational diabetes[J]. Eur J Obstet Gynecol Reprod Biol, 2014,176: 80-85. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
