Comparison of logistic regression with machine learning methods for the prediction of fetal growth abnormalities: a retrospective cohort study.
Comparison of logistic regression with machine learning methods for the prediction of fetal growth abnormalities: a retrospective cohort study.
复制标题
DOI：
10.1186/s12884-018-1971-2
复制
发表时间：
2018-08-15
影响因子：
3.1
通讯作者：
Allen VM
中科院分区：
文献类型：
--
作者：
Kuhle S;Maguire B;Zhang H;Hamilton D;Allen AC;Joseph KS;Allen VM
虽然人们对确定妊娠不良结局的风险越来越感兴趣，但现有的预测模型没有充分评估基于人群的风险，而是基于传统的回归方法。目前研究的目的是使用Logistic回归和机器学习方法确定胎儿生长异常的预测因素，并比较以人群为基础的婴儿样本的诊断特性。居住在加拿大新斯科舍省的母亲在2009年至2014年期间出生的30,705名单身婴儿的数据来自新斯科舍省阿特利围产期数据库。主要结果是胎龄较小(SGA)和较大(LGA)。怀孕前和怀孕26周时的母亲特征作为预测因素进行了研究。使用Logistic回归和选择机器学习方法建立模型，按胎次分层。用曲线下面积比较模型，定性比较各预测因子的相对重要性。小于胎龄儿占7.9%，胎龄儿占13.5%，初产妇占48.6%，经产妇占51.4%。SGA和LGA的预测较差到一般(曲线下面积为60-75%)，并随着胎次和妊娠信息的增加而改善。吸烟、既往低出生体重儿和孕期体重增加是SGA的重要预测因素；孕前体重指数、孕期体重增加和既往巨大儿是LGA的最强预测因素。这项研究中使用的机器学习方法在预测胎儿生长异常方面并没有提供任何优于Logistic回归的优势。基于母体信息的SGA和LGA的预测精度对于初产妇女来说较差，对于经产妇女来说是中等的。本文的在线版本(10.1186/s12884-0181971-2)包含补充材料，可供授权用户使用。
While there is increasing interest in identifying pregnancies at risk for adverse outcome, existing prediction models have not adequately assessed population-based risks, and have been based on conventional regression methods. The objective of the current study was to identify predictors of fetal growth abnormalities using logistic regression and machine learning methods, and compare diagnostic properties in a population-based sample of infants. Data for 30,705 singleton infants born between 2009 and 2014 to mothers resident in Nova Scotia, Canada was obtained from the Nova Scotia Atlee Perinatal Database. Primary outcomes were small (SGA) and large for gestational age (LGA). Maternal characteristics pre-pregnancy and at 26 weeks were studied as predictors. Logistic regression and select machine learning methods were used to build the models, stratified by parity. Area under the curve was used to compare the models; relative importance of predictors was compared qualitatively. 7.9% and 13.5% of infants were SGA and LGA, respectively; 48.6% of births were to primiparous women and 51.4% were to multiparous women. Prediction of SGA and LGA was poor to fair (area under the curve 60–75%) and improved with increasing parity and pregnancy information. Smoking, previous low birthweight infant, and gestational weight gain were important predictors for SGA; pre-pregnancy body mass index, gestational weight gain, and previous macrosomic infant were the strongest predictors for LGA. The machine learning methods used in this study did not offer any advantage over logistic regression in the prediction of fetal growth abnormalities. Prediction accuracy for SGA and LGA based on maternal information is poor for primiparous women and fair for multiparous women. The online version of this article (10.1186/s12884-018-1971-2) contains supplementary material, which is available to authorized users.
登录
查看更多内容
DOI：
10.1016/s0140-6736(15)00131-2
发表时间：
2015-11-21
期刊：
Lancet (London, England)
影响因子：
--
作者：
Sovio U;White IR;Dacey A;Pasupathy D;Smith GCS
通讯作者：
Smith GCS
影响因子：
2.3
作者：
Dietz, Patricia M.;Rizzo, Joanne H.;Hornbrook, Mark C.
通讯作者：
Hornbrook, Mark C.
影响因子：
158.5
作者：
MCCORMICK, MC
通讯作者：
MCCORMICK, MC
影响因子：
7.1
作者：
Hammami, A.;Zumaeta, A. Mazer;Nicolaides, K. H.
通讯作者：
Nicolaides, K. H.
影响因子：
2.6
作者：
Das, UG;Sysyn, GD
通讯作者：
Sysyn, GD