背景:使用逻辑回归进行死产的先前预测模型没有利用复杂的机器学习方法中涉及的先进和细微的技术,例如对结果之间的非线性关系进行建模。
目的:使用人口统计,利用存活前(22-24周)和整个妊娠期间的可用数据,创建和完善用于预测死产的机器学习模型,medical,和产前检查数据,包括超声和胎儿遗传学.
方法:这是对死胎合作研究网络的二次分析,其中包括2006-2009年在美国5个不同地区的59家医院分娩的死产和活产婴儿的妊娠数据.主要目的是使用生存能力之前的可用数据创建用于预测死产的模型。次要目标包括完善整个怀孕期间可用变量的模型并确定变量的重要性。
结果:在3000例活产和982例死产中,确定了101个感兴趣的变量。在包含可行之前可用数据的模型中,随机森林模型具有85.1%的准确度(曲线下面积[AUC])和高灵敏度(88.6%),特异性(85.3%),正预测值(85.3%),和负预测值(84.8%)。使用整个怀孕期间收集的数据的随机森林模型的准确率为85.0%;该模型的灵敏度为92.2%,77.9%的特异性,84.7%正预测值,和88.3%负预测值。存活前模型中的重要变量包括先前的死产,少数民族种族,最早产前检查和超声检查时的胎龄,和妊娠中期血清筛查。
结论:将先进的机器学习技术应用于具有独特和临床相关变量的死产和活产的综合数据库,产生了一种算法,该算法可以准确识别85%的导致死产的怀孕。在他们达到生存能力之前。一旦在反映美国分娩人口的代表性数据库中得到验证,然后进行前瞻性验证,这些模型可以提供有效的风险分层和临床决策支持,从而更好地识别和监测有死产风险的人群.
Previous predictive models using logistic regression for stillbirth do not leverage the advanced and nuanced techniques involved in sophisticated machine learning methods, such as modeling nonlinear relationships between outcomes.
This study aimed to create and refine machine learning models for predicting stillbirth using data available before viability (22-24 weeks) and throughout pregnancy, as well as demographic, medical, and prenatal visit data, including ultrasound and fetal genetics.
This is a secondary analysis of the Stillbirth Collaborative Research Network, which included data from pregnancies resulting in stillborn and live-born infants delivered at 59 hospitals in 5 diverse regions across the United States from 2006 to 2009. The primary aim was the creation of a model for predicting stillbirth using data available before viability. Secondary aims included refining models with variables available throughout pregnancy and determining variable importance.
Among 3000 live births and 982 stillbirths, 101 variables of interest were identified. Of the models incorporating data available before viability, the random forests model had 85.1% accuracy (area under the curve) and high sensitivity (88.6%), specificity (85.3%), positive predictive value (85.3%), and negative predictive value (84.8%). A random forests model using data collected throughout pregnancy resulted in accuracy of 85.0%; this model had 92.2% sensitivity, 77.9% specificity, 84.7% positive predictive value, and 88.3% negative predictive value. Important variables in the previability model included previous stillbirth, minority race, gestational age at the earliest prenatal visit and ultrasound, and second-trimester serum screening.
Applying advanced machine learning techniques to a comprehensive database of stillbirths and live births with unique and clinically relevant variables resulted in an algorithm that could accurately identify 85% of pregnancies that would result in stillbirth, before they reached viability. Once validated in representative databases reflective of the US birthing population and then prospectively, these models may provide effective risk stratification and clinical decision-making support to better identify and monitor those at risk of stillbirth.