文献速递产科母胎医学

利用机器学习识别死胎风险

Identifying risk of stillbirth using machine learning.
PubMed 文献 · Am J Obstet Gynecol · 2023-06-12

本研究对死胎协作研究网络(2006—2009年,美国5个地区59家医院)的数据进行二次分析,纳入3000例活产和982例死胎,构建并优化机器学习模型以预测死胎。在可存活前(22—24周)数据中,随机森林模型准确率(曲线下面积)为85.1%,灵敏度88.6%、特异度85.3%、阳性预测值85.3%、阴性预测值84.8%。作者认为,这些模型经具有代表性的数据库验证并前瞻性验证后,可能有助于风险分层与临床决策支持。

要点

  • 可存活前数据的随机森林模型准确率(曲线下面积)为85.1%,灵敏度88.6%、特异度85.3%。
  • 贯穿妊娠期数据的随机森林模型准确率85.0%,灵敏度92.2%、特异度77.9%。
  • 可存活前模型的重要变量包括既往死胎、少数族裔、最早产前检查与超声时的孕龄及孕中期血清筛查。

核心结论

  • 将先进机器学习技术应用于包含独特且具临床相关性变量的死胎与活产综合数据库,所得算法可在达到可存活前准确识别85%的将发生死胎的妊娠。
  • 作者认为,这些模型在能代表美国分娩人群的数据库验证并随后前瞻性验证后,可能提供有效的风险分层和临床决策支持,以更好地识别和监测死胎风险人群。

研究设计与样本

  • 这是对死胎协作研究网络的二次分析,数据来自2006—2009年美国5个不同地区59家医院分娩的死胎和活产妊娠。
  • 主要目标是利用可存活前(22—24周)可获得的数据建立死胎预测模型;次要目标包括利用贯穿妊娠期可获得的变量优化模型并确定变量重要性。
  • 共纳入3000例活产和982例死胎,确定101个感兴趣变量。

主要发现

  • 在纳入可存活前可用数据的模型中,随机森林模型准确率(曲线下面积)为85.1%,灵敏度88.6%、特异度85.3%、阳性预测值85.3%、阴性预测值84.8%。
  • 使用贯穿妊娠期收集数据的随机森林模型准确率为85.0%,灵敏度92.2%、特异度77.9%、阳性预测值84.7%、阴性预测值88.3%。
  • 可存活前模型中的重要变量包括既往死胎、少数族裔、最早产前检查时的孕龄、最早超声时的孕龄以及孕中期血清筛查。

临床怎么用

  • 作者认为,这些模型在能代表美国分娩人群的数据库验证并随后前瞻性验证后,可能提供有效的风险分层和临床决策支持,以更好地识别和监测死胎风险人群。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: 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. OBJECTIVE: 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. STUDY DESIGN: 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. RESULTS: 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. CONCLUSION: 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.

来源:Am J Obstet Gynecol,查看原文。版权归原作者所有。

引用

  1. Cersonsky TEK, Ayala NK, Pinar H, et al. Identifying risk of stillbirth using machine learning. Am J Obstet Gynecol. 2023. PMID: 37315754. doi:10.1016/j.ajog.2023.06.017

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。