Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA.
Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, USA.
Sci Transl Med. 2023 Feb 15;15(683):eadc9854. doi: 10.1126/scitranslmed.adc9854.
Although prematurity is the single largest cause of death in children under 5 years of age, the current definition of prematurity, based on gestational age, lacks the precision needed for guiding care decisions. Here, we propose a longitudinal risk assessment for adverse neonatal outcomes in newborns based on a deep learning model that uses electronic health records (EHRs) to predict a wide range of outcomes over a period starting shortly before conception and ending months after birth. By linking the EHRs of the Lucile Packard Children's Hospital and the Stanford Healthcare Adult Hospital, we developed a cohort of 22,104 mother-newborn dyads delivered between 2014 and 2018. Maternal and newborn EHRs were extracted and used to train a multi-input multitask deep learning model, featuring a long short-term memory neural network, to predict 24 different neonatal outcomes. An additional cohort of 10,250 mother-newborn dyads delivered at the same Stanford Hospitals from 2019 to September 2020 was used to validate the model. Areas under the receiver operating characteristic curve at delivery exceeded 0.9 for 10 of the 24 neonatal outcomes considered and were between 0.8 and 0.9 for 7 additional outcomes. Moreover, comprehensive association analysis identified multiple known associations between various maternal and neonatal features and specific neonatal outcomes. This study used linked EHRs from more than 30,000 mother-newborn dyads and would serve as a resource for the investigation and prediction of neonatal outcomes. An interactive website is available for independent investigators to leverage this unique dataset: https://maternal-child-health-associations.shinyapps.io/shiny_app/.
尽管早产是 5 岁以下儿童死亡的主要原因，但目前基于胎龄的早产定义缺乏指导护理决策所需的精确性。在这里，我们提出了一种基于深度学习模型的新生儿不良新生儿结局的纵向风险评估方法，该模型使用电子健康记录 (EHR) 来预测从受孕前不久开始到出生后数月结束的广泛结局。通过链接 Lucile Packard 儿童医院和斯坦福医疗保健成人医院的 EHR，我们开发了一个由 22,104 对在 2014 年至 2018 年期间分娩的母婴对组成的队列。提取了母婴的 EHR，并用于训练一个多输入多任务深度学习模型，该模型采用长短期记忆神经网络，预测 24 种不同的新生儿结局。另外一个由 2019 年至 2020 年 9 月在同一斯坦福医院分娩的 10,250 对母婴对组成的队列用于验证该模型。在分娩时，24 种新生儿结局中有 10 种的受试者工作特征曲线下面积超过 0.9，7 种额外的新生儿结局的面积在 0.8 和 0.9 之间。此外，综合关联分析确定了各种母婴特征与特定新生儿结局之间的多个已知关联。这项研究使用了超过 30000 对母婴对的 EHR，并将成为调查和预测新生儿结局的资源。一个交互式网站可供独立研究人员利用这个独特的数据集：https://maternal-child-health-associations.shinyapps.io/shiny_app/。
