A data-driven health index for neonatal morbidities.
A data-driven health index for neonatal morbidities.
复制标题
DOI：
10.1016/j.isci.2022.104143
复制
发表时间：
2022-04-15
期刊：
影响因子：
5.8
通讯作者：
Aghaeepour N
中科院分区：
文献类型：
--
作者：
De Francesco D;Blumenfeld YJ;Marić I;Mayo JA;Chang AL;Fallahzadeh R;Phongpreecha T;Butwick AJ;Xenochristou M;Phibbs CS;Bidoki NH;Becker M;Culos A;Espinosa C;Liu Q;Sylvester KG;Gaudilliere B;Angst MS;Stevenson DK;Shaw GM;Aghaeepour N
尽管早产是新生儿死亡、发病和终身损害的主要原因，但早产的程度通常由分娩时的胎龄（GA）而不是新生儿发病率来定义。在这里，我们提出了一个多任务深度神经网络模型，可以同时预测12种新生儿发病率，作为定义早产的新数据驱动方法的基础。从1991年至2012年加州11，594，786例活产的关联出生证明和孕产妇/婴儿住院记录中获得了孕产妇人口统计学资料、病史、产科并发症和产前胎儿检查结果。总的来说，我们的模型在评估基于GA和/或出生体重的早产方面优于传统模型（我们的模型的精确度-召回率曲线下面积为0.326，GA为0.229，GA为0.156）。这些发现强调了使用机器学习技术预测多种早产表型的潜力，并为预防，诊断和治疗新生儿发病率的临床决策提供信息。基于胎龄的早产传统定义需要更新对母体临床数据的深度学习改善了对新生儿发病率的预测数据驱动模型利用出生体重、分娩类型和母体种族准确的风险预测可以为临床决策提供信息生物科学;细胞生物学;分子生物学
Whereas prematurity is a major cause of neonatal mortality, morbidity, and lifelong impairment, the degree of prematurity is usually defined by the gestational age (GA) at delivery rather than by neonatal morbidity. Here we propose a multi-task deep neural network model that simultaneously predicts twelve neonatal morbidities, as the basis for a new data-driven approach to define prematurity. Maternal demographics, medical history, obstetrical complications, and prenatal fetal findings were obtained from linked birth certificates and maternal/infant hospitalization records for 11,594,786 livebirths in California from 1991 to 2012. Overall, our model outperformed traditional models to assess prematurity which are based on GA and/or birthweight (area under the precision-recall curve was 0.326 for our model, 0.229 for GA, and 0.156 for small for GA). These findings highlight the potential of using machine learning techniques to predict multiple prematurity phenotypes and inform clinical decisions to prevent, diagnose and treat neonatal morbidities. Traditional definitions of prematurity based on gestational age need to be updated Deep learning of maternal clinical data improves predictions of neonatal morbidity Data-driven model leverages birthweight, type of delivery and maternal race Accurate risk prediction can inform clinical decisions Biological sciences; Cell biology; Molecular biology
登录
查看更多内容
影响因子：
2.8
作者：
Lynch, Courtney D.;Zhang, Jun
通讯作者：
Zhang, Jun
影响因子：
3
作者：
Wen, Shi Wu;Smith, Graeme;Walker, Mark
通讯作者：
Walker, Mark
影响因子：
6.1
作者：
Romano, M.;Bifulco, P.;Cesarelli, M.
通讯作者：
Cesarelli, M.
影响因子：
5.8
作者：
Rahman, Raziur;Otridge, John;Pal, Ranadip
通讯作者：
Pal, Ranadip
影响因子：
158.5
作者：
Tyson, Jon E.;Parikh, Nehal A.;Higgins, Rosemary D.
通讯作者：
Higgins, Rosemary D.