Afifi Jehier, Ahmad Tahani, Guida Alessandro, Vincer Michael John, Stewart Samuel Alan
Division of Neonatal Perinatal Medicine, Department of Pediatrics, Dalhousie University, Halifax, NS B3K 6R8, Canada.
Department of Diagnostic Imaging, Dalhousie University, Halifax, NS B3K 6R8, Canada.
Children (Basel). 2024 Dec 12;11(12):1512. doi: 10.3390/children11121512.
Is machine learning (ML) superior to the traditionally used logistic regression (LR) in prediction of neurodevelopmental outcomes in preterm infants?
To develop and internally validate a ML model to predict neurodevelopmental impairment (NDI) in very preterm infants (<31 weeks) at 36 months corrected age, using clinical predictors.
A retrospective cohort of very preterm infants (2330 weeks) born between January 2004 and December 2016 in Nova Scotia, Canada. Survivors with neurodevelopmental assessment at 36 months corrected age were included. The study sample was randomly split (80:20) into a development and testing datasets. We compared four methods: LR, elastic net (EN), random forest ensemble (RF) and gradient boosting (XGB), in relation to discrimination (AUC), calibration, and diagnostic properties.
Of 811 eligible infants, 663 were included (mean gestational age 28 weeks, mean birth weight 1137 g and 52% male). Of those, 195 (29%) developed NDI and 468 (71%) did not. On internal validation using the testing dataset, all four models provided good discrimination of NDI with comparable AUC. RF was superior to the other three methods with a higher AUC (0.79 vs. 0.74, 0.74, and 0.73 for XGB, EN and LR, respectively), but all models have overlapped CIs.
In this population-based cohort of very preterm infants, RF was superior to conventional LR in prediction of NDI at 3 years corrected age. Accurate prediction of preterm infants at risk of NDI enables early referrals for intervention programs and resources allocation toward those who are most likely to benefit.
在预测早产儿的神经发育结局方面，机器学习（ML）是否优于传统使用的逻辑回归（LR）？
利用临床预测指标，开发并在内部验证一个用于预测极早产儿（<31周）在矫正年龄36个月时神经发育障碍（NDI）的ML模型。
对2004年1月至2016年12月在加拿大新斯科舍省出生的极早产儿（23 - 30周）进行回顾性队列研究。纳入在矫正年龄36个月时进行神经发育评估的存活者。研究样本随机分为（80:20）开发数据集和测试数据集。我们比较了四种方法：LR、弹性网络（EN）、随机森林集成（RF）和梯度提升（XGB）在区分度（AUC）、校准和诊断特性方面的表现。
在811名符合条件的婴儿中，663名被纳入研究（平均胎龄28周，平均出生体重1137克，52%为男性）。其中，195名（29%）发生了NDI，468名（71%）未发生。在使用测试数据集进行内部验证时，所有四种模型对NDI都有良好的区分度，AUC相当。RF优于其他三种方法，AUC更高（分别为0.79，而XGB、EN和LR的AUC分别为0.74、0.74和0.73），但所有模型的置信区间有重叠。
在这个基于人群的极早产儿队列中，RF在预测矫正年龄3岁时的NDI方面优于传统LR。准确预测有NDI风险的早产儿能够尽早转诊至干预项目，并为最可能受益的人群分配资源。
