Ambalavanan N, Baibergenova A, Carlo W A, Saigal S, Schmidt B, Thorpe K E
Department of Pediatrics, University of Alabama at Birmingham, Birmingham, AL, USA.
J Pediatr. 2006 Apr;148(4):438-444. doi: 10.1016/j.jpeds.2005.11.042.
To predict death or neurodevelopmental impairment (NDI) in extremely low birth weight infants by classification trees with recursive partitioning and automatic selection of optimal cut points of variables.
Data from the Trial of Indomethacin Prophylaxis in Preterms were randomly divided into development (n=784) and validation sets (n=262). Three models were developed for the combined outcome of death (8 days to 18 months) or NDI (cerebral palsy, cognitive delay, deafness, or blindness at 18 months corrected age): antenatal: antenatal data; early neonatal: antenatal+first 3 days data; and first week: antenatal, first 3 days, and 4th to 8th days data. Decision trees were tested on the validation set.
Variables associated with death/NDI in each model were: Antenatal: Gestation<or=25.5 weeks and antenatal steroids<7 days. Early neonatal: Birth weight<or=787 g and fluid intake>01 mL/kg/d. First week: Birth weight<or=787 g: transfusion>3 mL/kg/d. Birth weight>787 g: cranial echodense intraparenchymal lesion and transfusion>1 mL/kg/d. Correct classification rates were 61% to 62% for all models.
The ability to predict long-term morbidity/death in extremely low birth weight infants does not improve significantly over the first week of life. Effects of different variables depend on age.
通过具有递归划分和变量最佳切点自动选择功能的分类树，预测极低出生体重儿的死亡或神经发育障碍（NDI）。
将来自早产儿吲哚美辛预防试验的数据随机分为开发集（n = 784）和验证集（n = 262）。针对死亡（出生8天至18个月）或NDI（18个月矫正年龄时的脑瘫、认知延迟、耳聋或失明）的联合结局开发了三个模型：产前模型：产前数据；早期新生儿模型：产前+出生后前3天的数据；第一周模型：产前、出生后前3天以及第4至8天的数据。在验证集上对决策树进行测试。
每个模型中与死亡/NDI相关的变量为：产前模型：孕周≤25.5周且产前使用类固醇激素<7天。早期新生儿模型：出生体重≤787 g且液体摄入量>01 mL/kg/d。第一周模型：出生体重≤787 g：输血>3 mL/kg/d。出生体重>787 g：脑实质内回声增强病变且输血>1 mL/kg/d。所有模型的正确分类率为61%至62%。
在出生后的第一周内，预测极低出生体重儿长期发病/死亡的能力没有显著提高。不同变量的影响取决于年龄。
