Machine learning-based risk factor analysis of adverse birth outcomes in very low birth weight infants

Abstract

This study aimed to analyze major predictors of adverse birth outcomes in very low birth weight (VLBW) infants including particulate matter concentration (PM10), using machine learning and the national prospective cohort. Data consisted of 10,423 VLBW infants from the Korean Neonatal Network database during January 2013–December 2017. Five adverse birth outcomes were considered as the dependent variables, i.e., gestational age less than 28 weeks, gestational age less than 26 weeks, birth weight less than 1000 g, birth weight less than 750 g and small-for-gestational age. Thirty-three predictors were included and the artificial neural network, the decision tree, the logistic regression, the Naïve Bayes, the random forest and the support vector machine were used for predicting the dependent variables. Among the six prediction models, the random forest had the best performance (accuracy 0.79, area under the receiver-operating-characteristic curve 0.72). According to the random forest variable importance, major predictors of adverse birth outcomes were maternal age (0.2131), birth-month (0.0767), PM10 month (0.0656), sex (0.0428), number of fetuses (0.0424), primipara (0.0395), maternal education (0.0352), pregnancy-induced hypertension (0.0347), chorioamnionitis (0.0336) and antenatal steroid (0.0318). In conclusion, adverse birth outcomes had strong associations with PM10 month as well as maternal and fetal factors.