While there is increasing interest in identifying pregnancies at risk for adverse outcome, existing prediction models have not adequately assessed population-based risks, and have been based on conventional regression methods. The objective of the current study was to identify predictors of fetal growth abnormalities using logistic regression and machine learning methods, and compare diagnostic properties in a population-based sample of infants. Data for 30,705 singleton infants born between 2009 and 2014 to mothers resident in Nova Scotia, Canada was obtained from the Nova Scotia Atlee Perinatal Database. Primary outcomes were small (SGA) and large for gestational age (LGA). Maternal characteristics pre-pregnancy and at 26 weeks were studied as predictors. Logistic regression and select machine learning methods were used to build the models, stratified by parity. Area under the curve was used to compare the models; relative importance of predictors was compared qualitatively. 7.9% and 13.5% of infants were SGA and LGA, respectively; 48.6% of births were to primiparous women and 51.4% were to multiparous women. Prediction of SGA and LGA was poor to fair (area under the curve 60–75%) and improved with increasing parity and pregnancy information. Smoking, previous low birthweight infant, and gestational weight gain were important predictors for SGA; pre-pregnancy body mass index, gestational weight gain, and previous macrosomic infant were the strongest predictors for LGA. The machine learning methods used in this study did not offer any advantage over logistic regression in the prediction of fetal growth abnormalities. Prediction accuracy for SGA and LGA based on maternal information is poor for primiparous women and fair for multiparous women.

The literature shows a variable and inconsistent relationship between socioeconomic position and preterm birth. We examined risk factors for spontaneous and iatrogenic preterm birth, with a focus on socioeconomic position and clinical risk factors, in order to explain the observed inconsistency.

Fetal growth restriction and maternal smoking during pregnancy are independently implicated in lowering intellectual attainment in children. We hypothesized that only reduction of fetal growth that is attributable to extrinsic causes (e.g., maternal smoking) affects intellectual development of a child. Cross-sectional survey of 3,739 students in Nova Scotia (Canada) in 2003 was linked with the perinatal database, parental interviews on socio-demographic factors and the performance on standardized tests when primarily 11–12 years of age, thereby forming a retrospective cohort. Data was analyzed using hierarchical logistic regression with correction for clustering of children within schools. The risk of poor test result among children born small-for-gestational-age (SGA) to mothers who smoked was 29.4%, higher than in any other strata of maternal smoking and fetal growth. The adjusted odds ratio among SGA children born to mothers who smoked was the only one elevated compared to children who were not growth restricted and born to mothers who did not smoke (17.0%, OR = 1.46, 95% CI 1.02, 2.09). Other perinatal, maternal and socio-demographic factors did not alter this pattern of effect modification. Heterogeneity of etiology of fetal growth restriction should be consider in studies that address examine its impact on health over life course.