Comparison of logistic regression with machine learning methods for the prediction of fetal growth abnormalities: a retrospective cohort study

• Main Authors: Stefan Kuhle (Author), Bryan Maguire (Author), Hongqun Zhang (Author), David Hamilton (Author), Alexander C. Allen (Author), K. S. Joseph (Author), Victoria M. Allen (Author)
• Format: Book
• Published: BMC, 2018-08-01T00:00:00Z.
• Subjects: article
• Online Access: Connect to this object online.
• Notes: 10.1186/s12884-018-1971-2; 1471-2393
• Keywords: Pregnancy; Infant; Prediction; Birth weight; Fetal growth restriction; Fetal macrosomia; Gynecology and obstetrics; RG1-991
• Source: BMC Pregnancy and Childbirth, Vol 18, Iss 1, Pp 1-9 (2018)

Abstract Background 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. Methods 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. Results 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. Conclusions 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.