Table 3 Area under the curve, accuracy, and the three most important predictors for the prediction of large for gestational age (LGA) birth using logistic regression and five machine learning methods pre-pregnancy and at 26 weeks in nulliparous and multiparous women

 Area under the curve

0.592

0.587

0.563

0.576

0.587

0.594

0.702

0.705

0.675

0.673

0.697

0.705

 Accuracy

0.826

0.827

0.800

0.824

0.832

0.827

0.843

0.834

0.780

0.834

0.839

0.842

 Maternal age

●

●

●

 Common-law/married

●

 Pre-pregnancy smoking

●

●

●

●

 Pre-pregnancy BMI

●

●

●

●

●

●

●

●

●

●

 Pre-existing diabetes

●

●

●

●

●

●

●

 Weight gain at 26 wks

●

●

●

●

●

 Smoking in pregnancy

●

●

●

 Pregnancy-induced hypertension

●

●

 Gestational diabetes

●

 Area under the curve

0.700

0.700

0.659

0.692

0.704

0.700

0.745

0.748

0.718

0.728

0.748

0.746

 Accuracy

0.807

0.806

0.817

0.795

0.804

0.807

0.813

0.809

0.794

0.799

0.805

0.812

 Maternal age

●

 Pre-pregnancy smoking

●

●

 Pre-pregnancy BMI

●

●

●

●

●

●

●

●

 Pre-existing diabetes

●

●

●

●

●

 Previous LBW infant

 Previous infant > 4080 g

●

●

●

●

●

●

●

●

●

●

●

●

 Previous death of neonate ≥500 g

●

●

 Weight gain at 26 wks

●

●

●

●

●

 Smoking in pregnancy

●