Clinical risk models for preterm birth less than 28 weeks and less than 32 weeks of gestation using a large retrospective cohort

ObjectiveTo develop risk prediction models for singleton preterm birth (PTB) < 28 weeks and <32 weeks.MethodsUsing a retrospective cohort of 267,226 singleton births in Ontario hospitals, we included variables from the first and second trimester in multivariable logistic regression models to predict overall and spontaneous PTB < 28 weeks and <32 weeks.ResultsDuring the first trimester, the area under the curve (AUC) for prediction of PTB < 28 weeks for nulliparous and multiparous women was 68.5% (95% CI: 63.5–73.6%) and 73.4% (68.6–78.2%), respectively, while for PTB < 32 weeks it was 68.9% (65.5–72.3%) and 75.5% (72.3–78.7%), respectively. AUCs for second-trimester models were 72.4% (95% CI: 69.7–75.1%) and 78.2% (95% CI: 75.8–80.5%), respectively, in nulliparous and multiparous women. Predicted probabilities were well-calibrated within a wide range around expected base prevalence for the study outcomes.ConclusionsOur prediction models generated acceptable AUCs for PTB < 28 weeks and <32 weeks with good calibration during the first and second trimester.