Development and validation of a simplified risk prediction model for preterm birth: a prospective cohort study in rural Ethiopia

Abstract

Preterm birth is one of the most common obstetric complications in low- and middle-income countries, where access to advanced diagnostic tests and imaging is limited. Therefore, we developed and validated a simplified risk prediction tool to predict preterm birth based on easily applicable and routinely collected characteristics of pregnant women in the primary care setting. We used a logistic regression model to develop a model based on the data collected from 481 pregnant women. Model accuracy was evaluated through discrimination (measured by the area under the Receiver Operating Characteristic curve; AUC) and calibration (via calibration graphs and the Hosmer-Lemeshow goodness of fit test). Internal validation was performed using a bootstrapping technique. A simplified risk score was developed, and the cut-off point was determined using the "Youden index" to classify pregnant women into high or low risk for preterm birth. The incidence of preterm birth was 19.5% (95% CI:16.2, 23.3) of pregnancies. The final prediction model incorporated mid-upper arm circumference, gravidity, history of abortion, antenatal care, comorbidity, intimate partner violence, and anemia as predictors of preeclampsia. The AUC of the model was 0.687 (95% CI: 0.62, 0.75). The calibration plot demonstrated a good calibration with a p-value of 0.713 for the Hosmer-Lemeshow goodness of fit test. The model can identify pregnant women at high risk of preterm birth. It is applicable in daily clinical practice and could contribute to the improvement of the health of women and newborns in primary care settings with limited resources. Healthcare providers in rural areas could use this prediction model to improve clinical decision-making and reduce obstetrics complications.

Keywords: Ethiopia; Prediction model; Pregnant women; Preterm birth; Risk score.

Figure 1

Flow chart of the study design for preterm births in the Butajira Nutrition, Mental Health, and Pregnancy cohort.

Figure 2

Model performance of the prediction model for preterm birth. (A) The area under the receiver operating characteristics curve to evaluate the discrimination. The AUC suggests that the model has a 68.7% (95%CI:62.0%,75.3%) chance to correctly distinguish a high risk for preterm birth from normal pregnancy based on the characteristics of pregnant women in resource limited setting. (B) Calibration plot to evaluate the calibration of the prediction model. The visual calibration plot between the observed and prediction risk in different percentiles of the predicted values. The p-value of the calibration plot is 0.713.

Figure 3

Area under the receiver operating characteristic curve of an internal validation of the prediction model.

Figure 4

Model performance after adding maternal stress in the prediction model. (A) Area under the receiver operating characteristic curve of the final model with and without maternal stress. (B) Calibration plot to evaluate the calibration of the addition of maternal stress to the final model. The added value maternal stress was assessed through a calibration plot, revealing a good calibration (a p-value of 0.825).