Related Experiment Video
Updated: Jul 29, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Development of risk prediction models for preterm delivery in a rural setting in Ethiopia
Clara Pons-Duran1, Bryan Wilder1,2, Bezawit Mesfin Hunegnaw3
1Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, USA.
Insights
Predicting preterm birth risk using available data in Ethiopia proved challenging. Current models show poor performance, indicating a need for novel technologies to accurately identify high-risk pregnancies and improve maternal and infant outcomes.
Area of Science:
- Obstetrics and Gynecology
- Perinatal Health
- Public Health in Low-Resource Settings
Background:
- Preterm birth complications are a leading cause of mortality in children under five globally.
- Accurate prediction of high-risk pregnancies for preterm delivery is difficult, particularly in resource-limited settings lacking biomarker assessments.
Purpose of the Study:
- To evaluate the predictability of preterm delivery risk using routinely available data in a pregnancy and birth cohort in Ethiopia.
- To assess if incorporating cervical length and fetal fibronectin measurements could enhance predictive model performance.
Main Methods:
- Utilized data from 2493 pregnancies in Amhara region, Ethiopia (December 2018 - March 2020).
- Employed Cox and accelerated failure time models, and decision tree ensembles for risk prediction.
- Estimated model discrimination using Area Under the Curve (AUC) and simulated biomarker distributions (cervical length, fetal fibronectin).
Main Results:
- Overall predictive performance of the models was poor, with the tree ensemble classifier achieving the highest AUC of 0.60.
- When calibrated to identify 90% of preterm deliveries, 75% of those classified as high-risk did not experience preterm birth.
- Simulated cervical length and fetal fibronectin distributions did not significantly improve model performance.
Conclusions:
- Accurate prediction of preterm delivery risk remains a significant challenge, especially in resource-limited environments.
- Improved prediction could save lives and guide resource allocation for high-risk pregnancies.
- Novel technologies focusing on genetic factors, immunological biomarkers, or protein expression may be necessary for accurate risk prediction.
Background:
Preterm birth complications are the leading causes of death among children under five years. However, the inability to accurately identify pregnancies at high risk of preterm delivery is a key practical challenge, especially in resource-constrained settings with limited availability of biomarkers assessment.
Methods:
We evaluated whether risk of preterm delivery can be predicted using available data from a pregnancy and birth cohort in Amhara region, Ethiopia. All participants were enrolled in the cohort between December 2018 and March 2020. The study outcome was preterm delivery, defined as any delivery occurring before week 37 of gestation regardless of vital status of the foetus or neonate. A range of sociodemographic, clinical, environmental, and pregnancy-related factors were considered as potential inputs. We used Cox and accelerated failure time models, alongside decision tree ensembles to predict risk of preterm delivery. We estimated model discrimination using the area-under-the-curve (AUC) and simulated the conditional distributions of cervical length (CL) and foetal fibronectin (FFN) to ascertain whether they could improve model performance.
Results:
We included 2493 pregnancies; among them, 138 women were censored due to loss-to-follow-up before delivery. Overall, predictive performance of models was poor. The AUC was highest for the tree ensemble classifier (0.60, 95% confidence interval = 0.57-0.63). When models were calibrated so that 90% of women who experienced a preterm delivery were classified as high risk, at least 75% of those classified as high risk did not experience the outcome. The simulation of CL and FFN distributions did not significantly improve models' performance.
Conclusions:
Prediction of preterm delivery remains a major challenge. In resource-limited settings, predicting high-risk deliveries would not only save lives, but also inform resource allocation. It may not be possible to accurately predict risk of preterm delivery without investing in novel technologies to identify genetic factors, immunological biomarkers, or the expression of specific proteins.
Related Concept Videos
01:18Steps in Outbreak Investigation
01:52Regression Toward the Mean
01:03Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.