Related Experiment Video
Updated: Jan 16, 2026
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
Published on: May 17, 2024
Machine learning-augmented biomarkers in mid-pregnancy Down syndrome screening improve prediction of
Bin Zhang1, Xusheng Chen1, Zhaolong Zhan1
1Department of Medical Genetics, Changzhou Maternal and Child Health Care Hospital, Changzhou Medical Center, Nanjing Medical University, Changzhou, China.
Insights
Unconjugated estriol (uE3) shows superior prediction for adverse fetal growth outcomes (AFGO) compared to other markers. Machine learning models, particularly GBM and GLM, significantly improve small-for-gestational age (SGA) prediction.
Area of Science:
- Obstetrics and Gynecology
- Prenatal Diagnostics
- Biomarker Research
Background:
- Adverse fetal growth outcomes (AFGO), including small-for-gestational age (SGA), large-for-gestational age (LGA), low birth weight (LBW), and macrosomia (Mac), pose significant challenges for early prediction.
- Routine biochemical markers from prenatal screening are currently used, but their predictive capabilities for AFGO require enhancement.
Purpose of the Study:
- To establish predictive probabilities for AFGO using routine prenatal biochemical screening markers.
- To evaluate machine learning (ML) models incorporating these biomarkers and maternal characteristics for improved AFGO identification.
Main Methods:
- Retrospective analysis of 2533 singleton deliveries (2015-2017).
- Inclusion of early second-trimester biomarkers: α-fetoprotein (AFP), free β-human chorionic gonadotropin (fβ-hCG), and unconjugated estriol (uE3).
- Development and evaluation of four ML-based prediction models (including Gradient Boosting Machine - GBM and Generalized Linear Model - GLM).
Main Results:
- Serum uE3 demonstrated superior predictive performance for AFGO compared to fβ-hCG or AFP alone, evidenced by higher Area Under the Curve (AUC) values in ROC analyses.
- ML models, particularly GBM and GLM, significantly enhanced prediction for SGA, achieving AUCs of 0.873 and 0.706 in the training set and 0.717 and 0.739 in the test set, respectively.
- The study identified specific predictive values for various AFGOs using individual biomarkers and ML models.
Conclusions:
- Serum uE3 is a more effective predictor of AFGO than fβ-hCG and AFP.
- Gradient Boosting Machine (GBM) and Generalized Linear Model (GLM) models substantially improve the prediction accuracy for SGA.
- Integrating routine prenatal screening biomarkers with machine learning offers a promising approach for the early identification of adverse fetal growth outcomes.
Background:
Adverse fetal growth outcomes (AFGO), primarily characterized by small-for-gestational age (SGA), large-for-gestational age (LGA), low birth weight (LBW) neonates, and macrosomia (Mac), present substantial challenges in early prediction. This study aims to 1) establish a predictive probability for AFGO using routine biochemical markers from prenatal Down syndrome screening, and 2) evaluate the performance of machine learning-based prediction models that incorporate these biomarkers and maternal characteristics for AFGO identification.
Methods:
A retrospective analysis was conducted on 2533 singleton deliveries from 2015 to 2017, with available data on early second-trimester biomarkers [α-fetoprotein (AFP), free β-human chorionic gonadotropin (fβ-hCG), and unconjugated estriol (uE3)], as well as pregnancy outcomes.
Results:
Serum uE3 demonstrated higher predictive performance for AFGO compared to fβ-hCG or AFP alone, with higher area under the curve (AUC) values in receiver operating characteristic (ROC) analyses (SGA: 0.626 vs. 0.501/0.500; LGA: 0.557 vs. 0.502/0.537; LBW: 0.614 vs. 0.543/0.559; Mac: 0.546 vs. 0.532/0.519). To improve AFGO prediction, we developed four machine learning-based models. Gradient boosting machine (GBM) and generalized linear model (GLM) models demonstrated optimal performance for SGA prediction, achieving AUC values of 0.873 and 0.706, respectively, in the training set (n = 1782, SGA 143), and 0.717 and 0.739 in the test set (n = 751, SGA 68).
Conclusion:
Serum uE3 is superior to fβ-hCG and AFP in predicting AFGO. GBM and GLM models significantly enhance SGA prediction performance, highlighting the potential of integrating routine prenatal screening biomarkers with machine learning for early identification of AFGO.
