Dataset Information

Machine learning-augmented biomarkers in mid-pregnancy Down syndrome screening improve prediction of small-for-gestational-age infants.

ABSTRACT:

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.

SUBMITTER: Zhang B

PROVIDER: S-EPMC12487514 | biostudies-literature | 2025 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning-augmented biomarkers in mid-pregnancy Down syndrome screening improve prediction of small-for-gestational-age infants.

Zhang Bin B Chen Xusheng X Zhan Zhaolong Z Xi Sijie S Zhang Yinglu Y Dong He H Yuan Xiaosong X

Orphanet journal of rare diseases 20251001 1

<h4>Background</h4>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 bioma ...[more]

PMID: 41034923

Similar Datasets

Project description:Data on the temporal dynamics of human placental gene expression is scarce. We have completed the first whole-genome profiling of human placental gene expression dynamics (GeneChips, Affymetrix®) from early to mid- gestation (10 samples; gestational weeks 5 to 18) and report 154 genes with considerable change in transcript levels (FDR P<0.1). Functional enrichment analysis revealed >200 GO categories that are statistically over-represented among 105 genes with dynamically increasing transcript levels. Analysis in an extended sample (n=43; gestational weeks 5 to 41) conformed a highly significant (FDR P<0.05) expressional peak in mid-gestation placenta for ten genes: BMP5, CCNG2, CDH11, FST, GATM, GPR183, ITGBL1, PLAGL1, SLC16A10, STC1. A central hypothesis of our study states that the aberrant expression of genes characteristic to mid-gestation placenta may contribute to affected fetal growth, maternal preeclampsia (PE) or gestational diabetes (GD). The gene STC1 coding for Stanniocalcin 1 (STC1) was identified with a sharp placental expressional peak in mid-gestation, increased mRNA levels at term and significantly elevated STC1 protein levels in post-partum maternal plasma in all pregnancy complications. The highest STC1 levels were identified in women, who developed simultaneously PE and delivered an SGA baby (median 731 vs 418 pg/ml in controls; P=0.001). CCNG2 and LYPD6 exhibited significantly increased placental mRNA expression and enhanced intensity of immunohistochemistry staining in placental sections all studied in GD and PE cases. Aberrant expression of mid-gestation specific genes in pregnancy complications at term indicates the importance of the fine-scale tuning of the temporal dynamics of transcription regulation in placenta. Observed significantly elevated plasma STC1 in complicated pregnancies warrants further investigations of its potential as a biomarker. Interestingly, a majority of genes with high expression in mid-gestation placenta have also been implicated in adult complex disease. This observation promotes a recently opened discussion on the role of placenta in developmental programming.

Dataset Information

Machine learning-augmented biomarkers in mid-pregnancy Down syndrome screening improve prediction of small-for-gestational-age infants.

Background

Methods

Results

Conclusion

Publications

Machine learning-augmented biomarkers in mid-pregnancy Down syndrome screening improve prediction of small-for-gestational-age infants.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets