Abstract TH255: Machine Learning Models for the Prediction of Pre-Eclampsia: A Systematic Review and Meta-Analysis
Hypertension · 2026-10 · 83 (Suppl_1)
DOI: 10.1161/hyp.83.suppl_1.th255 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Hypertension, 2026-10. Verfasst von Maneeth Mylavarapu und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Background
Pre-eclampsia (PE) remains a leading cause of maternal and neonatal morbidity and mortality worldwide. Traditional clinical risk factors have limited predictive accuracy. While machine learning (ML) models offer a dynamic approach to prognostic risk stratification, but their collective performance and clinical utility have not been systematically synthesized.
Objective
To assess the performance of machine learning models in predicting the development of PE.
Methods
Per PRISMA guidelines, we systematically searched PubMed, Google Scholar, Embase, Science Direct, and Cochrane Library for studies published up to May 2026 evaluating ML models for prognostic risk prediction of PE. Studies were included if they reported model discrimination metrics (area under the receiver operating characteristic curve [AUC-ROC], sensitivity, specificity). Random-effects model with inverse variance was used to calculate the pooled metrics. P
Zitieren
APA
Mylavarapu, M., Kodali, L. S. M., Kiyani, M., & Tanwar, N. (2026). Abstract TH255: Machine Learning Models for the Prediction of Pre-Eclampsia: A Systematic Review and Meta-Analysis. Hypertension, 83(Suppl_1). https://doi.org/10.1161/hyp.83.suppl_1.th255
Vancouver
Mylavarapu M, Kodali LSM, Kiyani M, Tanwar N. Abstract TH255: Machine Learning Models for the Prediction of Pre-Eclampsia: A Systematic Review and Meta-Analysis. Hypertension. 2026;83(Suppl_1). doi:10.1161/hyp.83.suppl_1.th255
BibTeX
@article{Mylavarapu2026,
author = {Mylavarapu, Maneeth and Kodali, Lakshmi Sai Meghana and Kiyani, Madiha and Tanwar, Niharika},
title = {Abstract TH255: Machine Learning Models for the Prediction of Pre-Eclampsia: A Systematic Review and Meta-Analysis},
journal = {Hypertension},
year = {2026},
volume = {83},
number = {Suppl_1},
doi = {10.1161/hyp.83.suppl_1.th255}
}
EUVIMED