سامانه همایش های دانشگاه آزاد اسلامی واحد نجف آباد

صفحه اصلی / اولین همایش بین المللی تحول خدمات سلامت: تلفیق مراقبت، درمان، بازتوانی و امیدبخشی

Artificial Intelligence and Machine Learning Approaches for Preeclampsia Prediction: Predictive Models, Performance, and Clinical Translation

نویسندگان :

Nastaran Piroozeh¹ Sareh Kiani² Asiyeh Nabi Zadeh³ Shadi Goli⁴ Leila Ab Ab⁵

1- دانشگاه آزاد اسلامی واحد مستقل نجف آباد 2- دانشگاه آزاد اسلامی واحد مستقل نجف آباد 3- دانشگاه آزاد اسلامی واحد مستقل نجف آباد 4- دانشگاه آزاد اسلامی واحد مستقل نجف آباد 5- دانشگاه آزاد اسلامی واحد مستقل نجف آباد

کلمات کلیدی :

Preeclampsia،Artificial Intelligence،Machine Learning،Pregnancy،Risk Prediction،Biomarkers

چکیده :

Abstract Background: Preeclampsia is a major hypertensive disorder of pregnancy and a leading cause of maternal and fetal morbidity and mortality. Early prediction remains challenging due to limited accuracy of conventional screening methods. Artificial intelligence (AI) and machine learning (ML) have emerged as promising tools to improve early risk stratification. Methods: This narrative review assessed studies (2022-2025) on AI/ML applications in preeclampsia prediction. A structured search was performed in PubMed/MEDLINE, Scopus, Web of Science, ScienceDirect, and Google Scholar. Sixteen studies were included. Data on ML models, predictors, and performance metrics were synthesized narratively. Results: ML models, particularly Random Forest and XGBoost, showed superior performance compared with traditional methods. Reported AUC values ranged from 0.73 to 0.97. Key predictors included maternal history, blood pressure parameters, and biomarkers such as PlGF and PAPP-A. Model performance generally improved with gestational age, and external validation studies showed acceptable performance. Conclusion: AI/ML models demonstrate strong potential for early prediction of preeclampsia and improved risk stratification. However, further validation, standardization, and explainable AI development are required before clinical implementation. Keywords: Preeclampsia, Artificial Intelligence, Machine Learning, Pregnancy, Risk Prediction, Biomarkers