This systematic review evaluates the use of machine learning (ML) models to predict preeclampsia, a hypertensive disorder that affects pregnant women. The review adhered to PRISMA guidelines and searched multiple databases up to February 2023. After screening, 18 full-text articles were evaluated, and four studies were included. These studies used retrospective cohort designs and various ML models such as Elastic Net, Stochastic Gradient Boosting, Extreme Gradient Boosting, and Random Forest. The models were trained using maternal characteristics, medical history, medication intake, obstetrical history, and prenatal laboratory and ultrasound findings. The AUC of the ML models ranged from 0.860 to 0.973, indicating high prediction performance. The review highlights the potential of ML in early preeclampsia prediction, but also notes limitations such as the need for external validation and the exclusion of non-English articles. The findings suggest that ML can significantly aid in the prediction of preeclampsia risk from routine early pregnancy information.This systematic review evaluates the use of machine learning (ML) models to predict preeclampsia, a hypertensive disorder that affects pregnant women. The review adhered to PRISMA guidelines and searched multiple databases up to February 2023. After screening, 18 full-text articles were evaluated, and four studies were included. These studies used retrospective cohort designs and various ML models such as Elastic Net, Stochastic Gradient Boosting, Extreme Gradient Boosting, and Random Forest. The models were trained using maternal characteristics, medical history, medication intake, obstetrical history, and prenatal laboratory and ultrasound findings. The AUC of the ML models ranged from 0.860 to 0.973, indicating high prediction performance. The review highlights the potential of ML in early preeclampsia prediction, but also notes limitations such as the need for external validation and the exclusion of non-English articles. The findings suggest that ML can significantly aid in the prediction of preeclampsia risk from routine early pregnancy information.