This systematic review evaluates machine learning (ML) models for predicting preeclampsia. Four studies were included, all using retrospective cohort designs. Nine distinct ML models were analyzed, including elastic net, stochastic gradient boosting, extreme gradient boosting, and random forest. These models utilized maternal characteristics, medical history, medication intake, obstetrical history, and laboratory and ultrasound findings from prenatal visits. The area under the curve (AUC) of ML models ranged from 0.860 to 0.973, indicating high predictive performance. The best-performing models included stochastic gradient boosting, extreme gradient boosting, and random forest. The review highlights the potential of ML in early preeclampsia prediction using routine early pregnancy data. However, some studies had low to moderate risk of bias, and non-English articles were excluded. The results suggest that ML models can effectively predict preeclampsia, but further validation is needed. The review adheres to PRISMA guidelines and provides a comprehensive overview of ML applications in preeclampsia prediction.This systematic review evaluates machine learning (ML) models for predicting preeclampsia. Four studies were included, all using retrospective cohort designs. Nine distinct ML models were analyzed, including elastic net, stochastic gradient boosting, extreme gradient boosting, and random forest. These models utilized maternal characteristics, medical history, medication intake, obstetrical history, and laboratory and ultrasound findings from prenatal visits. The area under the curve (AUC) of ML models ranged from 0.860 to 0.973, indicating high predictive performance. The best-performing models included stochastic gradient boosting, extreme gradient boosting, and random forest. The review highlights the potential of ML in early preeclampsia prediction using routine early pregnancy data. However, some studies had low to moderate risk of bias, and non-English articles were excluded. The results suggest that ML models can effectively predict preeclampsia, but further validation is needed. The review adheres to PRISMA guidelines and provides a comprehensive overview of ML applications in preeclampsia prediction.