In this study we analyzed different well-established machine learning (ML) and deep learning (DL) supervised models to enable the risk prediction of maternal health, thus offering a viable and systematic technique to automatically identify pregnancy risk. The Maternal Health Risk Data Set, which covers various critical attributes such as age, blood pressure, blood sugar, body temperature, heart rate, and risk level, was applied [8]. Data pretreatment methods, including deleting missing data (if any) and conducting feature scaling and selection, were incorporated to create the model. Different ML models were created and tested, including but not limited to Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB), as well as deep learning architectures such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM). Model performances were evaluated using metric measures, including accuracy and F1 scores. Of them, CNN showed the highest accuracy (98.58), exceeding alternative models by its capacity to uncover spatial correlations crucial for successful risk prediction. CNN shows great accuracy, which indicates that its real-life clinical application in predicting high-risk pregnancies would result in a considerable improvement in maternal care. Adding AI-driven models to existing healthcare settings could assist in the faster and more accurate evaluation of pregnancy risk, particularly in low-resource settings, boosting focused preventative therapy and evidence-based clinical decision-making. The expanding presence of AI has the potential to revolutionize healthcare, taking us closer to scalable automated solutions for maternal health that correspond with global healthcare development goals, with implications from this study.

Automated Pregnancy Risk Prediction Machine Learning Deep Learning Risk Level Classification Healthcare AI