An essential component of prenatal care is fetal health monitoring, traditionally relying on subjective methods such as ultrasound and cardiotocography (CTG). This project aims to develop a strong classification scheme for predicting fetal health status utilizing several deep learning (DL) and machine learning (ML) models. The research employs feature selection techniques, including correlation analysis and SelectKBest, to enhance model performance by reducing dimensionality and eliminating irrelevant features. The xGBoost endorsed kBestFS approach is utilized to identify the optimal number of features, significantly improving the models’ performance. The project compares the results of different models, including Random Forest (RF), Gradient Boosting (GB), AdaBoost, XGBoost, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression (LR), and Deep Neural Networks (DeepNN). It aims to find the best course of action. The outcomes demonstrate that feature selection using SelectKBest and xGBoost significantly improves model accuracy, interpretability, and computational efficiency. The study also assesses additional performance indicators including precision, recall, F1-score, and ROC-AUC to offer a thorough evaluation of the model’s performance.