Obstetricians utilize cardiotocography (CTG) to assess the fetal heart and lungs during pregnancy. It can help determine if the foetus is healthy, in doubt, or suffering from disease by providing data on the fetal heart rate and uterine breathing. The analysis of CTG data has typically made use of machine learning (ML) techniques such as support vector machines and decision trees to forecast fetal health and enhance the detection procedure. Fetal heart rate and uterine contraction timing were recorded by CTG. Monitoring fetal health and ensuring normal fetal growth and development throughout pregnancy rely heavily on CTG intelligent categorization. Pregnancies with a higher risk of problems are the most common cases in which CTG is used to evaluate the health of the fetus. ML algorithms are utilized to evaluate state of the foetal health based on CTG-obtained factors. Compared to ML techniques, ensemble models have been shown to increase detection speed and effectiveness. Ensemble modeling refers to the practice of combining the scores or distributions from multiple related but distinct analytical models. In order to predict foetal health, ensemble models such as Boosting, AdaBoost, Extreme Gradient Boosting, Light gradient boost method (LightGBM), and stack models were used in the paper. When the outcomes are compared, the proposed stack model using logistic regression, decision tree, random forest and LightGBM proved to obtain the best performance with 96.71% success rate. The proposed methodology, which can be used to classify foetal health based on Fetal Heart Rate (FHR) data, is more efficient and superior to existing machine learning models, which have already been taken into consideration.