A Comparative Study of Machine Learning Models for Fetal Health Classification

The cardiotocogram (CTG) is the main technique used in clinical practice for monitoring fetal well-being. Eighteen machine learning single models were initially tested on the CTG dataset in this article. The four top models are then combined to create the Stacking Integration Model which is then contrasted with the Blender Model created in the same way utilizing a soft voting ensemble method. The best model described in this study outperformed the conventional machine learning models in a variety of Classification Model evaluations, achieving accuracy rate of 0.986, F1 score of 0.986, precision rate of 0.986, recall rate of 0.986, and MCC of 0.979, AUC of 1.