Catboost in Fetal Health Classification

The evaluation of fetal health is vital in safeguarding the overall welfare of pregnant women and their unborn children. Using the Catboost algorithm, we address the difficulty of precisely determining the health status of the fetus in this study. A variety of machine learning models were contrasted, such as AdaBoost, LightGBM, and XGBoost. The outcomes of experiments employing both train-test split and K-Fold cross-validation demonstrate that CatBoost consistently attains commendable levels of accuracy, precision, and recall, with values varying between 0.94 and 0.97 across distinct folds.