Fatal Health Risk Prediction Using Machine Learning Techniques with Cardiotocography Dataset

Pregnant women's health is crucial, and any issues or unpleasant circumstances that develop during pregnancy can have a major impact on the mother and the developing fetus. In order to predict fetal health outcomes using Cardiotocography (CTG) data, this research study examines the use of machine learning methods, such as SVC, a Random Forest the Decision Tree, and Logistic Regression. Evaluation of these algorithms' performance in terms of F1 score, recall, accuracy, and precision is the goal of the study. According to the results, Random Forest had the highest accuracy (95%), followed by Decision Tree (91.6%), SVC (90.6%), and Logistic Regression (89%). In addition, Random Forest had the best F1 score, recall, and precision—94.8%, 94.7%, and 94.8%, respectively.