AI-Powered Early Detection of Genetic Disorders in Fetuses Using Machine Learning Models

Pregnancy complications have significant effects on women and can threaten the health of an unborn child. Pregnant women have a great interest in issues related to fetuses. The aim of the project is to create a predicting instrument for anticipating the state of a fetus' health by studying its pulse, speed ups, mobility and as well as the contractions within the womb using computer-based learning methods applied to the database of Cardiotocography. In this study, Some examples of machine learning algorithms are Random Forest, Logistic Regression, Decision Trees, Support Vector Classifications and K-Nearest Neighbours were employed to process the dataset. Through using all implemented machine learning models, we managed to achieve an accuracy of 99% through Random Forest algorithm. Detecting early complications is vital, and this study shows how medical resource management can be improved by machine learning, thus saving time.