Classification of Fetal Status from Cardiotocogram Data by Using Machine Learning

The pregnance duration is about 9 months. In this period, there may be various reasons which may cause a problem which may lead to mortality in the newborn. We need to minimize such accidents. One of the most significant tool to analyze the health of the fetal in the womb is by doing a Cadiotocography (CTG). Cardiotocogram (CTG) is a commonly used technique to continuously monitor and record fetal heart rate (FHR) and uterine contractions (UC) during pregnancy to assess fetal health and diagnose the risk of pregnancy problems. Machine learning is a field that has been widely applied in life, especially in medicine, this technique has brought great advances in diagnosis, treatment and prognosis of diseases. In the content of the article, we study machine learning techniques to classify fetal status through CTG data by using classification methods: Support Vector Machine (SVM) and K-Nearest Neighbors (K-NN). The analytical results of the paper show that the accuracy of SVM and KNN, methods is 92, 89, respectively. These results will be assisted doctors in abnormal cardiotocogram early detection. © 2023 IEEE.