PREDICTING HEALTH OF FOETUS USING KNN ALGORITHM

Abstract: Fetal wellbeing is an important issue in prenatal care because early identification of complications was implemented, and performance was measured on the basis of important metrics: accuracy, precision, recall, and F1-score. Our model had an accuracy of can greatly lower the potential 94.5%, showing its in assisting gynecologists’ risk of neonatal death and long-term developmental problems. we introduce a data driven method for forecasting fetal health condition based on the KNearest Neighbors algorithm, which is an un complicated yet efficient machine learning technique commonly known as the best performer in medical diagnosis. The dataset fetal cardiotocographic measurement records, including fetal heartbeat, uterine contractions, and accelerations. These inputs were obstetricians with real-time decision- making in pregnancy monitoring. project tells the ability of machine learning to improve fetal health evaluation. KeyWords: Fetal health prediction, K-Nearest Neighbors (KNN), Machine Learning, Cardiotocography (CTG), Prenatal care, Classification, Medical diagnostics, Feature extraction, Neonatal mortality, Healthcare AI