This work explores the critical area of fetal health prediction and birth weight estimation using machine learning techniques that focus on the analysis of cardiotocography (CTG) data. Given the growing importance of pregnancy and childbirth, this effort highlights the transformative journey of motherhood in parallel with the development of medical technology. Fetal health prediction and birth weight should be calculated. Using sophisticated algorithms such as cat boost regressor, SGD regressor, light GBM regressor, and XGBoost regressor, the model achieves remarkable RMSE values which are 12.84, 11.61, 12.34, 13.04 in birth weight prediction and provides valuable insights into fetal growth and potential risk factors for delivery. Moreover, in terms of normal, suspicious, and pathological working conditions, a robust majority voting prediction algorithm is built using a combination of DNN, ANN, and CNN to assign the final labels, and the model can obtain macro-impressive accuracy scores which are 87.79, 94.13, 93.42% on testing datasets. Millions of babies die within the first 24 h after birth, and with alarming maternal mortality rates, prenatal care is essential. This effort will focus on CTG, the most common method of adoption, so keep an eye on fetal well-being. By analyzing the patterns captured in the data, the model effectively differentiates fetal health conditions, enabling early medical intervention whenever needed. This project represents a major advance in the application of machine learning in prenatal care.