BIRTH WEIGHT PREDICTION

Birth weight is a significant predictor of long-term results and a vital sign of neonatal health. Through the identification of pregnancies at risk and the facilitation of prompt treatments, accurate birth weight prediction can improve prenatal care. This study investigates many approaches to birth weight prediction, ranging from sophisticated machine learning methods to conventional statistical models. We examine variables related to prenatal care, gestational age, and maternal characteristics that affect birth weight. We evaluate the effectiveness of ensemble techniques, neural networks, and regression models using a large dataset. According to our research, machine learning models perform better in terms of predicted accuracy and resilience than conventional methods—especially when they make use of ensemble techniques. The use of these prediction models in clinical settings can enhance the quality of prenatal care and the outcomes for newborns by enabling medical plans that are specific to each patient's risk profile. Future studies should concentrate on improving these models using bigger, more varied datasets and adding more pertinent variables to increase their prediction potential.