Prediction of a birthweight of a baby using ML Models

One of the most significant reasons to predict the birth weight of infants is to identify the health risks and obtain prompt medical interventions in advance. In that regard, this paper analyzes the possible use of machine learning techniques in predicting baby weight by using maternal, foetal, and environmental factors. This dataset contains many explanatory and response variables such as maternal age, gestational period, nutrition, medical history, and ultrasound measurements, so we will apply and compare some of the most used ML models, namely Decision Tree, XGBoost, Extra Trees, feature engineering and data preprocessing to achieve the best level of model precision. This shows that ML models provide better results than traditional statistical techniques. Hence this holds great promise for machine learning in prenatal care because of high degree of accuracy. This may help healthcare professionals in in identifying risks in terms of low birth weight or macrosomia to improve neonatal outcomes