Prior Prediction and Classification of Low Birth Weights (LBW) Using Machine Learning

Low birth weight (LBW) is a significant global issue with various associated dangers. LBW is an important determinant of neonatal health, affecting infant mortality and long-term outcomes. There is a strong correlation between maternal well- being during pregnancy and childbirth weight. The study of machine learning techniques for classification tasks, which effectively discriminates between LBW and NOT-LBW cases. The project's primary goal is to achieve precise predictions of LBW cases through the application of various machine learning algorithms, including XGBoost, Random Forest, Decision Trees, and SVM. These models will undergo training using supervised datasets, enabling a comparative analysis to identify the most accurate predictor among them. Along with increased accuracy, this study includes creating a flexible web interface aimed at medical professionals and the public, which allows for ideal data input to predict LBW probability. The Proposed methodology aims to contributes to obstetrics and gynecology by addressing the challenge of the lack of comprehensive medical tests for LBW and promoting early intervention for LBW in the healthcare domain.