A Novel Approach Low Birth Weight Prediction Using Machine Learning Techniques

Abstract

In new-born babies, low birth weight (LBW) serves as a sign of illness. Infant mortality and a number of other health problems later in life are both strongly correlated with LBW. Numerous studies have found a significant link between maternal health during pregnancy and birth weight. This manuscript makes use of machine learning approaches to gather pertinent data from pregnancy-related health indicators for the early identification of prospective LBW cases. In order to use supervised machine learning for LBW detection as a binary machine classification problem, the forecasting problem has been framed as a classification problem between the LBW and NOT-LBW classes. The proposed model, as expected, had improved accuracy. To create decision criteria that may be applied to predictive health care in smart cities, Indian health care data was utilised. A screening tool based on the decision model is developed to assist health care professionals in Obstetrics and Gynecology (OBG).