Abstract:
This Research Aims to evaluate and predict the effects faced by women during maternity diagnosed with GDM. Adverse perinatal outcomes encompass multiple factors experienced during or after pregnancy and have a major impact on maternal and neonatal health. Timely identification and treatment can save major adverse outcome to occur. In recent years multiple issues are faced by women during the gestation period. Major outcomes may include but not limited to preterm or post-term delivery, shoulder dystocia, large or small at gestation period and fetal APGAR score measured multiple times after delivery. All above mentioned outcomes will be treated as dependent variables which have direct association with the other independent variables. Other independent variables which becomes the cause of these adverse effects also not limited to maternal age, height, weight resulted into BMI, obesity, ethnicity, previous obstetric history, parity, gravida, glucose tolerance test, folic acid dose, gestational diabetes and estimated total blood loss. The purpose behind this is to make an effective model which can determine the outcome and by analyzing the outcome the proactive measures can be taken on time to save any kind of maternal or neonatal casualty to occur. For this purpose, multiple techniques or prediction models are used. The objective of this research is to evaluate and predict the adverse effects experienced by women diagnosed with gestational diabetes mellitus (GDM) during maternity. The study aims to comprehensively assess adverse perinatal outcomes, which are influenced by various independent variables mentioned. By utilizing artificial intelligence (AI) techniques, the research seeks to develop an effective predictive model capable of analyzing multiple independent variables to accurately determine adverse outcomes. The ultimate goal is to facilitate timely identification and intervention to prevent maternal and neonatal casualties associated with GDM, thereby improving maternal and neonatal health outcomes.
