Fetal Health Classification and Visceral Fat Level Prediction using Gradient Boosting and Deep Learning Techniques

Maternal wellness is paramount in healthcare, with a focus on predicting fetal health risks and visceral fat levels being of utmost significance. This research endeavors to integrate machine learning, deep learning, and ensemble techniques to develop predictive models for fetal health risk identification (categorized as normal, suspect, and pathological) and visceral fat level prediction. Through exhaustive experimentation with a range of machine learning and deep learning methodologies, the most accurate models for each prediction category are identified. The importance of this work lies in its potential to enhance prenatal care by providing timely assessments of fetal health risks and enabling proactive interventions. Moreover, predicting visceral fat levels contributes to maternal health management, aiding in the prevention of complications such as gestational diabetes and hypertension. Ultimately, this research offers a comprehensive approach to maternal-fetal health monitoring, promising improved outcomes for both mother and child.