Prenatal Detection of Fetal Birth Weight and Bone Density using AI and ML techniques

Prenatal Detection of Fetal Birth Weight and Bone Density using AI and ML techniques

Mr. Sudarshan G K, Ahamed Pasha, Abhishek H N, Adithya P, Nandan D

Assistant Professor, Department of Information and Science, Malnad College Of Engineering, Hassan, India. Students, Department of Information and Science, Malnad College Of Engineering, Hassan, India.

ABSTRACT

The newborn's low birth weight, which can have a detrimental effect on the infant's health and even cause its death in more extreme conditions, is one of the most critical problems in prenatal care. The high infant mortality rates observed worldwide are caused by this disorder. Artificial intelligence approaches, particularly those based on machine learning (ML), can anticipate health issues that may arise throughout the entire gestation, including at birth. As a result, our project suggests analyzing several (ML) techniques that can determine whether a fetus would be born with less weight than expected for its gestational age. The potential for an increase in gestation days through prompt intervention underlies the significance of early detection of issues related to fetal development. With such an intervention, it would be possible to increase fetal weight at birth, which would lead to a reduction in newborn morbidity and mortality. So in this project we are going to predict the fetal birth weight in early stage also classified them as low weight if weight is less than 2.5kg, normal weight if weight is greater than 2.5kg and less than 4.5kg and abnormal weight if weight is greater than

4.5kg. To estimate the fetal birth weight in this situation, we employed ML approaches and algorithms including Linear and Random Forest Regressor, with Random Forest Regressor predicting more accurately than Linear Regression

Keywords: infant mortality rates, gestational age, neonatal morbidity, Linear Regression, Random Forest Regressor.