Smart Fetal Growth Monitoring, Real -Time Weight Prediction in High-Risk Pregnancies.
[1] Deepika R S, [2] Mrs. Deepthi C G, [3] Bhuvan M, [4] Anusha K H, [5] Deekshith Chandra
[1] Information and Science and Engineering, Malnad College of Engineering Hassan-573202, India
[2] Assistant Professor, Information and Science and Engineering, Malnad College of Engineering Hassan-573202, India
[3] Information and Science and Engineering, Malnad College of Engineering Hassan-573202, India
[4] Information and Science and Engineering, Malnad College of Engineering Hassan-573202, India
[5] Information and Science and Engineering, Malnad College of Engineering Hassan-573202, India
Email id: deepikars168@gmail.com, dcg@mcehassan.ac.in, bhuvibhuvan1624@gmail.com, anushaharish48@gmail.com, deekshithchandra09@gmail.com
Abstract— The newborn's low birth weight is one of the most important issues in prenatal care since it can negatively impact the infant's health and, in more severe cases, even result in its death. It is also because of this reason that infant mortality rates show higher numbers all around the globe. Methods of artificial intelligence, especially those based on machine learning (ML), can predict health problems that may occur at birth as well as for the whole duration of gestation. Therefore, our study proposes to study some machine learning (ML) techniques which could be employed to predict if a fetus would be born weighing less than what is expected for its gestational age. The importance of identifying fetal development problems early on is emphasized by the possibility of extending gestation days through timely intervention. Using such an intervention, a decrease in infant morbidity and death would result from the potential to raise fetal weight at birth. Therefore, in this research, we will forecast the fetal birth weight at an early stage and classify them as low weight if their weight is less than 2.5 kg, normal weight if their weight is more than 2.5 kg but less than 4.5 kg, and abnormal weight if their weight is more than 4.5 kg. We will use machine learning techniques and algorithms to estimate the fetal birth weight; in this case, the algorithm will be chosen based on the accuracy achieved by them in the studies we have conducted. Finally, we chose the Random Forest and Linear Regression.
Keywords: random forest, linear regression, neonatal morbidity, gestational age, and infant death rates.
