A Systematic Approach for Effective Apgar Score Assessment in 1 and 5 min Using Manifold Machine Learning Algorithms

The Apgar score was first introduced by Dr. Virginia Apgar in 1952, and its mainly used to find the well-being of newborn infants by using the five important aspects such as heartbeat, reflex irritation, color, muscle tone, and respiration. Apgar was an assessment tool that is performed at 1 and 5 min of a child’s birth. There is a potential impact of the score on medical decision making and providing care to newborn infants. Since a low Apgar score results in harmful interventions. So here in this research paper, the analysis and comparison of R2 Score of various machine learning algorithm models is done. Here, this comparison mainly focuses on improving the R2 score of the Apgar value. Additionally, the use of the Apgar score is a very important subject in terms of research and discussion among healthcare professionals. The Apgar score has also been evaluated in various populations including preterm infants and newborns with congenital anomalies. This research paper has analyzed the comparison of 13 different machine learning algorithms and the R2 Score was obtained as 96.5% for the hybrid approach. So, utilizing machine learning to predict the Apgar score will increase R2 Score, boost neonatal research and help us better understand the physiology and health of newborns.