Risk prediction with machine learning in cesarean section: Optimizing healthcare operational decisions

Abstract

In recent years, data mining is becoming very popular in healthcare and medical research. With its enormous library and a large number of machine learning (ML) algorithms, it is being used for the complex, multidimensional and large data in healthcare systems. Cesarean section or C-section is the widely used method when any abnormality affects the normal birth of a child. The aim of this research is to identify the cesarean section of child birth by considering some important situations of pregnant women using different ML algorithms. In this situation, several data imbalanced techniques were implemented in the cesarean data. Then, various classifiers were applied to the derived balanced and base cesarean sample. After applying ML classifiers, we have received a success rate over 95%.