Prediction of Infant Death in Incubator using Machine Learning Techniques

Deaths in incubator is a major problem worldwide which is the leading cause of death in infants. Early diagnosis of infant death in an incubator helps to improve the survival chances of neonatal babies in an infant incubator. Early diagnosis of death in an incubator can save the infant or treat him/her better than standard treatment. In this paper we proposed a different ML algorithm to predict infant death in an incubator. This research was carried out in the Satara district, Maharashtra. In this study, we have taken factors that were identified by medical professionals for infant incubation. The machine learning algorithms can help medical professionals to predict infant deaths in an incubator as well as identify factors that cause the death of the infant in the incubator. The various data imbalancing techniques, such as the synthetic oversampling technique (SMOTE) and adaptive synthetic (ADYSN) have been implemented to improve the performance of models. The XG Boost classifier (F1 score = 0.88) and Random Forest classifier (F1 score = 0.89) with ADYSN give us the better performance than other classifiers.