A Machine Learning Approach Using Statistical Models for Early Detection of Cardiac Arrest in Newborn Babies in the Cardiac Intensive Care Unit

An alarming yet typical medical emergency is cardiac arrest in newborn infants. Providing these babies with optimal care and treatment necessitates early detection as a critical factor. Identifying potential indicators and biomarkers of cardiac arrest in newborn infants and developing accurate, efficient diagnostic tools for early detection has been the focus of recent research endeavors. Early detection of cardiac arrest may be facilitated by an array of imaging techniques, including echocardiography and computed tomography. This project aims to develop a Cardiac Machine Learning model (CMLM) employing statistical models for the early detection of cardiac arrest in newborn babies admitted to the Cardiac Intensive Care Unit (CICU). A combination of the neonate's physiological parameters was utilized to identify the cardiac arrest events. Predictive models for cardiac arrest were constructed using statistical modeling techniques such as logistic regression and support vector machines.