Early Detection of Late Onset Neonatal Sepsis Using Machine Learning Algorithms

Abstract

Reducing newborn mortality by 2030 is a Sustainable Development Goals target 3.2. Neonatal sepsis is the third major cause of neonatal death after prematurity and birth asphyxia. Late-onset neonatal sepsis (LOS) refers to sepsis in neonates bet and is likely to be acquired from the environment rather than mate features are not evident in the initial stages of infection, early di Studies have shown that physiological parameters can predict L features. Clinicians can use these parameters as early warning sig and intervene earlier to prevent complications and provide e compares various machine learning algorithms to predict the ons signs, laboratory measurements, and observations captured within MIMIC III dataset. Experimental results show that adaptive boost random forest with Synthetic Minority Oversampling Technique receiver operating characteristic (AUROC) of 0.9248, 0.9245, and 0.9238, respectively, among all the algorithms evaluated using 10-fold stratified cross-validation. The soft voting classifier trained on an ensemble of the top three models predicted the onset of neonatal sepsis with an AUROC of 0.9266, accuracy of 0.8553, F1 score of 0.7829, and Matthew's correlation coefficient