Support vector machines in neonatal mortality detection: a comprehensive scoping review with disease-specific emphasis

Neonatal mortality is a widely significant problem since diseases such as sepsis, apnea and jaundice have claimed the lives of 2.3 million neonates in 2021. As such, better tools need to be developed to reduce its rate. While traditional methods like Clinical risk index (CRIB) and Score for neonatal acute physiology (SNAP) have proven helpful in predicting neonatal mortality, there is a need for more efficient measures. One such approach is support vector machine (SVM), a supervised machine-learning algorithm that is primarily used for classification. SVM can perform both linear and non-linear classification; it conducts the latter with the assistance of the kernel trick and functions such as polynomial, gaussian, RBF and sigmoid functions. This narrative review aims to explore the potential and limitations of SVM in predicting major global causes of neonatal mortality. We searched through articles employing SVM to predict different diseases and symptoms such as sepsis, seizures, fetal heart rate, low birth weight, hypoxic-ischemic encephalopathy, apnea, jaundice and neonatal respiratory distress syndrome, and concluded that while SVM has its merits and has shown promising results in many aspects, it also has its demerits such as requiring an extensive training time to achieve higher accuracy and precision.