A QUALITATIVE LITERATURE REVIEW OF MACHINE LEARNING TECHNIQUES USED FOR DIAGNOSIS OF NEONATAL DISEASES IN HEALTHCARE

Abstract

Background:There has been signicant growth in the use of Articial Intelligence (AI) for healthcare in the last decade. Aim: To identify effective AI techniques for the prediction & diagnosis of neonatal diseases and preventive measures & treatment plan for them. Neonates are newborn babies less than a month old. Methods:Research papers published in databases like IEEE Xplore, Medline, PUBMED and Elsevier were searched to nd publications reporting the application of AI for the prediction and prevention of neonatal diseases. The overall search strategy was to retrieve articles that included terms that were related to “NICU”, “Articial Intelligence”, “Neonatal diseases” and “Healthcare”. Results: Hundreds of papers were identied in initial search, out of which 13 publications met the evaluation criteria of related terms inclusion, AI for Neonatal Diseases in particular. These papers described application of AI techniques in neonatal healthcare for disease detection and were summarized for nal analysis. Most of the papers are focused on using supervised machine learning techniques for the prediction of diseases. Various other approaches in AI techniques used in neonatal disease diagnosis have been tested for related ndings, factors, methods, to address and document performance metrics. The comparative analysis of ML model evaluation parameters like AUC (Area under Curve), Specicity, Sensitivity, True Positive and False-negative Rates was done to develop the scope for improving performance of AI/MLtechniques. Conclusion: The systematic study and review of different AI techniques such as supervised machine learning; articial neural networks, data mining techniques used for neonatal disease diagnosis highlighted their role in disease prediction, management, and treatment plan. More studies are needed to improve the use of AI for timely prediction of neonatal diseases like respiratory distress syndrome, sepsis for increasing the survival chances in preterm or normal neonates. The supervised learning models like Support Vector Machines(SVM), Decision Trees, K nearest neighbors are found to be effective for neonatal disease detection and will be applied in future research.