Abstract
Artificial intelligence (AI), especially deep learning techniques, is revolutionizing neonatal neuroimaging by significantly improving the detection and prognostic evaluation of hypoxic-ischemic encephalopathy (HIE), a major contributor to neonatal morbidity and mortality. This systematic review integrates findings from five high-quality, peer-reviewed studies published between 2015 and 2025, identified through comprehensive searches of PubMed, Embase, Scopus, and the Cochrane Library. The review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and applied the Newcastle-Ottawa Scale (NOS), Risk of Bias 2 (RoB 2), and Assessment of Multiple Systematic Reviews 2 (AMSTAR 2) tools to ensure methodological rigor and minimize bias. AI algorithms, especially convolutional neural networks (CNNs), have shown high effectiveness in identifying brain injuries associated with HIE, with sensitivity ranging from 83% to 95% and specificity between 86% and 93%. These models frequently outperform conventional radiological assessments in diagnostic accuracy. These models also reduced interpretation time by up to 47%, streamlining critical care workflows. Prognostic AI tools showed 77-87% accuracy in predicting long-term neurodevelopmental outcomes, aiding in early clinical interventions and family guidance. Despite these promising results, limitations such as small sample sizes (n = 100-200), heterogeneous MRI protocols, and high computational demands hinder broader clinical application. Standardized imaging, multi-center collaboration, and explainable AI models are crucial for clinical scalability. Moreover, successful integration of AI into neonatal intensive care units (NICUs) requires rigorous validation, ethical oversight, and clinician training to ensure safety, transparency, and trust. Collaborative efforts between neonatologists, radiologists, data scientists, and policymakers will be essential to align AI innovations with patient-centered care. As this technology matures, it holds significant potential to improve diagnostic precision, optimize clinical outcomes, and reduce disparities in neonatal neurological care.