Artificial intelligence (AI), specifically a branch of AI called deep learning (DL), has proven revolutionary developments in almost all fields, from computer vision to health sciences, and its effects in medicine have changed clinical applications significantly. Although some sub-fields of medicine such as pediatrics have been relatively slow in receiving critical benefits of AI, related research in pediatrics started to be accumulated to a significant level too. Hence, in this paper, we review recently developed machine learning and deep learning based systems for neonatology applications. We systematically evaluate the role of AI in neonatology applications, define the methodologies, including algorithmic developments, and describe the remaining challenges in neonatal diseases. To date, survival analysis, neuroimaging, EEG, pattern analysis of vital parameters, and retinopathy of prematurity diagnosis with AI have been the main focus in neonatology. We have categorically summarized 96 research articles, from 1996 to 2022, and discussed their pros and cons, respectively. We also discuss possible directions for new AI models and the future of neonatology with the rising power of AI, suggesting roadmaps for integration of AI into neonatal intensive care units.

翻译：人工智能，特别是其子领域深度学习，已在从计算机视觉到健康科学等几乎所有领域展现出革命性进展，其在医学领域的影响显著改变了临床应用实践。尽管儿科学等医学分支领域在接收人工智能关键技术红利方面相对滞后，但相关儿科学研究也已积累至相当水平。因此，本文系统综述了近年来基于机器学习和深度学习的新生儿医学应用系统。我们系统评估了人工智能在新生儿医学应用中的角色，界定了包括算法发展在内的技术方法，并阐述了新生儿疾病领域现存挑战。迄今，新生儿医学领域的研究重点集中于生存分析、神经影像学、脑电图、生命体征模式分析以及基于人工智能的早产儿视网膜病变诊断。我们对1996年至2022年间发表的96篇研究论文进行了分类总结，分别论述了各研究的优缺点。同时，探讨了新型人工智能模型的可能发展方向，以及人工智能崛起背景下新生儿医学的未来前景，提出了将人工智能整合至新生儿重症监护室的路线图建议。