Neonatal Intensive Care Decision Support Systems Using Artificial Intelligence Techniques: A Systematic Review Publisher



Malak JS¹ ; Zeraati H² ; Nayeri FS³ ; Safdari R¹ ; Shahraki AD¹ Show Affiliations
Source: Artificial Intelligence Review Published:2019

Abstract

A neonatal intensive care unit (NICU) provides critical services to preterm and high-risk infants. Over the years, many tools and techniques have been introduced to support the clinical decisions made by specialists in the NICU. This study systematically reviewed the different technologies used in neonatal decision support systems (DSS), including cognitive analysis, artificial neural networks, data mining techniques, multi-agent systems, and highlighted their role in patient diagnosis, prognosis, monitoring, and healthcare management. Articles on NICU DSS were surveyed, Searches were based on the PubMed, Science Direct, and IEEE databases and only English articles published after 1990 were included. The overall search strategy was to retrieve articles that included terms that were related to “NICU Decision Support Systems” or “Artificial Intelligence” and “Neonatal”. Different methods and artificial intelligence techniques used in NICU decision support systems were assessed and related outcomes, variables, methods and performance measures was reported and discussed. Because of the dynamic, heterogeneous, and real-time environment of the NICU, the processes and medical rules that are followed within a NICU are complicated, and the data records that are produced are complex and frequent. Therefore, a single tool or technology could not cover all the needs of a NICU. However, it is important to examine and deploy new temporal data mining approaches and system architectures, such as multi-agent systems, services, and sensors, to provide integrated real-time solutions for NICU. © 2018, Springer Science+Business Media B.V., part of Springer Nature.