JMIR Publications

ABSTRACT

Background:

The use of Artificial Intelligence (AI) in healthcare has been steadily increasing for over two decades. Integrating AI into Neonatal Intensive Care Units (NICUs) has the potential to reshape neonatal care and improve outcomes.

Objective:

To analyse the current AI research landscape for predicting clinical outcomes and length of stay in the NICU, and to explore the benefits and challenges of utilising AI in the NICU for these predictions.

Methods:

A rapid review was conducted across 6 databases, PubMed, Embase, CIHANL, Cochrane Library, Informit, and La Trobe Library, to identify Englished-language peer reviewed articles published between January 2017 and March 2023 that focused on the use of AI for predicting length of stay and clinical outcomes for NICU patient. A thematic analysis of AI application in NICUs from the articles identified was conducted.

Results:

A total of 24 articles were included in the review, with AI applied in NICU settings to predict comorbidities (18/24), mortality (4/24), and length of stay (2/24). Sixteen of the studies were in the exploration stage, lacking a cohesive AI strategy, while the remaining eight were in the emerging stage, where the exploration of AI had been conducted systematically. None of the studies reported a fully integrated AI solution in a NICU setting. This review also identified several critical challenges, including data quality, clinical interpretability, model generalisation, and ethical considerations. Despite the lack of maturity and the challenges of AI in the NICU, the thematic analysis revealed four themes of potential AI application in enhancing NICU care: data-driven insights and predictive models, advancements in medical imaging, improved risk stratification, and personalised neonatal care and interventions.

Conclusions:

AI provides opportunities, particularly in medical imaging and data-driven insights, offering the potential for improved diagnostic accuracy and personalised care. Data quality and ethical considerations are challenges to be addressed. Bridging these gaps can harness the transformative potential of AI to enhance neonatal care and healthcare delivery. Future research should prioritise practical implementation and ethical guidelines to fully realise the benefits of AI in the NICU.