Transforming neonatal care through informatics: A review of artificial intelligence, data, and implementation considerations

Authors

Robert Barrett, Biomedical Informatics and Data Science, Johns Hopkins University, Baltimore, MD, United States.
Brooke Lawler, Biomedical Informatics and Data Science, Johns Hopkins University, Baltimore, MD, United States.
Star Liu, Biomedical Informatics and Data Science, Johns Hopkins University, Baltimore, MD, United States.
Woo Yeon Park, Biomedical Informatics and Data Science, Johns Hopkins University, Baltimore, MD, United States.
Marjan Davoodi, Biomedical Informatics and Data Science, Johns Hopkins University, Baltimore, MD, United States.
Ben Martin, Biomedical Informatics and Data Science, Johns Hopkins University, Baltimore, MD, United States.
Sai Manasa Kalyanam, Department of Pediatrics, Johns Hopkins University, Baltimore, MD, United States.
Kartikeya Makker, Department of Pediatrics, Johns Hopkins University, Baltimore, MD, United States.
Jordan R. Kuiper, Department of Environmental & Occupational Health, George Washington University, Washington, DC, United States.
Khyzer B. Aziz, Biomedical Informatics and Data Science, Johns Hopkins University, Baltimore, MD, United States; Department of Pediatrics, Johns Hopkins University, Baltimore, MD, United States. Electronic address: kaziz5@jhmi.edu.

Document Type

Journal Article

Publication Date

9-18-2025

Journal

Seminars in perinatology

DOI

10.1016/j.semperi.2025.152144

Keywords

Artificial intelligence; Data; Informatics; Learning health system; Neonatal; Networks; Outcomes

Abstract

Significant strides have been made in utilizing data, information, and knowledge to enhance neonatal outcomes. This review examines how data informatics, encompassing electronic health records (EHRs), data standards, and artificial intelligence (AI), has facilitated advancements in neonatal care and research. Vast amounts of data, structured and unstructured, have been produced from clinical care. In turn AI stands to improve patient care, safety, and quality improvement initiatives. Facilitated by AI, clinicians' interaction with neonatal informatic tools is transitioning from reactive to real-time, proactive care. Historically, necrotizing enterocolitis, sepsis, medical imaging, and neonatal mortality have been the targets of AI-integrated neonatal care. While much progress has been made in developing state-of-the-art AI tools, their development and implementation must consider optimization of patient care, clinical workflows, and aim to decrease clinician burnout. Employing a sociotechnical framework to assess both technical and human factors is key to effectively evaluating clinical utility, promoting adoption, and facilitating successful deployment. Beyond technical concerns, ethical considerations such as trust in AI, data security, and model transparency are critical to the responsible deployment of informatics tools. Ongoing advancements in neonatal care coupled with informatics, multi-omics, AI, and federated learning expands the possibilities of personalized care for neonates.

APA Citation

Barrett, Robert; Lawler, Brooke; Liu, Star; Park, Woo Yeon; Davoodi, Marjan; Martin, Ben; Kalyanam, Sai Manasa; Makker, Kartikeya; Kuiper, Jordan R.; and Aziz, Khyzer B., "Transforming neonatal care through informatics: A review of artificial intelligence, data, and implementation considerations" (2025). GW Authored Works. Paper 7934.
https://hsrc.himmelfarb.gwu.edu/gwhpubs/7934

Department

Environmental and Occupational Health