EUVIMEDTutustu EUVIMEDiin
Systematische ÜbersichtOpen access

Opportunities and Challenges of Using Artificial Intelligence in Predicting Clinical Outcomes and Length of Stay in Neonatal Intensive Care Units: Systematic Review

Chancen und Herausforderungen des Einsatzes künstlicher Intelligenz zur Vorhersage klinischer Outcomes und der Verweildauer in neonatalen Intensivstationen: systematische Übersicht

Samantha Tudor iD, Risha Bhatia iD, Michael Liem iD, Tafheem Ahmad Wani iD, James Boyd iD, Urooj Raza Khan iD

Journal of Medical Internet Research · 2025-10-03 · 27 · e63175

DOI: 10.2196/63175 ↗

Auf einen Blick

24 Studien zeigen, dass KI in NICUs für Vorhersagemodelle, medizinische Bildgebung und Risikostratifizierung Potenzial hat. Eine vollständige Integration in die Versorgung wurde nicht berichtet.

Fragestellung

Welche Forschung zu KI für die Vorhersage klinischer Outcomes und der Verweildauer bei NICU-Patient:innen liegt vor, und welche Chancen und Herausforderungen werden beschrieben?

Methode

Systematische Übersicht in 6 Datenbanken; englischsprachige begutachtete Artikel von Januar 2017 bis März 2023; thematische Analyse.

Ergebnisse

24 Studien: 15 retrospektiv, 9 prospektiv. Untersucht wurden Komorbiditäten (18/24), Mortalität (4/24) und Verweildauer (2/24). 16 Studien waren explorativ, 8 systematisch explorativ.

Einschränkungen

Methodische Heterogenität, kleine Stichproben, Verzerrungsrisiko und fehlende externe Validierung.

Schlussfolgerung der Autor:innen

Die Übersicht sieht Potenzial von KI für die NICU-Versorgung, verweist aber auf deutliche methodische Grenzen und eine fehlende Einbettung in die klinische Praxis.

Kernaussagen

  • KI wurde vor allem für Komorbiditäten, Mortalität und Verweildauer untersucht.
  • Keine Studie berichtete ein vollständig integriertes KI-System.
  • Herausforderungen: Datenqualität, Generalisierbarkeit und Ethik.

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Systematische Übersicht in Journal of Medical Internet Research, published online on 2025-10-03. Written by Samantha Tudor and 5 co-authors. Institution: La Trobe University, Melbourne, Australia. Major MEDLINE topics: Intensive Care Units, Neonatal, Artificial Intelligence, Length of Stay. Cited 17 times so far (Crossref); 95 references. The full text is freely available in PubMed Central.

Auf einen BlickTiivistelmäSubjectsBibliografiset tiedotCiteRelated studies

Abstract (original language)

Background

The use of artificial intelligence (AI) in health care has been steadily increasing for over 2 decades. Integrating AI into neonatal intensive care units (NICUs) has promise as it has the potential to reshape neonatal care and improve outcomes. However, challenges such as data quality, clinical interpretation, and ethical considerations may hinder AI’s practical implementation in NICUs.

Objective

This study aims (1) to analyze the current AI research landscape for predicting clinical outcomes and length of stay in the NICU and (2) to explore the benefits and challenges of using AI in the NICU for these predictions.

Methods

A systematic review was conducted across 6 databases—PubMed, Embase, CINAHL, Cochrane Library, Informit, and La Trobe Library—to identify English-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 patients. Eligibility criteria excluded studies outside the NICU context or lacking predictive focus. Both prospective and retrospective designs were included. A thematic analysis of AI applications in NICUs from the articles identified was conducted.

Results

A total of 24 studies were included in the review, comprising 15 retrospective and 9 prospective designs. These studies primarily originated from the United States (13 studies), with others from Austria, Taiwan, and other countries. The studies evaluated AI applications in NICU settings to predict comorbidities (18/24), mortality (4/24), and length of stay (2/24). Sixteen studies were in the exploration stage, lacking cohesive AI strategies, while 8 demonstrated systematic exploration but no fully integrated solutions. The synthesis of results identified key applications of AI in NICU care, including data-driven insights and predictive models, advancements in medical imaging, improved risk stratification, and personalized neonatal care. AI showed promise in enhancing diagnostic accuracy and care planning, but significant challenges persist, such as data quality, model generalization, and ethical concerns. No studies reported a fully integrated AI ecosystem, highlighting the need for further research to bridge gaps and realize AI’s transformative potential in neonatal care.

Conclusions

This review highlights the potential of AI in improving NICU care, particularly through predictive models, medical imaging, and personalized interventions. However, the evidence is limited by significant methodological variability, small sample sizes, risk of bias, and a lack of external validation in included studies. Many studies remain in exploratory phases without cohesive AI strategies or integration into clinical practice, limiting the practical applicability of findings. These results underscore the importance of addressing challenges such as data quality, model generalization, and ethical considerations to fully realize AI’s potential in neonatal care. Future research should focus on robust validation, comprehensive implementation strategies, and ethical frameworks to ensure AI's effective and responsible integration into NICU settings.

Subjects

MeSH terms (MEDLINE)

Intensive Care Units, NeonatalArtificial IntelligenceLength of StayHumansInfant, Newborn

Author keywords

NICUartificial intelligenceclinical outcomesdeep learninglength of staymachine learningneonatal intensive care unitpredictive modelingsystematic review

Authors and institutions

  • La Trobe University, Melbourne, Australia.
  • Monash University, Melbourne, Australia.

ORCID profiles: Samantha Tudor, Risha Bhatia, Michael Liem, Tafheem Ahmad Wani, James Boyd, Urooj Raza Khan

Cite

APA

Tudor, S., Bhatia, R., Liem, M., Wani, T. A., Boyd, J., & Raza Khan, U. (2025). Opportunities and Challenges of Using Artificial Intelligence in Predicting Clinical Outcomes and Length of Stay in Neonatal Intensive Care Units: Systematic Review. Journal of Medical Internet Research, 27, e63175. https://doi.org/10.2196/63175

Vancouver

Tudor S, Bhatia R, Liem M, Wani TA, Boyd J, Raza Khan U. Opportunities and Challenges of Using Artificial Intelligence in Predicting Clinical Outcomes and Length of Stay in Neonatal Intensive Care Units: Systematic Review. Journal of Medical Internet Research. 2025;27:e63175. doi:10.2196/63175

BibTeX
@article{Tudor2025,
  author = {Tudor, Samantha and Bhatia, Risha and Liem, Michael and Wani, Tafheem Ahmad and Boyd, James and Raza Khan, Urooj},
  title = {Opportunities and Challenges of Using Artificial Intelligence in Predicting Clinical Outcomes and Length of Stay in Neonatal Intensive Care Units: Systematic Review},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e63175},
  doi = {10.2196/63175}
}
Start for free →