How could artificial intelligence aid clinicians caring for preterm neonates with respiratory pathology?
- 1Department of Paediatrics, University of Oxford, Oxford, United Kingdom.
Abstract
Artificial intelligence (AI) presents an opportunity to transform neonatal care. By rapidly assimilating large volumes of complex, multi-dimensional data to produce real-time predictions, machine learning (ML) models have the potential to enable personalised monitoring and treatment and earlier intervention. This narrative review aims to provide clinicians with a foundational overview of AI and its potential role in the care of preterm infants, with a particular focus on respiratory pathologies. We introduce different types of AI tools and ways to assess predictive model performance. We summarise existing literature using AI and conventional predictive models to predict respiratory conditions, including extubation readiness, bronchopulmonary dysplasia, and apnoea occurrence and risk. Finally, we discuss current limitations of AI in neonatology, barriers to clinical translation and the next steps needed to overcome them. These may include multicentre collaboration and data sharing, using dynamic inputs such as vital signs to reflect evolving physiology, and improved transparency, accessibility and training for clinicians, as well as clear guidelines for clinical application, accountability and ongoing monitoring.
Related
- Digital health and artificial intelligence in paediatric respiratory medicine: what clinicians need to know and what is coming next
- Effectiveness and user experience of ambient artificial intelligence-driven scribe technology among clinicians: a protocol for a systematic review.
- The Use of Artificial Intelligence in Creating Educational Material for Critical Care Clinicians: A Survey.
- Bridging the Artificial Intelligence Translation Gap in Perioperative Pulmonary and Respiratory Complications: A Practical Framework for Institution-Level Implementation
- Identification of adventitious lung sounds in children with respiratory illnesses in Bangladesh using artificial intelligence and digital auscultation
BibTeX
@article{ketheeswaranathan2026could,
title = {{How could artificial intelligence aid clinicians caring for preterm neonates with respiratory pathology?}},
author = {Vithushanan Ketheeswaranathan and Surina Fordington and Caroline Hartley},
journal = {Frontiers in pediatrics},
year = {2026},
month = oct,
doi = {10.3389/fped.2026.1885589},
url = {https://europepmc.org/article/MED/42948079},
note = {CC BY},
}
RIS
TY - JOUR
TI - How could artificial intelligence aid clinicians caring for preterm neonates with respiratory pathology?
AU - Vithushanan Ketheeswaranathan
AU - Surina Fordington
AU - Caroline Hartley
PY - 2026
DA - 2026/10/13
JO - Frontiers in pediatrics
DO - 10.3389/fped.2026.1885589
UR - https://europepmc.org/article/MED/42948079
AB - Artificial intelligence (AI) presents an opportunity to transform neonatal care. By rapidly assimilating large volumes of complex, multi-dimensional data to produce real-time predictions, machine learning (ML) models have the potential to enable personalised monitoring and treatment and earlier intervention. This narrative review aims to provide clinicians with a foundational overview of AI and its potential role in the care of preterm infants, with a particular focus on respiratory pathologies. We introduce different types of AI tools and ways to assess predictive model performance. We summarise existing literature using AI and conventional predictive models to predict respiratory conditions, including extubation readiness, bronchopulmonary dysplasia, and apnoea occurrence and risk. Finally, we discuss current limitations of AI in neonatology, barriers to clinical translation and the next steps needed to overcome them. These may include multicentre collaboration and data sharing, using dynamic inputs such as vital signs to reflect evolving physiology, and improved transparency, accessibility and training for clinicians, as well as clear guidelines for clinical application, accountability and ongoing monitoring.
SN - 2296-2360
ER -