Related Experiment Video
Updated: May 5, 2026
Use of Electron Paramagnetic Resonance in Biological Samples at Ambient Temperature and 77 K
Published on: January 11, 2019
Artificial Intelligence Implementation in Pediatric Radiology for Patient Safety: A Multisociety Statement From the
Susan C Shelmerdine1, Jaishree Naidoo2, Brendan S Kelly3
1Department of Clinical Radiology, Great Ormond Street Hospital for Children, London, UK; UCL Great Ormond Street Institute of Child Health, Great Ormond Street Hospital for Children, London, UK; National Institute for Health and Care Research Great Ormond Street Hospital Biomedical Research Centre, Bloomsbury, London, UK.
Artificial intelligence (AI) offers great potential in pediatric radiology. This position statement outlines a child-centered framework for safe AI integration, emphasizing tailored regulation, implementation, and education for children's unique needs.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence
Background:
- Current AI in radiology primarily serves adults, neglecting children's distinct physiological and developmental needs.
- Safe and effective AI integration in pediatric radiology requires specialized approaches.
- A multisociety position statement addresses critical pillars for AI adoption in pediatrics.
Purpose of the Study:
- To propose a child-centered framework for the adoption of artificial intelligence in pediatric radiology.
- To outline specific recommendations for regulation, implementation, interpretation, and education of AI tools for pediatric use.
- To ensure the safety, accuracy, and well-being of children when using AI in medical imaging.
Main Methods:
- Systematic review and position statement development by multiple societies.
- Proposal of pediatric-specific safety ratings, diverse datasets, transparency metrics, and explainability.
- Recommendation of a phased implementation strategy with pilot testing and continuous postmarket surveillance.
- Emphasis on foundational AI literacy and specialized training for healthcare professionals.
Main Results:
- Advocacy for pediatric-specific safety ratings and diverse datasets to mitigate bias.
- Recommendations for phased implementation, stakeholder engagement, and robust postmarket surveillance.
- Highlighting the necessity of AI literacy and specialized training for healthcare professionals.
- Stress on public and patient engagement for AI acceptance in pediatric radiology.
Conclusions:
- A child-centered framework is essential for integrating AI in pediatric radiology.
- Prioritizing children's unique needs ensures the safe and effective use of AI in medical imaging.
- Tailored regulation, implementation, and education are crucial for successful AI adoption in pediatric radiology.
