Current State and Future of Artificial Intelligence in Pediatric Interventional Radiology: A Narrative Review

Area of Science:

• Radiology
• Pediatric Interventional Radiology
• Artificial Intelligence

Background:

• Artificial intelligence (AI) is transforming diagnostic radiology, yet its application in pediatric interventional radiology (PIR) is underdeveloped.
• PIR presents unique challenges, including radiation sensitivity and anatomical variability, alongside a rich data environment.

Purpose of the Study:

• To review the current state of AI technologies relevant to PIR.
• To outline future perspectives for clinical integration of AI in PIR.

Main Methods:

• A narrative review synthesizing peer-reviewed literature and position statements up to Q1 2026.
• Literature search across MEDLINE/PubMed, Embase, Scopus, and major society publications.

Main Results:

• AI applications span dose reduction, image interpretation, procedural planning, and risk prediction in PIR.
• Pediatric-specific challenges like data scarcity and regulatory hurdles are identified.
• Emerging AI paradigms include explainable AI, federated learning, and multimodal integration.

Conclusions:

• AI holds potential for enhancing PIR patient care but requires specific design, validation, and deployment for children.
• Current AI tools show feasibility but lack strong links to pediatric clinical endpoints.
• Addressing evidence gaps and prioritizing research are crucial for safe and effective AI adoption in PIR.