AI in Robotic-assisted Pediatric Surgery: Current Applications and Future Directions

Le résumé fourni par la source

Background: Artificial intelligence (AI) is increasingly integrated into surgical practice, offering enhanced decision-making, precision, and workflow efficiency. In pediatric surgery, the convergence of AI and robotic-assisted platforms represents a promising frontier, addressing the unique anatomical, physiological, and technical challenges of operating on children. Aim of this review is to provide an overview of the current state of art of AI use in pediatric robotic-assisted surgery (RAS), outlining the available evidence, potential benefits, existing limitations, and prospective developments. Materials and Methods: A literature-based search of PubMed and Scopus was performed to identify articles covering any aspect of AI application in pediatric RAS. Selection criteria included English language, pediatric patients (under 18 years of age), and AI application to pediatric RAS. Additionally, studies reporting AI applications in adult RAS or for surgical training, which were not primarily focused on pediatric surgery but presented potential translational applicability to pediatric RAS, were considered. Results: A total of 746 papers published until July 2025 were collected. A total of 15 full-text articles were assessed for eligibility, meeting the inclusion criteria. The other studies were excluded because they did not address pediatric surgery, did not involve robotic-assisted procedures, or did not include applications of AI. Conclusion: Although RAS is well established in pediatric practice, the direct application of AI remains limited, with AI-like features such as machine vision and augmented reality serving mainly as supportive tools rather than autonomous decision-making systems. Nevertheless, emerging AI-like technologies and ongoing research hold promising potential for future applications in pediatric robotic surgery.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.