Related Experiment Videos
Artificial intelligence in robotic urologic surgery: a scoping review
Francesco Cei1,2,3, Hossein Arang4, Ethan Layne5
1Unit of Urology, Division of Experimental Oncology, URI, Urological Research Institute, IRCCS San Raffaele Scientific Institute, Via Olgettina, 60, 20132, Milan, Italy. cei.francesco@hsr.it.
Background And Aim:
Artificial intelligence (AI) is increasingly being integrated into robotic urologic surgery. However, existing literature remains fragmented across different technological domains. This scoping review aimed to systematically map and synthesize current evidence on AI applications within robotic urologic surgery, identifying principal domains, clinical relevance, and existing limitations.
Evidence Acquisition:
A scoping review was conducted according to PRISMA-ScR guidelines. PubMed and Web of Science were searched for English-language peer-reviewed studies published between 2018 and 2024. Studies were included if they evaluated AI applications integrated into the robotic surgical workflow (computer vision, augmented reality, cognitive analytics, skill assessment, or outcomes prediction). Reviews, editorials, and non-robotic applications were excluded.
Evidence Synthesis:
Of 256 records identified, 47 met the inclusion criteria. Applications were distributed across five domains: computer vision (19%), augmented reality and navigation (15%), AI-driven objective skill assessment (30%), cognitive analytics (17%), and surgical outcomes prediction (19%). Most studies were single-center feasibility investigations. Computer vision demonstrated high technical accuracy for instrument and gesture recognition, while AI-based performance metrics showed emerging associations with clinically relevant outcomes. Augmented reality systems improved anatomical visualization and surgical planning, and cognitive analytics explored real-time workload assessment.
Conclusion:
AI in robotic urologic surgery is predominantly focused on assistive and analytical applications, particularly intraoperative image analysis and objective performance assessment. While early evidence suggests technical feasibility and potential clinical value, most systems remain investigational. Robust multicenter validation, workflow integration, and governance frameworks addressing accountability and data management are required before routine clinical implementation.