Are we developing the right intraoperative AI assistance? Surgeons’ perspectives and desired functions

Le résumé fourni par la source

BACKGROUND: As Artificial intelligence (AI) is increasingly integrated into surgical practice, particularly in robotic surgery, the clinical intraoperative implementation remains limited. Continued progress will require not only technical advances but also a clear understanding of which functions surgeons find valuable in practice. This study aimed to assess surgeons' perceptions, knowledge, attitudes, and current use of AI-driven intraoperative assistance. METHODS: We conducted a structured, web-based survey of 53 surgeons across 5 continents, assessing demographics, attitudes, knowledge, current use, and perceived usefulness of five AI-based intraoperative guidance components, using video footage from robotic upper gastrointestinal surgeries. Participants were stratified by surgical experience level. Ordinal and categorical data were analyzed using non-parametric tests, and paired comparisons, with statistical significance set at p < 0.05. RESULTS: Perceived knowledge of AI tools for surgery was rated as average or lower by 83.0% of respondents, and 79.2% reported never using such tools intraoperatively. Confidence in relying on clinically validated AI tools was reported by 75.5%, and 86.8% agreed that intraoperative AI assistance could positively impact surgical performance. Anatomy recognition and risk detection received the highest usefulness scores (4.57 ± 0.54 and 4.45 ± 0.72, respectively), followed by vision-language model assistance (3.94 ± 0.97), while step recognition (3.36 ± 1.11) and decision-making guidance (3.51 ± 1.15) were rated lowest; overall usefulness differed significantly across the five components (p < 0.001). CONCLUSION: This study clarifies how surgeons expect intraoperative AI to be implemented. Despite high perceived usefulness across multiple surgical AI functions, especially for anatomical guidance, adoption in routine practice remains limited, highlighting a gap between positive perceptions and clinical implementation.

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