Department of Surgery, University of Florida Health, Gainesville, FL.
Amsterdam UMC, location AMC, University of Amsterdam, Department of Intensive Care, Amsterdam, Netherlands.
Surgery. 2022 May;171(5):1435-1439. doi: 10.1016/j.surg.2021.10.047. Epub 2021 Nov 21.
As opportunities for artificial intelligence to augment surgical care expand, the accompanying surge in published literature has generated both substantial enthusiasm and grave concern regarding the safety and efficacy of artificial intelligence in surgery. For surgeons and surgical data scientists, it is increasingly important to understand the state-of-the-art, recognize knowledge and technology gaps, and critically evaluate the deluge of literature accordingly. This article summarizes the experiences and perspectives of a global, multi-disciplinary group of experts who have faced development and implementation challenges, overcome them, and produced incipient evidence thereof. Collectively, evidence suggests that artificial intelligence has the potential to augment surgeons via decision-support, technical skill assessment, and the semi-autonomous performance of tasks ranging from resource allocation to patching foregut defects. Most applications remain in preclinical phases. As technologies and their implementations improve and positive evidence accumulates, surgeons will face professional imperatives to lead the safe, effective clinical implementation of artificial intelligence in surgery. Substantial challenges remain; recent progress in using artificial intelligence to achieve performance advantages in surgery suggests that remaining challenges can and will be overcome.
随着人工智能在外科护理中应用机会的增加，相关文献的大量涌现既引发了人们对人工智能在外科手术中的安全性和有效性的浓厚兴趣，也引发了人们的严重担忧。对于外科医生和外科数据科学家来说，越来越有必要了解最新技术，认识到知识和技术差距，并相应地批判性地评估大量文献。本文总结了一组具有全球视野和多学科背景的专家的经验和观点，他们在开发和实施人工智能的过程中遇到了挑战，并克服了这些挑战，同时也取得了初步的成果。总的来说，有证据表明人工智能有可能通过决策支持、技术技能评估以及资源分配、修补前肠缺陷等任务的半自动执行来增强外科医生的能力。大多数应用仍处于临床前阶段。随着技术及其应用的不断改进和积极证据的积累，外科医生将面临在外科手术中安全、有效地实施人工智能的专业要求。仍存在巨大的挑战；最近在利用人工智能在手术中实现性能优势方面取得的进展表明，剩余的挑战是可以克服的。
