Clinical Effectiveness Research Group, Institute of Health and Society, Faculty of Medicine, University of Oslo, Oslo, Norway.
Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan.
J Gastroenterol Hepatol. 2021 Jan;36(1):7-11. doi: 10.1111/jgh.15339.
Adoption of artificial intelligence (AI) in clinical medicine is revolutionizing daily practice. In the field of colonoscopy, major endoscopy manufacturers have already launched their own AI products on the market with regulatory approval in Europe and Asia. This commercialization is strongly supported by positive evidence that has been recently established through rigorously designed prospective trials and randomized controlled trials. According to some of the trials, AI tools possibly increase the adenoma detection rate by roughly 50% and contribute to a 7-20% reduction of colonoscopy-related costs. Given that reliable evidence is emerging, together with active commercialization, this seems to be a good time for us to review and discuss the current status of AI in colonoscopy from a clinical perspective. In this review, we introduce the advantages and possible drawbacks of AI tools and explore their future potential including the possibility of obtaining reimbursement.
人工智能（AI）在临床医学中的应用正在彻底改变日常实践。在结肠镜检查领域，主要的内镜制造商已经在欧洲和亚洲获得监管批准，将其自主研发的 AI 产品推向市场。这一商业化得到了强有力的证据支持，这些证据是通过严格设计的前瞻性试验和随机对照试验最近确立的。根据一些试验结果，AI 工具可能会将腺瘤检出率提高约 50%，并有助于降低 7-20%的结肠镜检查相关费用。鉴于可靠的证据正在出现，并且商业化活动也在积极进行，现在似乎是我们从临床角度回顾和讨论 AI 在结肠镜检查中应用现状的好时机。在这篇综述中，我们介绍了 AI 工具的优势和可能的缺点，并探讨了它们的未来潜力，包括获得报销的可能性。
