摘要
目的探讨人工智能辅助结肠镜对结直肠息肉和腺瘤检出率的影响。方法318例患者接受结肠镜检查,第一观察者使用普通结肠镜独立操作(对照组),第二观察者使用人工智能辅助结肠镜系统监测息肉辅助诊断(研究组),并在系统检测到漏诊息肉时提示第一观察者重新评估。比较两组不同部位(近端结肠、远端结肠)、不同大小的腺瘤检出率和息肉检出率的差异。结果研究组息肉检出率和息肉长径≤5 mm的息肉检出率均高于对照组,长径6~9 mm的息肉检出率低于对照组,差异均有统计学意义(χ^(2)分别=20.72、7.87、5.09,P均<0.05)。两组在不同部位息肉检出率和长径≥10 mm的息肉检出率比较,差异均无统计学意义(χ^(2)分别=0.10、2.15,P均>0.05)。研究组的腺瘤检出率高于对照组,差异有统计学意义(χ^(2)=4.12,P<0.05)。两组在不同部位和大小的腺瘤检出率比较,差异均无统计学意义(χ^(2)分别=1.29、0.77,P均>0.05)。结论人工智能辅助结肠镜可以提高息肉与腺瘤的检出率,在提高微小及小息肉检出率方面更有优势。
Objective To explore the impact of artificial intelligence-assisted colonoscopy on colorectal polyp and ad⁃enoma detection rates.Method A total of 318 patients underwent colonoscopy.The first observer used an ordinary colo⁃noscopy independently(control group),and the second observer used an AI-assisted colonoscopy system to monitor pol⁃yps to assist diagnosis(study group),and prompted the first observer to re-evaluate when the system detected missed polyps.The detection rates of adenomas and polyps in different locations(proximal colon,distal colon)and different sizes were compared between the two groups.Results The detection rate of polyps and polyps with long diameter≤5 mm in the study group were higher than those in the control group,while the detection rate of polyps with long diameter 6~9 mm was lower than that in the control group,and the differences were statistically significant(χ^(2)=20.72,7.87,5.09,P<0.05).There was no significant difference between the two groups in the polyp detection rate at different sites and the polyp de⁃tection rate with long diameter≥10 mm(χ^(2)=0.10,2.15,P>0.05).The detection rate of adenoma in the study group was higher than that in the control group,and the difference was statistically significant(χ^(2)=4.12,P<0.05).There was no sig⁃nificant difference in the detection rate of adenoma in different parts and sizes between the two groups(χ^(2)=1.29,0.77,P>0.05).Conclusion Artificial intelligence-assisted colonoscopy can improve the detection rate of polyps and adeno⁃mas and has more advantages in improving the detection rate of small and small polyps.
作者
翁雪健
郑恩典
滕苗苗
WENG Xuejian;ZHENG Endian;TENG Miaomiao(Department of Gastroenterology,Wenzhou People's Hospital,Wenzhou 325000,China)
出处
《全科医学临床与教育》
2024年第11期981-983,987,共4页
Clinical Education of General Practice
基金
2020年温州市科技局项目(Y2020283)。
关键词
人工智能
结肠镜检查
息肉
腺瘤
检出率
artificial intelligence
colonoscopy
polyp
adenoma
detection rate
