人工智能肠镜辅助诊断技术诊断肠道腺瘤的价值及其影响因素分析

Artificial intelligence colonoscopy-assisted diagnosis technology for intestinal adenomas and its influencing factors

目的:探讨人工智能肠镜辅助诊断技术诊断肠道腺瘤的临床效果,并分析其影响因素。方法:回顾分析2019年5月至2020年5月接受肠镜相关检查的436例患者的临床资料,分为接受常规肠镜检查的对照组(n=203)与接受人工智能肠镜辅助诊断的观察组(n=233),比较两组肠道腺瘤检出率,并评估透明帽使用、肠道清洁程度、操作者经验等因素对腺瘤检出率的影响。结果:对照组与观察组分别检出腺瘤81例与143例,检出率为39.90%与61.37%,差异有统计学意义(P<0.05)。与经验不足的医师相比,对照组与观察组肠镜检查经验超过1000例的医师腺瘤检出率更高(P<0.05);观察组在肠镜镜头处安装透明帽对于隐藏于褶皱处的凸起腺瘤具有更好的检出效果(P<0.05);腺瘤检出率与患者性别、年龄并无显著相关性。结论:利用人工智能肠镜辅助诊断技术可提高临床肠道腺瘤检出率,透明帽的使用、经验较丰富的医师有助于肠道腺瘤的检出。

Objective:To explore the clinical effect of artificial intelligence colonoscopy-assisted diagnosis technology on the detection rate of intestinal adenomas,and to analyze its influencing factors.Methods:A retrospective analysis was performed on clinical data of 436 patients who received colonoscopy-related examinations from May 2019 to May 2020,and they were divided into the control group(n=203)who received routine colonoscopy and the observation group(n=233)who received artificial intelligence colonoscopy-assisted diagnosis.This study compared the detection rates of intestinal adenomas in patients undergoing two different colonoscopy m ethods and evaluated the impact of factors such as the use of a transparent cap,the level of bowel cleanliness,and the experience of the o perator on the adenoma detection rate.Results:There were 81 and 143 adenomas detected in the control group and the observation group,respectively,and the detection rates were 39.90%and 61.37%,respectively(P<0.05).Compared with the doctors with insu-fficient experience,the detection rate of adenoma was higher in doctors with more than 1000 cases of colonoscopy experience in the c ontrol group and the observation group(P<0.05).In the observation group,installing a transparent cap on the colonoscope lens had a better detection effect on the raised adenoma hidden in the folds(P<0.05).There was no significant correlation between the detection rate of adenoma and the gender and age of patients.Conclusions:The use of artificial intelligence colonoscopy-assisted diagnosis technology can greatly improve the clinical detection rate of intestinal adenomas,and the use of transparent caps and high qualifications of physicians can promote the detection of intestinal adenomas.