Vilkoite Ilona, Tolmanis Ivars, Meri Hosams Abu, Polaka Inese, Mezmale Linda, Anarkulova Linda, Leja Marcis, Lejnieks Aivars
Health Centre 4, LV-1012 Riga, Latvia.
Digestive Diseases Center GASTRO, LV-1079 Riga, Latvia.
Diagnostics (Basel). 2023 Feb 13;13(4):701. doi: 10.3390/diagnostics13040701.
Colorectal cancer (CRC) is the third most common cancer worldwide. Colonoscopy is the gold standard examination that reduces the morbidity and mortality of CRC. Artificial intelligence (AI) could be useful in reducing the errors of the specialist and in drawing attention to the suspicious area.
A prospective single-center randomized controlled study was conducted in an outpatient endoscopy unit with the aim of evaluating the usefulness of AI-assisted colonoscopy in PDR and ADR during the day time. It is important to understand how already available CADe systems improve the detection of polyps and adenomas in order to make a decision about their routine use in practice. In the period from October 2021 to February 2022, 400 examinations (patients) were included in the study. One hundred and ninety-four patients were examined using the ENDO-AID CADe artificial intelligence device (study group), and 206 patients were examined without the artificial intelligence (control group).
None of the analyzed indicators (PDR and ADR during morning and afternoon colonoscopies) showed differences between the study and control groups. There was an increase in PDR during afternoon colonoscopies, as well as ADR during morning and afternoon colonoscopies.
Based on our results, the use of AI systems in colonoscopies is recommended, especially in circumstances of an increase of examinations. Additional studies with larger groups of patients at night are needed to confirm the already available data.
结直肠癌（CRC）是全球第三大常见癌症。结肠镜检查是降低CRC发病率和死亡率的金标准检查。人工智能（AI）有助于减少专家的误诊，并能提醒注意可疑区域。
在门诊内镜检查单元进行了一项前瞻性单中心随机对照研究，目的是评估白天AI辅助结肠镜检查在息肉检出率（PDR）和腺瘤检出率（ADR）方面的有效性。了解现有的计算机辅助检测（CADe）系统如何提高息肉和腺瘤的检测率，对于决定其在实际中的常规应用非常重要。在2021年10月至2022年2月期间，400例检查（患者）纳入研究。194例患者使用ENDO - AID CADe人工智能设备进行检查（研究组），206例患者未使用人工智能进行检查（对照组）。
研究组和对照组之间，所有分析指标（上午和下午结肠镜检查的PDR和ADR）均未显示出差异。下午结肠镜检查的PDR有所增加，上午和下午结肠镜检查的ADR也有所增加。
根据我们的研究结果，建议在结肠镜检查中使用AI系统，尤其是在检查量增加的情况下。需要对更多患者进行夜间检查的进一步研究，以证实现有数据。
