RESUMO
The development of deep learning systems in artificial intelligence (AI) has enabled advances in endoscopy, and AI-aided colonoscopy has recently been ushered into clinical practice as a clinical decision-support tool. This has enabled real-time AI-aided detection of polyps with a higher sensitivity than the average endoscopist, and evidence to support its use has been promising thus far. This review article provides a summary of currently published data relating to AI-aided colonoscopy, discusses current clinical applications, and introduces ongoing research directions. We also explore endoscopists’ perceptions and attitudes toward the use of this technology, and discuss factors influencing its uptake in clinical practice.
RESUMO
Background/Aims@#Sigmoidoscopy is performed in most medical centers to evaluate the distal colons of young adults presenting with hematochezia who are at risk of developing proximal lesions. Colonoscopies offer more complete evaluations but are associated with a higher incidence of complications and possible low yield. @*Methods@#An analysis was conducted on colonoscopies performed in our center on patients 40 years of age or younger. The study population was sub-divided into 2 age groups for analysis: <30 years of age and 30–39 years of age. @*Results@#We recruited 453 patients for the study. Patients were 115 and 338 individuals that were <30 and 30–39 years of age, respectively. Hemorrhoids was identified as the cause of bleeding in the majority of cases. The overall incidence of polyps was 6.5%; this was significantly higher in the 30–39 age group (7.4% vs. 1.7%, p=0.026). There were two cases of advanced/malignant polyps. While the majority of the polyps were in the distal colon, 28% of the polyps in the older age group were found in the proximal colon. There was one case of colonic perforation. @*Conclusions@#Colonic polyps are more prevalent in patients aged 30–39. Colonoscopies should be considered for patients over the age of 30 with rectal bleeding.