Could Artificial Intelligence-Assisted Colonoscopy Be Better for Adenoma Detection? - European Medical Journal

Could Artificial Intelligence-Assisted Colonoscopy Be Better for Adenoma Detection?

2 Mins
Gastroenterology

ACCORDING to the results of a prospective randomised clinical trial, artificial intelligence (AI) colonoscopy has enhanced the detection rate of adenoma compared with standard colonoscopy. Remarkable efforts have been dedicated to improving adenoma detection rate (ADR), as ADR is linked to a lowered risk of post-colonoscopy colorectal cancer. AI has been used in different disciplines in healthcare. There has been more interest in AI-assisted colonoscopy and its effect in reducing adenoma miss rates.  

In this study, the researchers compared the use of AI-assisted colonoscopy with standard colonoscopy in 3,059 asymptomatic participants who were between 45–75 years old. The participants underwent colorectal cancer screening by colonoscopy or a faecal immunochemical test. The participants were either in the AI-assisted colonoscopy group or the standard colonoscopy group (1,519 and 1,540, respectively). The outcomes of the study included general ADR, average number of adenomas per colonoscopy (APC), and colonoscopy withdrawal time.  

The researchers’ findings showed that participants in the AI-assisted group had a higher overall ADR compared with standard colonoscopy (39.9% versus 32.4%, respectively). Additionally, the AI-assisted group had more advanced ADR (6.6%) compared with the standard colonoscopy group (4.9%). Furthermore, the adenomas per colonoscopy was higher in the AI group (0.59±0.97 versus 0.45±0.81); however, the mean withdrawal time took longer in those in the AI group (8.3 minutes versus 7.8 minutes). Remarkably, the results showed that the AI-assisted colonoscopy had an increased rate of the detection of adenomas smaller than 5 mm (16.5%) and larger than or equal to 10 mm (6.5%). 

This large-scale, multicentre randomised study showed the benefits of AI-assisted colonoscopy in asymptomatic subjects undergoing colorectal cancer screening. AI-assisted image analysis has already been applied in mammography for the screening of breast cancer, as well as in 3D low-dose CT for the screening of lung cancer,” Hong Xu, Professor of Medicine and Director of the Department of Gastroenterology and Endoscopy Center at The First Hospital of Jilin University (JLU), Changchun, China, and colleagues concluded. “It is time for us to consider generalising the use of AI-assisted endoscopy in the gastrointestinal tract.” 

Join our mailing list

To receive the EMJ updates straight to your inbox free of charge, please click the button below.
Join Now