In the Journals

Real-time colonoscopy system increases adenoma yield

A real-time colonoscopy quality improvement system known as ENDOANGEL helped improve adenoma detection, according to study results.

Honggang Yu, MD, PhD, of the department of gastroenterology at Wuhan University, and colleagues wrote that blind spots come up during colonoscopies because of endoscope slipping and differences in control among endoscopists.

“We constructed a real-time quality improvement system, named ENDOANGEL, for monitoring withdrawal speed and timing of colonoscopy intubation and withdrawal and to remind endoscopists of blind spots caused by endoscope slipping,” they wrote. “We then aimed to evaluate whether the ENDOANGEL system could improve polyp yield during colonoscopy.”

Researchers developed the system using deep neural networks and perceptual hash algorithms. They randomly assigned 704 patients to colonoscopy with the ENDOANGEL system (n = 355) or unassisted colonoscopy (n = 349). The primary endpoint was adenoma detection rate.

In their intention-to-treat analysis, investigators found that the ADR was higher in the ENDOANGEL group than in the control group. Fifty-eight patients in the study group had at least one adenoma detected (16%) compared with 27 (8%) in the control group (OR = 2.3; 95% CI, 1.4–3.77).

The ADR in the ENDOANGEL group was also higher in the per-protocol analysis. Of 324 patients assigned to ENDOANGEL, 54 patients had at least one adenoma detected (17%) compared with 26 of 318 patients (8%) in the control group (OR = 2.18; 95% CI, 1.31–3.62).

Yu and colleagues wrote that by providing real-time reminders about blind spots and withdrawal times, ENDOANGEL can improve polyp yield by limiting skill variations between endoscopists.

“The ENDOANGEL system, therefore, can give endoscopists real-time feedback to monitor and control the time spent on each colonoscopy, mitigating skill variations from subjective factors and external pressure,” they wrote. “The ENDOANGEL system could be a powerful assistant for mitigating skill variations among endoscopists and improving the quality of everyday colonoscopy.” – by Alex Young

Disclosure: Yu reports receiving grants from Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Hubei Province Major Science and Technology Innovation and the National Natural Science Foundation of China and has a patent pending for a system and method of colonoscopy blind spot monitoring. Please see the full study for all other authors’ relevant financial disclosures.

A real-time colonoscopy quality improvement system known as ENDOANGEL helped improve adenoma detection, according to study results.

Honggang Yu, MD, PhD, of the department of gastroenterology at Wuhan University, and colleagues wrote that blind spots come up during colonoscopies because of endoscope slipping and differences in control among endoscopists.

“We constructed a real-time quality improvement system, named ENDOANGEL, for monitoring withdrawal speed and timing of colonoscopy intubation and withdrawal and to remind endoscopists of blind spots caused by endoscope slipping,” they wrote. “We then aimed to evaluate whether the ENDOANGEL system could improve polyp yield during colonoscopy.”

Researchers developed the system using deep neural networks and perceptual hash algorithms. They randomly assigned 704 patients to colonoscopy with the ENDOANGEL system (n = 355) or unassisted colonoscopy (n = 349). The primary endpoint was adenoma detection rate.

In their intention-to-treat analysis, investigators found that the ADR was higher in the ENDOANGEL group than in the control group. Fifty-eight patients in the study group had at least one adenoma detected (16%) compared with 27 (8%) in the control group (OR = 2.3; 95% CI, 1.4–3.77).

The ADR in the ENDOANGEL group was also higher in the per-protocol analysis. Of 324 patients assigned to ENDOANGEL, 54 patients had at least one adenoma detected (17%) compared with 26 of 318 patients (8%) in the control group (OR = 2.18; 95% CI, 1.31–3.62).

Yu and colleagues wrote that by providing real-time reminders about blind spots and withdrawal times, ENDOANGEL can improve polyp yield by limiting skill variations between endoscopists.

“The ENDOANGEL system, therefore, can give endoscopists real-time feedback to monitor and control the time spent on each colonoscopy, mitigating skill variations from subjective factors and external pressure,” they wrote. “The ENDOANGEL system could be a powerful assistant for mitigating skill variations among endoscopists and improving the quality of everyday colonoscopy.” – by Alex Young

Disclosure: Yu reports receiving grants from Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Hubei Province Major Science and Technology Innovation and the National Natural Science Foundation of China and has a patent pending for a system and method of colonoscopy blind spot monitoring. Please see the full study for all other authors’ relevant financial disclosures.