Dataset Information

Does Artificial Intelligence Improve Polyp Detection at Colonoscopy?

ABSTRACT: Interventions: Usual standard of care from the endoscopist doctor, with addition of Endo-AID (Olympus Corporation) AI module to be on during withdrawal phase of colonoscopy. -Usual standard of care: single colonoscopy, which may take between 3-30 minutes. During withdrawal phase, which may take between 6 and 60 minutes, the AI module will be activated. It is not known if use of this module will increase the withdrawal time (compared to standard of care, without it). -The nurses will advise the doctor of the randomisation (AI or standard of care), and turn on the AI device once withdrawal has commenced. -The AI will analyse the video output from the scope to automatically detect suspected polyps in real-time during withdrawal. Polyps would then be further analysed and resected as per usual standard of care. Primary outcome(s): ADR (Adenoma Detection Rate) - proportion of patients with at least one histologically proven adenoma or carcinoma. Histology will be assessed using standard procedure in the laboratory. This data will be gathered from colonoscopy reports and lab reports of patients[At time of colonoscopy] Study Design: Purpose: Diagnosis; Allocation: Randomised controlled trial; Masking: Open (masking not used);Assignment: Parallel;Type of endpoint: Efficacy

DISEASE(S): Oral And Gastrointestinal-other Diseases Of The Mouth, Teeth, Oesophagus, Digestive System Including Liver And Colon,Colonic Polyps,Cancer-bowel-back Passage (rectum) Or Large Bowel (colon)

PROVIDER: 2737810 | ecrin-mdr-crc |

REPOSITORIES: ECRIN MDR

ACCESS DATA

Similar Datasets

Project description:Insufflation of the colon, usually with room air, is necessary to distend the lumen for exploration. Carbon dioxide (CO2) insufflation instead of room air insufflation (AI) has been shown to decrease symptoms of abdominal pain or discomfort during the procedure and particularly during the following 24 hours. CO2 is is rapidly absorbed by the intestinal mucosa and exhaled through respiration. AI colonoscopy has usually been the reference standard to compare colonoscopy using CO2 insufflation. In two recent articles AI was compared to either CO2 insufflation and Water-aided colonoscopy (WAC), which entails infusion of water to facilitate insertion to the cecum. WAC can be categorized broadly in Water Immersion (WI) and Water Exchange (WE). In WI water is infused during the insertion phase of colonoscopy, with removal of infused water predominantly during withdrawal. Occasional use of insufflation may be allowed. WE entails complete exclusion of insufflation, removal of residual colonic air pockets and feces, and suction of infused water predominantly during insertion to minimize distention. During the withdrawal phase insufflation is used to distend the colonic lumen. In the WAC arms of the two mentioned articles the insertion method used was WI, with infusion of water at room temperature or at 37°C. During withdrawal, air insufflation or either air or CO2 insufflation were employed. Compared to AI, CO2 insufflation and WI (using room air insufflation or CO2 insufflation during withdrawal) were effective in both studies in decreasing sedation requirement, pain and tolerance scores, with patients’ higher willingness to repeat the procedure. Until now no direct comparison has been made within a single study about pain score during colonoscopy using AI, CO2 insufflation, WI/CO2, WE/CO2, WI/AI and WE/AI. In this study we test the hypothesis that, compared to AI, CO2 insufflation and WAC/CO2-AI methods will decrease pain score during colonoscopy, with reduction of sedation requirement, and that WE will achieve the best result. This comparative study has also the aim to test the respective peculiarities of each method.

Project description:The degree of protection afforded by colonoscopy against proximal colorectal cancer (CRC) appears to be related to the quality of the procedure, and the incomplete removal of lesions has been shown to increase the subsequent risk of developing a colon cancer. Some studies suggest that small polyps with advanced histology are more common in the right than in the left colon (right colon proximal to splenic flexure, left colon distal to the splenic flexure). The average size of polyps in the right colon with advanced pathology or containing adenocarcinoma was ≤9 mm, whereas in the left colon their average size was >9 mm, P<0.001. Inadequate prevention of right-sided CRC incidence and mortality may be due to right-sided polyps with advanced histology or that harbor malignancy. These presumptive precursors of cancer are smaller and possibly more easily obscured by residual feces, and more likely to be missed at colonoscopy. Water-aided colonoscopy (WAC) can be subdivided broadly into two major categories: water immersion (WI), characterized by suction removal of the infused water predominantly during the withdrawal phase of colonoscopy, and water exchange (WE), characterized by suction removal of infused water predominantly during the insertion phase of colonoscopy. In some reports WE appeared to be superior to both WI and air insufflation colonoscopy (AI) in terms of pain reduction and adenoma detection, particularly for <10 mm adenomas in the proximal colon. In this multicenter, double-blinded randomized controlled trial (RCT) we test the hypothesis that that WE, compared to AI and WI, will enhance overall Adenoma Detection Rate (ADR) in CRC screening patients. Confirmation of the primary hypothesis will provide evidence that WE enhances the quality of screening colonoscopy. We also hypothesize that WE may be more effective in detecting proximal colon adenomas than WI and AI, particularly <10 mm adenomas, thus increasing proximal colon ADR and proximal colon ADR <10 mm. Confirmation of secondary hypotheses will provide justification for further testing that WE may provide a strategy to improve prevention of colorectal cancer by increasing detection of adenomas in screening colonoscopy. Unlike previous reports of single colonoscopist studies, the insertion and withdrawal phases of colonoscopy will be done by different investigators. The second investigator will be blinded to the method used to insert the instrument, thus eliminating possible bias about procedure related issues. Several secondary outcomes will also be analysed.

Dataset Information

Does Artificial Intelligence Improve Polyp Detection at Colonoscopy?

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets