An interventional study of "aetherAI" Computer-aided Polyp Detection (CADe) Systems for Colonoscopy and Standard colonoscopy in Colon Adenoma and Colorectal Cancer, sponsored by National Taiwan University Hospital. Recruiting at 1 site in Taiwan. Open to participants aged 40 Years to 80 Years, including healthy volunteers. Per ClinicalTrials.gov, last updated 2024-06-20.
Sponsored by National Taiwan University Hospital · Not applicable, Interventional, and Screening
Colonoscopy is clinically used as the gold standard for detection of colorectal cancer (CRC) and removal of adenomatous polyps of the colon and rectum. Evidence has shown that CRC could be prevented by colonoscopic removal of adenomatous polyps. Despite the success of colonoscopy in reducing cancer-related deaths, there exists a disappointing level of adenomas missed at colonoscopy. In recent years, emerging artificial intelligence (AI) and computer-aided detection (CADe) technology has been shown to improve ADR. Based on a meta-analysis, ADR was demonstrated to be significantly higher in the CADe groups than in the standard colonoscopy groups, representing a relative risk of 25.2%.
In this study, performance of colonoscopy with or without aid of CADe will be compared in terms of quality indicators. The adenoma detection rate (ADR), which is the proportion of average-risk patients undergoing screening colonoscopy in whom an adenoma is found, is regarded as a robust measure of colonoscopy performance quality that correlates with subsequent cancer risk. Thus, ADR is taken as the primary outcome of this study. The target population includes individuals who are undergoing screening, diagnostic, or surveillance colonoscopy.
This multiple-site study aims to evaluate whether a computer-aided detection (CADe) device can assist in adenoma detection rate (ADR) when compared with the current standard-of-care procedure. The subject CADe device used in this study contains an artificial intelligence/machine learning (AI/ML) advanced algorithm to aid the endoscopists in detection of colonic mucosal lesions and the detected polyps will be highlighted to the endoscopists during the real-time colonoscopy procedures. This study plans to enroll subjects aged ≥ 40 years and \< 80 years, who are scheduled for screening or diagnostic colonoscopy for colorectal cancer (CRC) or surveillance colonoscopy for post-polypectomy follow-up. After being evaluated with the inclusion and exclusion criteria, eligible subjects will be randomized in a 1:1 ratio to receive either the computer-aided colonoscopy (CC) or the standard colonoscopy(SC). Randomization will be stratified by gender, age, and colonoscopy indication (screening, diagnostic, or surveillance) of subjects. The resected polyps will be submitted for histologic examination by one expert pathologist at each site. If any uncertainty or doubt exists, an expert in gastrointestinal pathology will serve as the adjudicator to perform a second review and make the final decision. All of the pathologists (including the final adjudicator) who will perform the histopathologic examinations and produce the pathology assessment will be blinded to the assigned study arm of the specimens. The pathology reports of the subjects will be kept securely at each site as the source data.
The primary endpoint is the ADR of the CC as compared with that of the SC. The ADR is defined as the percentage of subjects undergoing a complete colonoscopy, who have at least one histologically confirmed adenoma detected and removed. In addition, the following secondary endpoints will also be evaluated, including: Polyp detection rate (PDR), Adenomas per colonoscopy (APC), Polyps per colonoscopy (PPC), Non-neoplastic polypectomy rate (NNPR), Non-neoplastic polypectomy (NNP), Sessile serrated lesions per colonoscopy (SPC), Advanced adenomas per colonoscopy (AAPC), and withdrawal time.
Signed written informed consent forms will be obtained from all participating subjects before enrollment.
5,599 studies on the registry are indexed under Colorectal Neoplasms; 1,459 are open to participants now.
This study's planned enrollment of 1,500 is above the median of 77 across 4,123 interventional studies indexed under Colorectal Neoplasms.
Browse Colorectal Neoplasms studies →National Taiwan University Hospital is the lead sponsor of 2,563 studies on the registry; 569 are open to participants now.
Of its 11 completed or terminated interventional studies of FDA-regulated products, 2 (18%) have results posted.
Counted across the registry records on this site, refreshed daily.
Exclusion Criteria:
Subjects with any of the following prior history or current conditions:
Subjects with any of the following conditions per the investigator's judgement:
The subject will receive the standard colonoscopy procedure simultaneously with a computer-aided detection (CADe) analysis software designed to automatically detect and highlight potential polyps on colonoscopy images in a real-time manner during colonoscopy procedures.
Device: "aetherAI" Computer-aided Polyp Detection (CADe) Systems for Colonoscopy · Procedure: Standard colonoscopy
The subject will receive the standard colonoscopy procedure.
Procedure: Standard colonoscopy
The investigational medical device is intended to automatically detect potential polyps via colonoscopy in real-time during colonoscopy examinations. The subject device contains an artificial intelligence/machine learning (AI/ML) advanced algorithm to aid the endoscopists in detection of colonic mucosal lesions and the detected polyps will be highlighted to the endoscopists during the real-time colonoscopy procedures.
Standard colonoscopy procedure.
Adenoma detection rate
The percentage of subjects undergoing a complete colonoscopy, who have at least one histologically confirmed adenoma detected and removed.
Time frame: 1 week (after the colonoscopy procedure, when pathology report is released)
Polyp detection rate (PDR)
Percentage of subjects undergoing a complete colonoscopy who have at least one polyp detected.
Time frame: 1 day(right after the colonoscopy procedure)
Adenomas per colonoscopy (APC)
Number of adenomas per colonoscopy, calculated by dividing the total number of adenomas detected by the total number of colonoscopies.
Time frame: 1 week (after the colonoscopy procedure, when pathology report is released)
Polyps per colonoscopy (PPC)
Number of polyps of any kind (i.e., adenoma, sessile serrated polyp, hyperplastic polyp, or non-neoplastic polyp) per colonoscopy, calculated by dividing the total number of polyps detected by the total number of colonoscopies.
Time frame: 1 day(right after the colonoscopy procedure)
Non-neoplastic polypectomy rate (NNPR)
Percentage of subjects with at least one non-neoplastic polypectomy at the time of colonoscopy.
Time frame: 1 week (after the colonoscopy procedure, when pathology report is released)
Sessile serrated lesions per colonoscopy (SPC)
Number of sessile serrated lesions (SSLs) per colonoscopy, calculated by dividing the total number of sessile serrated lesions detected by the total number of colonoscopies.
Time frame: 1 week (after the colonoscopy procedure, when pathology report is released)
Advanced adenomas per colonoscopy (AAPC)
Number of advanced adenomas per colonoscopy, calculated by dividing the total number of advanced adenomas detected by the total number of colonoscopies.
Time frame: 1 week (after the colonoscopy procedure, when pathology report is released)
Withdrawal time
The time spent in inspecting the colonic mucosa as the endoscope is withdrawn during a colonoscopy, excluding procedure time
Time frame: 1 day(right after the colonoscopy procedure)
Plan to share: No — Not shareable due to local IRB considerations.
No publications or documents are linked to this record.
Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.
Contact study teamGet an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
National Taiwan University Hospital