[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-study-detail:100657839":3},{"organization":4,"outcomesModule":7,"designInfo":17,"detailedDescription":24,"studyPopulation":16,"armGroups":25,"interventions":36,"overallOfficials":16,"centralContacts":41,"locations":16,"responsibleParty":47,"collaborators":16,"id":51,"slug":52,"hasResults":53,"nctId":54,"briefTitle":55,"officialTitle":56,"acronym":57,"eligibilityCriteria":58,"healthyVolunteers":59,"sex":60,"minAge":61,"maxAge":62,"enrollmentInfo":63,"targetDuration":16,"studyType":66,"phases":67,"briefSummary":69,"conditions":70,"keywords":72,"overallStatus":76,"whyStopped":16,"lastUpdateSubmitDate":77,"lastUpdatePostDateStruct":78,"startDateStruct":81,"completionDateStruct":83,"leadSponsor":85,"locationsCount":16},{"fullName":5,"class":6},"Chinese University of Hong Kong","OTHER",{"primaryOutcomes":8,"secondaryOutcomes":16,"otherOutcomes":16},[9,13],{"measure":10,"description":11,"timeFrame":12},"Primary endpoints (1)","Superiority: neoplastic to non-neoplastic polyp (NNP) ratio, defined as the total number of neoplastic polyps divided by the number of NNP per group. (indicating the treatment efficacy)","3 years",{"measure":14,"description":15,"timeFrame":12},"Primary Endpoints (2)","Non-inferiority: adenoma detection rate (ADR), defined as proportion of subjects with at least one histologically confirmed adenoma in the colonoscopies. (indicating the safety margin for implementation)",null,{"allocation":18,"interventionModel":19,"interventionModelDescription":20,"primaryPurpose":21,"observationalModel":16,"timePerspective":16,"maskingInfo":22},"RANDOMIZED","PARALLEL","Eligible subjects undergoing elective colonoscopies will be randomized to either CADe\u002FCADx arm or CADe arm. In both arms, endoscopists will make the final decision for resecting (neoplastic) or leaving the polyps in-situ (non-neoplastic) by optical diagnosis under validated classifications, with or without CADx assistance.","SCREENING",{"masking":23,"maskingDescription":16,"whoMasked":16},"NONE","In a meta-analysis, the performance of CADx systems was superior to endoscopists, with pooled sensitivity and specificity of 92.3% and 89.8% respectively. The proportion of incorrect predictions could be significantly reduced by 12% with CADx assistance. It was reported that autonomous AI prediction could achieve a 91.5% agreement with the standard pathology-based surveillance intervals. In a prospective study targeting diminutive rectosigmoid polyps, CADx achieved a negative predictive value of 97.6% compared to the histology as gold standard. 82% of lesions were amendable for a leave-in-situ strategy, suggesting a potential to reduce the burden of unnecessary polypectomies. It was estimated that the average colonoscopy cost and annual reimbursement could be reduced by 6.9-18.9% under the 'diagnose-and-leave' strategy.",[26,30],{"label":27,"type":28,"description":29,"interventionNames":16},"CADe","NO_INTERVENTION","In the CADe mode, an alert box will be automatically displayed on the screen when a suspicious lesion is detected.",{"label":31,"type":32,"description":33,"interventionNames":34},"CADe\u002FCADx","ACTIVE_COMPARATOR","In this arm, when a suspicious lesion is detected, an alert box and a prediction on the histopathology (neoplastic vs non-neoplastic) will be generated by the underlying AI algorithm and displayed.",[35],"Device: CADe\u002FCADx",[37],{"type":38,"name":31,"description":39,"armGroupLabels":40,"otherNames":16},"DEVICE","A novel all-in-one AI system for colonoscopy (GI Genius™ ColonPro™, version 4.0.0, Medtronic plc, Minneapolis, United States) is developed as a pre-installed software in a plug-in device which is compatible with all existing endoscopes and processors.",[31],[42],{"name":43,"role":44,"phone":45,"phoneExt":16,"email":46},"Li","CONTACT","+85246572604","venusli@cuhk.edu.hk",{"type":48,"investigatorFullName":49,"investigatorTitle":50,"investigatorAffiliation":5,"oldNameTitle":16,"oldOrganization":16},"PRINCIPAL_INVESTIGATOR","Louis Ho Shing Lau","Associate Professor","100657839","a-novel-multi-functional-artificial-intelligence-system-on-treatment-efficacy-and-implementation-in-colonoscopy-100657839",false,"NCT07844252","A Novel Multi-functional Artificial Intelligence System on Treatment Efficacy and Implementation in Colonoscopy","A Novel Multi-functional Artificial Intelligence System on Treatment Efficacy and Implementation in Colonoscopy: an International Multicenter Randomized Controlled Trial","mAInstream","Inclusion Criteria:\n\n1. Aged 45-85 years old;\n2. Undergoing elective colonoscopy for screening, surveillance or diagnostic indication;\n3. Informed consented.\n\nExclusion Criteria:\n\n1. Contraindication for colonoscopy (e.g. intestinal obstruction);\n2. Contraindication for polypectomy (e.g. active gastrointestinal bleeding, uninterrupted anticoagulants);\n3. Prior surgical resection of colon;\n4. High-risk group of CRC (e.g. personal history of CRC, familial polyposis syndrome, inflammatory bowel disease);\n5. Advanced comorbidity (defined as American Society of Anesthesiologists grade 4 or above).",true,"ALL","45 Years","85 Years",{"count":64,"type":65},2818,"ESTIMATED","INTERVENTIONAL",[68],"NA","To overcome non-neoplastic polyp (NNP) resections, computer-aided diagnosis (CADx) systems have been developed. In a meta-analysis, the performance of CADx systems was superior to endoscopists. The proportion of incorrect predictions could be significantly reduced with CADx assistance. It was reported that autonomous AI prediction could achieve an agreement with the standard pathology-based surveillance intervals. In a prospective study targeting diminutive rectosigmoid polyps, CADx achieved a negative predictive value compared to the histology as gold standard. Lesions were amendable for a leave-in-situ strategy, suggesting a potential to reduce the burden of unnecessary polypectomies. It was estimated that the average colonoscopy cost and annual reimbursement could be reduced under the 'diagnose-and-leave' strategy.\n\nNevertheless, almost all existing literature reporting the efficacy of CADx were simulated studies and focused on the diagnostic accuracy (i.e. all polyps were ultimately resected for histopathology). There is a lack of real-world data with hard clinical endpoints to support its implementation. A recent RCT compared leave-in-situ and resect-all strategy with real-time CADx in both arms. Using ADR as the surrogate marker, it was shown that the leave-in-situ strategy with CADx support was non-inferior. The major limitations of this RCT were that: i) CADx were activated in both arms - the pure CADx effect could not be demonstrated; ii) 'resect-all' strategy was not a real-world practice especially for diminutive rectosigmoid polyps; iii) the interaction and decision making between AI and human was not documented and uncertain.\n\nA well-designed RCT is warranted to evaluate the pure CADx effect on reducing NNP resections (enhance treatment efficacy) while maintaining the benchmark of ADR (safe implementation). In addition, AI-measured metrics may objectively validate the procedural quality for performance tracking and auditing purposes. If the above points are proven, AI-assisted colonoscopy would become the 'mainstream' in CRC prevention.",[71],"Colorectal Cancer (CRC) Screening",[73,74,75],"artificial intelligence (AI)","automatic computer-aided detection (CADe) systems","computer-aided diagnosis (CADx) systems","NOT_YET_RECRUITING","2026-09-21",{"date":79,"type":80},"2026-09-28","ACTUAL",{"date":82,"type":65},"2026-10-30",{"date":84,"type":65},"2029-09-30",{"name":5,"class":6}]