Colorectal Cancer (CRC) ScreeningmAInstreamNCT07844252
A Novel Multi-functional Artificial Intelligence System on Treatment Efficacy and Implementation in Colonoscopy
A study testing CADe/CADx in people with Colorectal Cancer (CRC) Screening, run by Chinese University of Hong Kong.
Trial summary
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. Read more about this study
- Who is it for?
- Ages 45 to 85 yearsHealthy volunteers can take part
- Conditions the study is for
- Colorectal Cancer (CRC) Screening
- What is being tested?
- CADe/CADx
- Type of treatment
- Medical device
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 2,818 participants
- Where
- No sites listed yet
- Study dates
- 30 Oct 2026to 30 Sep 2029
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 45 to 85 years
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- Aged 45-85 years old;
- Undergoing elective colonoscopy for screening, surveillance or diagnostic indication;
- Informed consented.
Who cannot join
- Contraindication for colonoscopy (e.g. intestinal obstruction);
- Contraindication for polypectomy (e.g. active gastrointestinal bleeding, uninterrupted anticoagulants);
- Prior surgical resection of colon;
- High-risk group of CRC (e.g. personal history of CRC, familial polyposis syndrome, inflammatory bowel disease);
- Advanced comorbidity (defined as American Society of Anesthesiologists grade 4 or above).
Trial locations and contacts
No sites are listed yet. Contact the study team or a site near you to ask about taking part.
About this study
Official title: A Novel Multi-functional Artificial Intelligence System on Treatment Efficacy and Implementation in Colonoscopy: an International Multicenter Randomized Controlled Trial
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.
Nevertheless, 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.
A 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.
Read the detailed description
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.
- Conditions
- Colorectal Cancer (CRC) Screening
- Being tested
- CADe/CADx
- Keywords
- artificial intelligence (AI), automatic computer-aided detection (CADe) systems, computer-aided diagnosis (CADx) systems
- Medical subject headings
- Colorectal Neoplasms
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
CADe/CADxDevice
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.
| Study group | Role | What they receive |
|---|---|---|
| CADe | No intervention | In the CADe mode, an alert box will be automatically displayed on the screen when a suspicious lesion is detected. |
| CADe/CADx | 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. Receives: Device: CADe/CADx |
What is being measured
The primary outcome is the main question the study is designed to answer.
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)
Measured: 3 years
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)
Measured: 3 years
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted28 Sep 2026
- Study start30 Oct 2026 (estimated)
- Primary completion31 Dec 2028 (estimated)
- Study completion30 Sep 2029 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Colorectal Cancer (CRC) ScreeningStudies of the same condition, open and under way.
- More trials run by Chinese University of Hong KongThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Screening
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Model description
- Eligible subjects undergoing elective colonoscopies will be randomized to either CADe/CADx 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.
- Masking
- None (open label)
- Enrolment
- 2,818 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Chinese University of Hong Kong
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, Louis Ho Shing Lau, Chinese University of Hong Kong
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07844252
- Sponsor's protocol ID
- NTEC-CREC-2026.416
- Acronym
- mAInstream
- Status last verified
- Sep 2026
- First submitted
- 8 Sep 2026
- Last updated
- 28 Sep 2026
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- Yes
- Individual data sharing
- Undecided
Study at a glance
From the registry record, last updated by the sponsor on 28 Sep 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- A Novel Multi-functional Artificial Intelligence System on Treatment Efficacy and Implementation in Colonoscopy: an International Multicenter Randomized Controlled Trial
- ClinicalTrials.gov ID
- NCT07844252
- Acronym / sponsor ID
- mAInstream / NTEC-CREC-2026.416
- Conditions
- Colorectal Cancer (CRC) Screening
- Keywords
- artificial intelligence (AI), automatic computer-aided detection (CADe) systems, computer-aided diagnosis (CADx) systems
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 2,818 participants (estimated)
- Lead sponsor
- Chinese University of Hong KongUniversity, hospital or other
- Study start
- 30 Oct 2026 (estimated)
- Primary completion
- 31 Dec 2028 (estimated)
- Study completion
- 30 Sep 2029 (estimated)
- First posted
- 28 Sep 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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.
Nevertheless, 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.
A 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.
Detailed description
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.
Study design
- Primary purpose
- Screening
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Number of arms
- 2
- Model description
- Eligible subjects undergoing elective colonoscopies will be randomized to either CADe/CADx 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.
| Arm | Type | Receives |
|---|---|---|
| CADe | No intervention | –In the CADe mode, an alert box will be automatically displayed on the screen when a suspicious lesion is detected. |
| CADe/CADx | Active comparator | Device: CADe/CADxIn 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. |
Who may qualify
- Ages
- 45 to 85 years
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (3 listed)
- Aged 45-85 years old;
- Undergoing elective colonoscopy for screening, surveillance or diagnostic indication;
- Informed consented.
Key exclusion criteria (5 listed)
- Contraindication for colonoscopy (e.g. intestinal obstruction);
- Contraindication for polypectomy (e.g. active gastrointestinal bleeding, uninterrupted anticoagulants);
- Prior surgical resection of colon;
- High-risk group of CRC (e.g. personal history of CRC, familial polyposis syndrome, inflammatory bowel disease);
- Advanced comorbidity (defined as American Society of Anesthesiologists grade 4 or above).
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| CADe/CADxA 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. | Device | CADe/CADx |
Primary outcome
Primary endpoints (1)
Time frame: 3 years
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)
Primary Endpoints (2)
Time frame: 3 years
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)
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 28 Sep 2026.
- Individual participant dataSharing planned: Undecided
Related trials for Colorectal Cancer (CRC) Screening
Active, not recruiting
Guardant Shield Colorectal Cancer Screening
Colorectal Cancer
Not yet recruiting
Evaluation of Gixam's Repeatability and Reproducibility Predicting the Presence of Advanced and Non-Advanced Colorectal Neoplasia
CRC Screening
Active, not recruitingPhase 2
Targeted Therapy Directed by Genetic Testing in Treating Patients With Advanced Refractory Solid Tumors, Lymphomas, or Multiple Myeloma (The MATCH Screening Trial)
Advanced Lymphoma, Advanced Malignant Solid Neoplasm
Not yet recruiting
Young Adult-Mediated Intervention to Increase Colorectal Cancer Screening
Young Adult-Mediated Intervention to Increase Colorectal Cancer Screening
Recruiting
Evaluation of Gixam's Efficacy Predicting the Presence of Advanced and Non-advanced Colorectal Neoplasia in a FIT Negative Population
CRC Screening, Microbiome
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Questions about this trial
What is this clinical trial studying?
A study testing CADe/CADx in people with Colorectal Cancer (CRC) Screening, run by Chinese University of Hong Kong.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 3 inclusion and 5 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 28 Sep 2026. Status can change between updates, so confirm with the study contact before making plans.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Li (+85246572604, venusli@cuhk.edu.hk), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Primary endpoints (1) (time frame: 3 years). The study lists 2 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 28 Sep 2026.