AI-Assisted Detection for Adenoma During Colonoscopy

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Centre hospitalier de l'Université de Montréal (CHUM)

Disqualifiers: Emergency colonoscopy, Familial polyposis, Inflammatory bowel, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 1

Duration: 1 day

1596 Participants Needed

Trial Summary

What is the purpose of this trial?

This is a pragmatic, double-blind, randomized, controlled trial, to evaluate the effect of implementing a Computer-assisted detection (CADe) system within the routine clinical practice of Canadian healthcare institutions. The main hypothesis of this study is that the ADR in the operating room equipped with the GI genius CADe system will be significantly higher than the ADR in the ordinary operating room.

Do I need to stop my current medications for the trial?

The trial information does not specify whether you need to stop taking your current medications.

What data supports the effectiveness of the treatment Medtronic-GI genius for AI-Assisted Detection for Adenoma During Colonoscopy?

Research shows that using artificial intelligence (AI) during colonoscopy can significantly increase the detection of polyps and adenomas (a type of polyp that can turn into cancer) by about 10%, and reduce the rate of missed adenomas from 36.7% to 13.8% in some studies. This suggests that AI systems like Medtronic-GI genius can help doctors find more potential problem areas during colonoscopies, potentially improving patient outcomes. ^{1 2 3 4 5}

Is the AI-Assisted Detection for Adenoma During Colonoscopy safe for humans?

The AI system, including Medtronic-GI Genius, has been tested in various studies and is the first AI-powered device for colonoscopy approved by the US FDA. While the focus has been on improving detection rates, no specific safety concerns have been highlighted in the available research, suggesting it is generally safe for use in humans. ^{2 4 6 7 8}

How is the GI Genius treatment different from other treatments for adenoma detection during colonoscopy?

The GI Genius treatment is unique because it uses artificial intelligence to assist in real-time detection of adenomas during colonoscopy, improving the accuracy and efficiency of the procedure compared to standard methods. This AI-powered system highlights areas that need closer examination, potentially reducing the number of missed polyps and enhancing overall detection rates. ^{1 3 6 7 9}

Research Team

Daniel von Renteln

Principal Investigator

Centre hospitalier de l'Université de Montréal (CHUM)

Eligibility Criteria

This trial is for people aged 45-80 who are at high risk of colorectal polyps due to a positive FIT, family or personal history of CRC, or previous polyps. They must consent to the study and need a screening or diagnostic colonoscopy. It's not for those with inflammatory bowel disease, severe coagulopathy, emergency cases, familial polyposis syndrome, or very poor health.

Inclusion Criteria

Signed informed consent

I am at high risk for colorectal polyps due to family history, personal history, or previous findings.

I am scheduled for a colonoscopy for screening, surveillance, or diagnosis.

Exclusion Criteria

I do not have inflammatory bowel disease, active colitis, severe coagulopathy, need for emergency colonoscopy, familial polyposis syndrome, or poor general health.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants undergo colonoscopy with or without the CADe system, depending on the assigned group

1 day

1 visit (in-person)

Follow-up

Participants are monitored for adenoma detection rate and other secondary outcomes

30 days

Data Collection and Analysis

Data is collected from clinical files and endoscopy reports, deidentified, and analyzed

Through study completion, an average of 3 years

Treatment Details

Interventions

• Medtronic-GI genius

Trial Overview The trial tests if using AI (Medtronic-GI genius) during colonoscopies increases adenoma detection rates compared to standard procedures. Participants will be randomly assigned to either an AI-assisted room or a regular one without knowing which they're in (double-blind).

Participant Groups

Group I: Operating room equipped with the CADe (Medtronic-GI genius for real-time detection) Experimental Treatment 1 Intervention

The Medtronic-GI genius (CADe) system can be used to detect polyps of all sizes. Use of CADe is left to the discretion of the treating physician performing the colonoscopy. If used CADe will provide real-time feedback throughout each colonoscopy procedure and will alert the endoscopists of the presence of a polyp in the endoscopy field by displaying a bounding box on the same screen.

Group II: Colonoscopy performed in room without CADe system Active Control 1 Intervention

In the control group (standard colonoscopy), the participating endoscopists will detect and classify colorectal lesions without using any AI modules.

Who Is Running the Clinical Trial?

Centre hospitalier de l'Université de Montréal (CHUM)

Lead Sponsor

Trials

389

Recruited

143,000+

Université de Sherbrooke

Collaborator

Trials

317

Recruited

79,300+

University of British Columbia

Collaborator

Trials

1,506

Recruited

2,528,000+

University of Alberta

Collaborator

Trials

957

Recruited

437,000+

McGill University

Collaborator

Trials

421

Recruited

1,017,000+

Findings from Research

The artificial intelligence system for colorectal neoplasia detection (CADe) demonstrated high sensitivity (92.9%) and accuracy (91.7%), indicating its potential to significantly enhance lesion recognition during colonoscopy.

The CADx system also showed promising results with an accuracy of 83.6%, and notably, non-expert endoscopists using CAD achieved performance levels similar to experts, although with lower specificity, suggesting that AI can help improve diagnostic capabilities in less experienced practitioners.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Performance of a new integrated computer-assisted system (CADe/CADx) for detection and characterization of colorectal neoplasia. Weigt, J., Repici, A., Antonelli, G., et al.[2022]

In a study of 150 patients undergoing colonoscopy, an artificial intelligence (AI) system showed comparable adenoma miss rates (AMR) and adenoma detection rates (ADR) to experienced endoscopists, indicating its potential effectiveness in real-time colonoscopy.

The AI system did not significantly improve the detection of adenomas compared to routine colonoscopy, with both methods achieving high ADRs of over 50%, suggesting that while AI can assist, it may not surpass the performance of skilled endoscopists.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Diagnostic accuracy of a novel artificial intelligence system for adenoma detection in daily practice: a prospective nonrandomized comparative study. Zippelius, C., Alqahtani, SA., Schedel, J., et al.[2022]

Computer-aided diagnosis in colonoscopy can significantly reduce the miss rates for polyps, which are currently as high as 22%, potentially decreasing the risk of interval colorectal cancers.

Recent advancements in artificial intelligence have led to algorithms that can match the performance of human experts in detecting and characterizing polyps, enhancing the reliability of optical biopsy techniques.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions. Ahmad, OF., Soares, AS., Mazomenos, E., et al.[2019]

Artificial intelligence, particularly through deep neural networks, has significantly improved polyp detection during colonoscopy, increasing detection rates by about 10% according to recent prospective trials.

Tandem randomized control trials demonstrated that AI assistance reduced the adenoma miss rate from 36.7% to 13.8%, indicating a substantial improvement in the accuracy of colonoscopy procedures.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificial intelligence in colonoscopy: A review on the current status. Larsen, SLV., Mori, Y.[2022]

Artificial intelligence can enhance the quality of colonoscopy screenings by improving adenoma detection rates through real-time computer-assisted detection of polyps.

AI technology can also reduce unnecessary costs by enabling optical biopsies for low-risk polyps, allowing for strategies like resect-and-discard, which streamlines patient management.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

How Artificial Intelligence Will Impact Colonoscopy and Colorectal Screening. Shung, DL., Byrne, MF.[2021]

GI Genius is the first AI-powered medical device for colonoscopy, showing promise in enhancing decision-making and consistency during procedures, as it has been widely tested and reviewed in the scientific community.

The device's transparent AI architecture and training methods suggest it could significantly improve the accuracy and efficiency of colonoscopy procedures, marking a major advancement in the integration of AI in medical practice.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A Review of the Technology, Training, and Assessment Methods for the First Real-Time AI-Enhanced Medical Device for Endoscopy. Cherubini, A., Dinh, NN.[2023]

The GI Genius™ system, a real-time deep-learning computer-aided detection tool, has been approved by the US FDA to assist in identifying polyps during colonoscopy, addressing the issue that about 25% of colorectal cancers are missed during these procedures.

This review highlights the potential of artificial intelligence to enhance endoscopic surveillance strategies, improving the detection rates of precancerous lesions and potentially leading to better outcomes in colorectal cancer prevention.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Discovering the first US FDA-approved computer-aided polyp detection system. Spadaccini, M., Marco, A., Franchellucci, G., et al.[2022]

A study involving 33 early-career endoscopists analyzing 200 colonoscopy videos showed that using an AI tool significantly improved their ability to detect polyps, increasing sensitivity from 86.3% to 91.7%.

The AI tool also enhanced the detection of neoplastic polyps, with sensitivity rising from 85.4% to 92.1%, indicating that AI can effectively support endoscopists in identifying potentially harmful growths.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Impact of artificial intelligence on colorectal polyp detection for early-career endoscopists: an international comparative study. Ainechi, D., Misawa, M., Barua, I., et al.[2022]

The COLO-DETECT trial will assess the effectiveness of the GI Genius™ computer-aided detection system in improving adenoma detection rates during colonoscopy, involving 1828 participants across various NHS sites in England.

This study is significant as it will be the first multi-centre randomized controlled trial to evaluate both the clinical and cost-effectiveness of GI Genius™ in routine colonoscopy practice, potentially enhancing colorectal cancer screening outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Trial protocol for COLO-DETECT: A randomized controlled trial of lesion detection comparing colonoscopy assisted by the GI Genius™ artificial intelligence endoscopy module with standard colonoscopy. Seager, A., Sharp, L., Hampton, JS., et al.[2022]

References

1. Germany pubmed.ncbi.nlm.nih.gov

Performance of a new integrated computer-assisted system (CADe/CADx) for detection and characterization of colorectal neoplasia. [2022]

2. Germany pubmed.ncbi.nlm.nih.gov

Diagnostic accuracy of a novel artificial intelligence system for adenoma detection in daily practice: a prospective nonrandomized comparative study. [2022]

3. Netherlands pubmed.ncbi.nlm.nih.gov

Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions. [2019]

4. Australia pubmed.ncbi.nlm.nih.gov

Artificial intelligence in colonoscopy: A review on the current status. [2022]

5. United States pubmed.ncbi.nlm.nih.gov

How Artificial Intelligence Will Impact Colonoscopy and Colorectal Screening. [2021]

6. Switzerland pubmed.ncbi.nlm.nih.gov

A Review of the Technology, Training, and Assessment Methods for the First Real-Time AI-Enhanced Medical Device for Endoscopy. [2023]

7. England pubmed.ncbi.nlm.nih.gov

Discovering the first US FDA-approved computer-aided polyp detection system. [2022]

8. England pubmed.ncbi.nlm.nih.gov

Impact of artificial intelligence on colorectal polyp detection for early-career endoscopists: an international comparative study. [2022]

9. England pubmed.ncbi.nlm.nih.gov

Trial protocol for COLO-DETECT: A randomized controlled trial of lesion detection comparing colonoscopy assisted by the GI Genius™ artificial intelligence endoscopy module with standard colonoscopy. [2022]