Artificial Intelligence-assisted Colonoscopy in the Detection and Characterization of Colorectal Lesions

Artificial Intelligence-assisted Colonoscopy in the Detection and Characterization of Colorectal Lesions: Randomized Controlled Clinical Trial

The study aims to evaluate the effectiveness of artificial intelligence-assisted colonoscopy in increasing adenoma detection rate and the accuracy in the characterization of colorectal lesions, compared to standard colonoscopy, in a randomized controlled clinical trial setting.

Study Overview

• Status: Recruiting
• Conditions: Colorectal Cancer; Colorectal Cancer (CRC); Colorectal Lesions; Adenomatous Polyposis
• Intervention / Treatment: Procedure: Colonoscopy

Detailed Description

Colorectal cancer (CRC) currently shows, according to GLOBOCAN, an incidence of 19.5 individuals per 100,000 inhabitants in both sexes, being the third most common cancer in men and the second in women, representing the third leading cause of death in both men and women.

According to the GLOBOCAN registry of the World Health Organization (WHO), it is estimated that CRC is the third most common type of cancer worldwide, responsible for 10% of all newly diagnosed cancer cases, corresponding to 1,931,590 cases in 2020, preceded only by lung cancer (11.4%) and breast cancer (11.7%). CRC is the second leading cause of cancer mortality (9.4%; 935,173 cases in 2020), following only lung cancer, which accounts for 18% of cancer deaths globally.

In Brazil, according to data from the National Cancer Institute (INCA), CRC mirrors the global incidence, being the second most common cancer by sex.

Colonoscopy is the most accurate CRC screening method, with sensitivity reaching 100% in the detection of colorectal lesions. According to studies, for each 1% increase in adenoma detection rate, there is a 5% decrease in CRC mortality, highlighting the importance of performing colonoscopy to detect colorectal lesions, especially adenomas.

Consequently, with the advancement of technology, new high-definition endoscopes with virtual chromoscopy and image magnification have been developed to increase adenoma detection rates. More recently, AI-assisted colonoscopy has been gaining prominence in helping prevent CRC in some medical centers worldwide, such as in Japan.

In a multicenter study with 700 patients in 2019, a significantly higher adenoma detection rate was demonstrated with AI-assisted colonoscopy compared to standard colonoscopy (54.8% vs. 40.4%). Subsequently, a randomized, double-blind clinical trial with 1,058 patients was conducted, comparing standard colonoscopy to AI-assisted colonoscopy. The result was an adenoma detection rate of 29% for AI-assisted colonoscopy and 20% for standard colonoscopy, with the difference being statistically significant. Two other studies comparing AI-assisted colonoscopy and standard colonoscopy showed similar results.

However, when analyzing the accuracy of AI systems in characterizing colorectal lesions, different results are observed in the literature. On one hand, Japanese studies report accuracies above 90% in characterizing neoplastic and non-neoplastic lesions with artificial intelligence, while other studies, such as the Dutch study and the German study, found accuracies of 74.4% and 84.7%, respectively, results significantly lower compared to the Japanese studies.

Therefore, given not only the differences in results obtained by various authors but also the differences in population and the lack of studies on AI-assisted colonoscopy in developing countries, the objective of this work is to evaluate the adenoma detection rate of AI-assisted colonoscopy and assess the accuracy of artificial intelligence in characterizing colorectal lesions.

• Study Type: Interventional
• Enrollment (Estimated): 1000
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Márcio Roberto Facanali Júnior; Phone Number: +55 19 99825-2870; Email: marcio.facanali@hc.fm.usp.br
• Study Contact Backup: Name: Adriana Vaz Safatle Ribeiro, PhD; Phone Number: +55 19 99825-2870

Study Locations

• Brazil
  • SP
    • São Paulo, SP, Brazil, 05403-010
      • Recruiting
      • Hospital das Clinicas da Faculdade de Medicina da USP
      • Sub-Investigator: Márcio R Facanali Júnior

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• All patients aged 18 years or older, with an elective indication for colonoscopy who sign the informed consent form agreeing to participate in the study.

Exclusion Criteria:

• History of inflammatory bowel disease.
• History of colorectal cancer.
• Personal history of colorectal surgery.
• Contraindication to endoscopic biopsies.
• History of intestinal polyposis syndromes.
• Urgent or emergency cases.
• Presence of severe, decompensated comorbidities, or with a score of 3 or higher according to the American Society of Anesthesiologists (ASA) classification.
• Incomplete colonoscopy that does not reach the cecum.
• Insufficient or inadequate bowel preparation, with a score lower than 6 on the Boston Bowel Preparation Scale.
• Patients who do not agree to participate in the study and do not sign the informed consent form (ICF).

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Active Comparator: Colonoscopy with the aid of artificial intelligence; Stratum 1: Patients aged 18 to 44 years Stratum 2: Patients aged 45 to 75 years Stratum 3: Patients aged 76 years or older	Procedure: Colonoscopy; This single-center, randomized, open-label clinical trial will assess the effectiveness of artificial intelligence (AI)-assisted colonoscopy versus standard high-definition colonoscopy in detecting and characterizing colorectal lesions. Conducted over 12 months in São Paulo, Brazil, the study will include 100 adult patients undergoing elective colonoscopy. Participants will be stratified by age and randomized (1:1) after sedation. All lesions will be resected, recorded, and analyzed histologically. The intervention group will also include AI output data (CAD EYE). The primary goals are to evaluate adenoma detection rate (ADR) and AI diagnostic accuracy. Given the global burden of colorectal cancer (CRC), particularly in developing countries, this study aims to provide real-world data on the impact of AI in CRC screening.
Active Comparator: Colonoscopy without the aid of artificial intelligence; Stratum 1: Patients aged 18 to 44 years Stratum 2: Patients aged 45 to 75 years Stratum 3: Patients aged 76 years or older	Procedure: Colonoscopy; This single-center, randomized, open-label clinical trial will assess the effectiveness of artificial intelligence (AI)-assisted colonoscopy versus standard high-definition colonoscopy in detecting and characterizing colorectal lesions. Conducted over 12 months in São Paulo, Brazil, the study will include 100 adult patients undergoing elective colonoscopy. Participants will be stratified by age and randomized (1:1) after sedation. All lesions will be resected, recorded, and analyzed histologically. The intervention group will also include AI output data (CAD EYE). The primary goals are to evaluate adenoma detection rate (ADR) and AI diagnostic accuracy. Given the global burden of colorectal cancer (CRC), particularly in developing countries, this study aims to provide real-world data on the impact of AI in CRC screening.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Number of patients with at least one adenoma detected, confirmed by histopathological analysis, during colonoscopy, in the AI group vs. control group	The measure will be expressed as the number and percentage (%) of patients with at least one adenoma detected during colonoscopy and confirmed by histopathological analysis, comparing the AI and non-AI groups (CAD EYE). Detection will be based on the analysis of biopsies performed and processed according to the standard protocol.	7 days after colonoscopy (estimated time for histopathological report release).

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy of CAD EYE for characterization of lesions as neoplastic (adenoma) or non-neoplastic (hyperplastic), compared to histopathological analysis as the gold standard.	The accuracy of artificial intelligence (CAD EYE) in characterizing detected lesions as neoplastic or non-neoplastic will be calculated, based on comparison with histopathological diagnosis (gold standard). The following will be reported: sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), in percentage (%), for each type of lesion.	7 days after colonoscopy

Collaborators and Investigators

• Sponsor: Instituto do Cancer do Estado de São Paulo

Publications and helpful links

Helpful Links

• Shaukat A, Kahi CJ, Burke CA, Rabeneck L, Sauer BG, Rex DK. ACG Clinical Guidelines: Colorectal Cancer Screening 2021. Am J Gastroenterol [Internet]. 2021 Mar;116(3):458-79.
• Repici A, Badalamenti M, Maselli R, Correale L, Radaelli F, Rondonotti E, et al. Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial. Gastroenterology [Internet]. 2020 Aug;159(2):512-520.e7.
• Wang P, Liu X, Berzin TM, Glissen Brown JR, Liu P, Zhou C, et al. Effect of a deeplearning computer-aided detection system on adenoma detection during colonoscopy (CADe-DB trial): a double-blind randomised study. Lancet Gastroenterol Hepatol [Internet].
• Gong D, Wu L, Zhang J, Mu G, Shen L, Liu J, et al. Detection of colorectal adenomas with a real-time computer-aided system (ENDOANGEL): a randomised controlled study. Lancet Gastroenterol Hepatol [Internet]. 2020 Apr;5(4):352-61.
• Liu W-N, Zhang Y-Y, Bian X-Q, Wang L-J, Yang Q, Zhang X-D, et al. Study on detection rate of polyps and adenomas in artificial-intelligence-aided colonoscopy. Saudi J Gastroenterol [Internet]. 2020;26(1):13
• Aihara H, Saito S, Inomata H, Ide D, Tamai N, Ohya TR, et al. Computer-aided diagnosis of neoplastic colorectal lesions using 'real-time' numerical color analysis during autofluorescence endoscopy. Eur J Gastroenterol Hepatol [Internet]. 2013 Apr;25(4):4
• Kominami Y, Yoshida S, Tanaka S, Sanomura Y, Hirakawa T, Raytchev B, et al. Computer-aided diagnosis of colorectal polyp histology by using a real-time image recognition system and narrow-band imaging magnifying colonoscopy. Gastrointest Endosc [Internet
• Kuiper T, Alderlieste Y, Tytgat K, Vlug M, Nabuurs J, Bastiaansen B, et al. Automatic optical diagnosis of small colorectal lesions by laser-induced autofluorescence. Endoscopy [Internet]. 2014 Sep 29;47(01):56-62.
• Rath T, Tontini G, Vieth M, Nägel A, Neurath M, Neumann H. In vivo real-time assessment of colorectal polyp histology using an optical biopsy forceps system based on laser-induced fluorescence spectroscopy. Endoscopy [Internet].
• Keats AS. The ASA Classification of Physical Status-A Recapitulation. Anesthesiology [Internet]. 1978 Oct 1;49(4):233-5.
• Calderwood AH, Jacobson BC. Comprehensive validation of the Boston Bowel Preparation Scale. Gastrointest Endosc [Internet]. 2010 Oct;72(4):686-92
• Chernik DA, Gillings D, Laine H, Hendler J, Silver JM, Davidson AB, et al. Validity and reliability of the Observer's Assessment of Alertness/Sedation Scale: study with intravenous midazolam. J Clin Psychopharmacol [Internet]. 1990 Aug;10(4):244-51
• Kudo S, Hirota S, Nakajima T, Hosobe S, Kusaka H, Kobayashi T, et al. Colorectal tumours and pit pattern. J Clin Pathol [Internet]. 1994 Oct 1;47(10):880-5.
• Kimura T, Yamamoto E, Yamano H, Suzuki H, Kamimae S, Nojima M, et al. A Novel Pit Pattern Identifies the Precursor of Colorectal Cancer Derived From Sessile Serrated Adenoma. Am J Gastroenterol [Internet]. 2012 Mar;107(3):460- 9
• Participants in the Paris Workshop. The Paris endoscopic classification of superficial neoplastic lesions: esophagus, stomach, and colon. Gastrointest Endosc [Internet]. 2003 Dec;58(6):S3-43.
• Dixon MF. Gastrointestinal epithelial neoplasia: Vienna revisited. Gut [Internet]. 2002 Jul 1;51(1):130-1.
• Harris PA, Taylor R, Minor BL, Elliott V, Fernandez M, O'Neal L, et al. The REDCap consortium: Building an international community of software platform partners. J Biomed Inform [Internet]. 2019 Jul;95:103208
• Corley DA, Jensen CD, Marks AR, Zhao WK, Lee JK, Doubeni CA, et al. Adenoma Detection Rate and Risk of Colorectal Cancer and Death. N Engl J Med [Internet]. 2014 Apr 3;370(14):1298-306

Study record dates

Study Major Dates

• Study Start (Actual): February 1, 2025
• Primary Completion (Estimated): February 1, 2026
• Study Completion (Estimated): December 1, 2026

Study Registration Dates

• First Submitted: May 22, 2025
• First Submitted That Met QC Criteria: July 4, 2025
• First Posted (Actual): July 15, 2025

Study Record Updates

• Last Update Posted (Actual): July 16, 2025
• Last Update Submitted That Met QC Criteria: July 15, 2025
• Last Verified: July 1, 2025

More Information

Terms related to this study

• Keywords: Colonoscopy; Artificial Intelligence; Adenoma; Colorectal lesions
• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Genetic Diseases, Inborn; Intestinal Diseases; Neoplasms by Histologic Type; Gastrointestinal Neoplasms; Digestive System Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Intestinal Neoplasms; Rectal Diseases; Neoplasms, Glandular and Epithelial; Colonic Diseases; Adenoma; Neoplastic Syndromes, Hereditary; Adenomatous Polyps; Intestinal Polyposis; Colorectal Neoplasms; Adenomatous Polyposis Coli
• Other Study ID Numbers: 64060322.7.0000.0068

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: We do not plan to share Individual Participant Data (IPD) with other researchers due to privacy concerns and the nature of the study

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No