Clinical Validity Verification on Diagnostic Assistance for Presence and Severity of Colorectal Cancer and Polyps Using Artificial Intelligence-based Medical Device Software Endoscopic Imaging Assistance

NCT07744607 | Completed

• 1 other identifier: Ainex-CRC-01
• Study Type: observational
• Target: 1,114
• Locations: 1 country
• Sites: 1

Brief Summary

This completed retrospective study evaluated the clinical performance of ENAD-CADx-01, an artificial intelligence-based medical device software intended to assist healthcare professionals in characterizing colorectal lesions in colonoscopy images. Previously collected colonoscopy images and corresponding histopathological results from Asan Medical Center were analyzed. The performance of ENAD-CADx-01 was evaluated based on its sensitivity, specificity, and overall accuracy in classifying colorectal lesions as neoplasm, hyperplastic polyp, or sessile serrated lesion. No participants were prospectively enrolled, and no study-related intervention was performed.

Conditions

Colorectal Neoplasms; Colonic Polyps; Hyperplastic Polyps; Sessile Serrated Lesions

Keywords

Computer-Aided Diagnosis; Artificial Intelligence; Colonoscopy; Colorectal Lesion Characterization; Medical Device Software

Outcome Measures

Primary Outcomes (6)

• Clinical Sensitivity for Neoplasm

  Up to 4 weeks

• Clinical Specificity for Neoplasm

  Up to 4 weeks

• Clinical Sensitivity for Hyperplastic Polyps

  Up to 4 weeks

• Clinical Specificity for Hyperplastic Polyps

  Up to 4 weeks

• Clinical Sensitivity for Sessile Serrated Lesions

  Up to 4 weeks

• Clinical Specificity for Sessile Serrated Lesions

  Up to 4 weeks

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consisted of adults aged 18 years or older who underwent colonoscopy at Asan Medical Center and had previously collected colonoscopy images of colorectal lesions with corresponding histopathological results. Eligible images were retrospectively analyzed to evaluate the clinical performance of ENAD-CADx-01 in classifying lesions as neoplasm, hyperplastic polyp, or sessile serrated lesion.

You may qualify if:

• Participants aged 18 years or older at the time of colonoscopy.
• Participants who underwent colonoscopy at Asan Medical Center and had colorectal lesion images available for retrospective analysis.
• Participants with corresponding histopathological results available as the reference standard.
• Colonoscopy images that met the predefined image quality requirements for analysis by ENAD-CADx-01.

You may not qualify if:

• Participants without corresponding histopathological results for the colorectal lesion.
• Images with insufficient quality for analysis, including severe blur, obstruction, or inadequate visualization of the lesion.
• Images or records with missing or insufficient data required for the clinical performance analysis.
• Lesions that did not meet the predefined target lesion categories or other eligibility requirements specified in the clinical investigation plan.

Sponsors & Collaborators

• Ainex Corporation: lead

Study Sites (1)

Asan Medical Center

Seoul, Seoul, 05505, South Korea

Location

MeSH Terms

Conditions

Colorectal Neoplasms; Colonic Polyps

Condition Hierarchy (Ancestors)

Intestinal Neoplasms; Gastrointestinal Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Colonic Diseases; Intestinal Diseases; Rectal Diseases; Intestinal Polyps; Polyps; Pathological Conditions, Anatomical; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: July 29, 2026
• First Posted: August 4, 2026
• Study Start: January 20, 2025
• Primary Completion: February 17, 2025
• Study Completion: February 17, 2025
• Last Updated: August 4, 2026

Record last verified: 2026-08

Data Sharing

• IPD Sharing: Will not share

Locations

KR (1)