Effect of Two Colonoscopy AI Systems for Colon Polyp Detection

Effect of Two Colonoscopy AI Systems for Colon Polyp Detection According to the False Positive Rates of the Systems: A Single-center Prospective Study

Status

Completed

Phases

Study type

Interventional

Source

ClinicalTrials.gov

Registry ID

NCT05089071

Enrollment

3046

Registered

2021-10-22

Start date

2021-11-01

Completion date

2022-12-31

Last updated

2023-07-27

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Adenoma, Colonoscopy, Sessile Serrated Adenoma

Keywords

endoscopist, adenoma detection rate, colonoscopy, artificial intelligence

Brief summary

Computer-aided detection (CADe) systems have been actively researched for polyp detection in colonoscopy. The investigators aim to identify the effect of two CADe systems according to the system performance on false positive rate

Detailed description

Artificial intelligence technology based on deep learning is being applied in various medical fields, and research is being actively conducted to develop computer-aided detection (CADe) systems for colonoscopies to overcome the limitation of the variance of human skills. These well-trained CADe systems demonstrated high performance for neoplastic polyp detection and reported a 44% increase in adenoma detection rate (ADR) for endoscopists. However, the level of performance in the CADe system is not clear for expert endoscopists to be useful for ADR increase. Furthermore, false positives(FPs) of the CADe system may negatively influence ADR during a screening colonoscopy. Accordingly, the investigators sought to identify the effect of the colonoscopy CADe system according to FP performance in endoscopists with various levels. The investigators hypothesized that the CADe system with low FPs would be useful to prevent the decrease in ADR in case of a high endoscopy workload according to the performance of CADe systems.

Interventions

DEVICEAssist by artificial intelligence system for colon polyp detection

Assist by artificial intelligence system for colon polyp detection

Study design

Allocation

NON_RANDOMIZED

Intervention model

PARALLEL

Primary purpose

DIAGNOSTIC

Masking

SINGLE (Outcomes Assessor)

Intervention model description

The primary outcome was the comparison of ADR between the control and AI groups according to the intervention system (SCAI vs ENAD system).

Eligibility

Sex/Gender

ALL

Age

45 Years to 100 Years

Healthy volunteers

Yes

Inclusion criteria

patient for screening or surveillance colonoscopy patients agreed with participating in the study

Exclusion criteria

patients who do not agree with participating in the study patients with a history of colon resection patients with a history of inflammatory bowel resection patients with poor bowel preparation

Design outcomes

Primary

Measure	Time frame	Description
Adenoma detection rate	12 months	proportion of colonoscopies with at least one adenoma detected overall and as detected by the physician.
Sessile serrated lesion detection rate	12 months	proportion of colonoscopies with at least one sessile serrated lesion detected overall and as detected by the physician.

Secondary

Measure	Time frame	Description
polyp detection rate	12 months	proportion of colonoscopies with at least one polyp detected overall and as detected by the physician.

Countries

South Korea

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026