European endoscopists weakly back CADe in screening colonoscopy

ESGE's panel voted 13 to 6 for a weak recommendation of CADe in screening and surveillance colonoscopy. In 44 pooled trials, adenomas were found in 44.7% of patients with CADe against 36.7% without.

  • 2 for a person

    In the 44 pooled trials, adenomas were found in 44.7% of patients with CADe against 36.7% without.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Partly reported benefit.
Evidence

foundstudiedreportedclaimed

An independent assessment report supports the benefit.

Compared with

Colonoscopy without CADe in 44 randomized trials. Measured.

Without the system
36.7%
With it
44.7%
The system’s part
The pooled randomized trials compared colonoscopy with and without CADe, which isolates the software's effect on detection. ESGE describes the systems as artificial intelligence, and the review it relied on compared them by neural network architecture. No trial measured cancer incidence or deaths, so the cancer effects come from a model.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
Computer-aided detection (CADe) colonoscopy systems in the 44 trials behind ESGE's position, including GI Genius, CAD EYE and EndoScreener
Made by
Medtronic (GI Genius), Fujifilm (CAD EYE), Wision AI (EndoScreener) and other makers
Used by
Endoscopy services in the 44 randomized trials that the evidence pooled, with screening and surveillance services in Europe as intended users
Where
Multiple countries (trials), with a position for Europe
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Peer-reviewed study, by authors with no tie to the system.

    Soleymanjahi S, Huebner J, Elmansy L, et al. Artificial Intelligence-Assisted Colonoscopy for Polyp Detection: A Systematic Review and Meta-analysis. Annals of Internal Medicine 2024;177:1652-1663. doi:10.7326/ANNALS-24-00981. Results, sensitivity analysis by CADe platform (archived copy). No funding was received.

    On comparing the performance across different CADe platforms, we found a trend toward increased overall ADR in studies using a CADe that was developed on the basis of You Only Look Once (YOLO) (https://arxiv.org/abs/1506.02640) (944 of 3279 [29%] vs. 740 of 3315 [22%], RR = 1.36 [CI, 1.14 to 1.62]), compared with studies using GI Genius (Medtronic) (2105 of 3830 [55%] vs. 1906 of 3819 [50%], RR = 1.16 [CI, 1.00 to 1.34]) (Supplement Figure 3). Studies using Fujifilm CAD EYE (1479 of 2796 [53%] vs. 1043 of 2399 [43%], RR = 1.21 [CI, 1.10 to 1.34]) and EndoScreener (developed based on SegNet) (729 of 2332 [31%] vs. 596 of 2331 [26%], RR = 1.22 [CI, 1.11 to 1.35]) exhibited similar performance in ADR.

  2. Assessment report, by authors with no tie to the system.

    European Society of Gastrointestinal Endoscopy. Bretthauer M, Ahmed J, Antonelli G, et al. Use of computer-assisted detection (CADe) colonoscopy in colorectal cancer screening and surveillance: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement. Endoscopy 2025;57(6):667-673, published online 27 March 2025. doi:10.1055/a-2543-0370. Abstract, Recommendation.

    The panel believes that most well-informed patients who have already decided to undergo colonoscopy for screening or surveillance would favor CADe assistance during colonoscopy. This is due to the potential benefits, although limited, of reduction in colorectal cancer incidence and mortality.

  3. Assessment report, by authors with no tie to the system. Context or contrary evidence.

    Foroutan F, Vandvik PO, Helsingen LM, et al. Computer aided detection and diagnosis of polyps in adult patients undergoing colonoscopy: a living clinical practice guideline. BMJ Rapid Recommendations, BMJ 2025;388:e082656. PMID 40147837. Abstract, Recommendation.

    For adults who have agreed to undergo colonoscopy, we suggest against the routine use of CADe (weak recommendation).

Details

AI system

Workflow

CADe analyzed the live colonoscopy video and flagged possible polyps for the endoscopist. The trials randomized patients to colonoscopy with or without CADe.

Follow-up

Conditions for replication

Patients undergo colonoscopy for primary screening, after a positive fecal immunochemical test or for polyp surveillance. Patients accept more surveillance colonoscopies and more removal of polyps that would not have become cancer.

Entry details

Sector

Healthcare.

Purpose

Medtronic, Fujifilm, Wision AI and other makers built CADe systems to flag possible polyps to the endoscopist in real time during colonoscopy.

30 more questions not yet checked

model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). European endoscopists weakly back CADe in screening colonoscopy (AIBD-1125). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1125.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions