Endoscopy · Colonoscopy CADe
CADDIE
Olympus Corporation (Odin Medical Ltd.)
The first cloud-based CADe system cleared by the FDA and CE-marked under MDR, with a 7.3-percentage-point absolute ADR gain and a 93 % relative increase in large-adenoma detection in the 841-patient EAGLE randomised trial.
Performance Metrics
Clinical Evidence
The EAGLE study (NCT05730192) was an eight-centre, four-country European RCT enrolling 841 screening and surveillance patients (417 CADe-arm, 424 standard-of-care arm). The primary endpoint — adenoma detection rate in the screening/surveillance population — showed a 7.3 percentage-point absolute improvement with CADDIE versus standard colonoscopy. Secondary endpoints demonstrated a 93 % relative increase in large (>10 mm) adenomas detected per colonoscopy, a 57 % relative increase in non-polyploid adenomas, and a 230 % relative increase in sessile serrated lesions (SSLs). No increase in unnecessary resections was observed. The paper was published in npj Digital Medicine (December 2025).
| Study | Design | n | Sensitivity | Specificity | AUC | Published |
|---|---|---|---|---|---|---|
| Kader R, Hassan C, Lanas Á, et al. (EAGLE Trial Investigators) | RCTRCT | 841 | — | — | — | npj Digital Medicine, Dec 2025 |
Clinical Pulse
Verified clinician sentiment
Verified clinician reviews launching soon · Apply to contribute →
Reviews are signed by clinicians verified against their regulator's public register.
Inside the algorithm
Editorial featureHow CADDIE reaches a verdict.
Five stages — from raw input to verdict — drawn from manufacturer documentation and the public regulatory record.
- INGEST
- NORMALISE
- DETECT
- LOCALISE
- VERDICT
Stage 01 · INGEST
Live colonoscopy video streams to a cloud-based detector.
During a standard white-light colonoscopy, the live video from the endoscope is streamed to CADDIE's cloud service. No additional hardware is attached to the endoscope and no modification of the imaging stack is required — the system runs entirely on the inbound video feed.
The cloud delivery model is itself part of the regulatory story: CADDIE was one of the first cloud-based systems to clear the FDA 510(k) pathway (K240044) and CE MDR.
Input
Live white-light colonoscopy video
Inside the Auris+ Listing
Five more sections complete this device’s Auris+ Listing.
Decision Ledger
ProPro unlocks a private, cross-vendor log of every case you read on this device — what the AI called, what you concluded, and a one-line reason if you overrode it. Ready for the EU AI Act's deployer logging obligations when they land in 2028.
Clinical Evidence Deep Dive
ProPro unlocks the structured clinical-evidence summary — study count, target patient population, and a tabular accuracy-metrics view drawn from peer-reviewed sources.
Peer-Reviewed Publications
ProPro unlocks the curated peer-reviewed publication list with PubMed cross-links — the citation backbone of every editorial verdict.
Post-Market & Regulatory Conditions
ProPro unlocks the post-market surveillance summary, recall record, and the conditions of approval that bound real-world use.
AI Algorithm Version History
ProPro unlocks the chronological record of algorithm version changes — what changed when, drawn from manufacturer changelogs and regulatory filings.
Regulatory Approvals
Safety Record
No device recalls or FDA safety alerts specific to CADDIE have been identified as of the review date. The EAGLE trial reported no increase in unnecessary polypectomies, addressing a key concern regarding CADe-induced over-treatment. The system is limited to standard white-light endoscopy imaging; use outside that modality is not cleared.
Intended Use & Indications
CADDIE is indicated to assist qualified gastroenterologists in identifying and localising suspected colorectal polyps during standard white-light colonoscopy. The system analyses live video streamed to the cloud and returns real-time detection overlays; it is not intended to replace endoscopist judgement or to characterise lesion histology.