The EAGLE Trial, a multicenter randomized controlled study evaluating the Olympus CADDIE™ device, has demonstrated that cloud-based artificial intelligence can significantly enhance the detection of high-risk colorectal lesions during colonoscopy. Published in npj Digital Medicine, the study represents a pivotal development in computer-aided detection technology for gastrointestinal endoscopy.
Conducted across eight centers in four European countries, the trial involved 841 patients and 22 endoscopists performing screening and surveillance colonoscopies. Patients were randomized to receive either standard colonoscopy or CADDIE-assisted colonoscopy. The CADDIE™ application is the first cloud-based Computer-Aided Detection solution for real-time polyp detection during colonoscopy that has received both FDA clearance and CE marking.
Key findings from the study revealed substantial improvements in detecting clinically significant lesions. In screening and surveillance patients, use of the CADDIE™ application was associated with a 7.3% absolute increase in adenoma detection rate compared to standard colonoscopy. More importantly, the system demonstrated remarkable relative increases in detection rates for specific high-risk lesion subtypes: 93% for large adenomas (>10 mm), 57% for non-polypoid adenomas, and 230% for sessile serrated lesions (SSLs).
The clinical significance of these findings is substantial, as lesions with sessile or flat morphology are particularly difficult to detect yet can harbor clinically relevant pathology. SSLs, in particular, represent high-risk lesions whose detection is critical to reducing the risk of post-colonoscopy colorectal cancer. The ability to reliably detect SSLs is increasingly viewed as a critical quality consideration in colonoscopy, as noted in recent guidelines from the European Society of Gastrointestinal Endoscopy and the American Gastroenterological Association.
The CADDIE™ application is specifically trained on a dataset enriched in clinically relevant and hard-to-detect lesions, including flat sessile serrated lesions and large polyps. This targeted approach addresses some of the concerns raised in recent guidelines regarding unnecessary resections, as the study demonstrated increased detection of clinically relevant lesions without increasing unnecessary procedures.
Cloud deployment represents a significant innovation in medical AI implementation. The CADDIE™ application leverages cloud architecture with industry standard security controls, offering hospitals flexibility by reducing reliance on hardware and enabling subscription-based procurement models. This approach has the potential to democratize access to advanced AI tools and lays the foundation for future AI applications in endoscopy. For complete access to the EAGLE Trial study, visit https://doi.org/10.1038/s41746-025-02270-1.
Principal Investigator Rawen Kader noted that "cloud deployment can remove hardware barriers and give hospitals access to the latest AI innovations, which has the potential of improving detection of the lesions that matter most for reducing colorectal cancer risk." This sentiment was echoed by Olympus executives, who emphasized that delivering AI in real time through the cloud can help accelerate innovation and enable hospitals worldwide to benefit from evidence-based technologies.
The study's publication in a high-impact journal supports clinical adoption of the CADDIE™ device as an AI solution that can enhance detection of clinically relevant lesions without compromising safety or efficiency. As colorectal cancer remains a leading cause of cancer mortality worldwide, technologies that improve early detection of precancerous lesions represent significant advancements in preventive medicine. The EAGLE Trial results suggest that cloud-based AI systems could become standard tools in colorectal cancer screening programs, potentially reducing interval cancers and improving patient outcomes through more comprehensive lesion detection.
