A Nationwide study of Artificial Intelligence in Adenoma Detection: Interim results from NAIAD trial

Aims The detection and resection of adenomatous polyps during colonoscopy decreases the incidence of colorectal cancer and associated mortality, with adenoma detection rate (ADR) being a key performance indicator. While higher ADR is associated with lower post-colonoscopy colorectal cancer (PCCRC) rates, the latter varies significantly across the UK and the true ‘baseline’ ADR is unknown. Meeting the rising demand for high quality colonoscopy is a significant challenge, but the emergence of artificial intelligence presents a potential solution. The use of computer assisted detection (CADe) is associated with a significant improvement in ADR across multiple clinical trials, but real-world performance data is lacking. We sought to evaluate effect on adenoma detection of implementing CADe in a ‘real-world’ setting, in the largest such study to date.

Methods This was a randomised, stepped-wedge, open-label trial, using the GI Genius™ (GIG) module, powered to measure the site effect of CADe. A mix of District General Hospitals (DGH) and Teaching Hospitals (TH) were included, with an emphasis on ‘non-expert’ colonoscopists (lifetime colonoscopy<2000 at study start). ‘Expert’ colonoscopists were eligible (lifetime colonoscopy>2000 and ADR>40%).

Data collection was divided into three, 3-month phases: phase 1, baseline data collection with no CADe; phase 2, the intervention phase, where GIG-CADe was active; phase 3 where GIG-CADe was removed.

Data will be forthcoming from 29 hospitals (England, Scotland, and Wales), n=124 colonoscopists and n>5000 patients, but we report herein results from the first 8 sites to complete the trial.

All patients undergoing routine (non-BCSP) colonoscopy were eligible, but those having colonoscopy for polyp or IBD surveillance were excluded. The study design was as close to real world practice as possible, with no other changes in procedure or technique.

Results Across the 8 sites involved (2 TH), 34 endoscopists (64.7% non-expert vs 35.3% expert) and 1418 patients (56.4±16.9 years; 49.5% female) were eligible for analysis. Comparative results (univariate analysis) through the three study phases are reported in Table 1. When adjusted for bowel preparation and the endoscopists’ experience, there was a 9.53% increase in ADR in the CADe group (r²=0.16; p=0.01).

Conclusions NAIAD is the largest trial of CADe to date and, in this interim analysis, establishes a baseline ADR of approximately 27.0% outside of screening programmes. The use of GIG-CADe is associated with a significant increase in ADR, but this returns to baseline when the device is switched off. Further analysis of our result will inform the implementation of CADe in routine practice.

 

MissingLinkText

Conflicts of Interest

Authors do not have any conflict of interest to disclose.

Publication History

Article published online:
27 March 2025