AI Colonoscopy: Clinical and Economic Benefits - EMJ

This site is intended for healthcare professionals

AI-Assisted Colonoscopy Improves Outcomes and Saves Costs

Author:
Doctor holding endoscope.

Key Summary:

  • AI-assisted colonoscopy was found to improve outcomes and reduce costs in symptomatic patients.
  • The model estimated £69 savings per person and a 0.046 gain in quality-adjusted life years.
  • Findings supported the clinical and economic value of AI-assisted colonoscopy, although uncertainty remained.

AI-assisted colonoscopy was associated with improved clinical outcomes and lower healthcare costs in a simulated population of symptomatic patients undergoing investigation for suspected colorectal cancer (CRC) in England. The economic evaluation found that the GI Genius (GIG) system could increase adenoma detection rates, reduce subsequent CRC incidence, and generate cost savings compared with standard colonoscopy alone.

Evaluating the Economic Impact of AI-Assisted Colonoscopy

the study developed a patient-level simulation model to assess the long-term clinical and economic implications of introducing GIG-assisted colonoscopy into the diagnostic pathway. The analysis focused on symptomatic patients with suspected CRC in England and adopted a National Health Service and Personal Social Services perspective over a lifetime horizon.

Model inputs were informed by the NAIAD trial, which investigated the effect of GIG on adenoma detection rates compared with conventional colonoscopy. Researchers conducted a base case analysis alongside scenario analyses and probabilistic sensitivity analysis (PSA) to evaluate cost-effectiveness and uncertainty surrounding the findings.

Cost Savings and Improved Clinical Outcomes

The base case analysis indicated that GIG-assisted colonoscopy was cost-saving, generating an estimated £69 reduction in costs per person alongside a gain of 0.046 quality-adjusted life years (QALYs). These improvements were primarily attributed to increased adenoma detection and a subsequent reduction in CRC incidence.

Additional scenario analyses explored uncertainties relating to colonoscopy sensitivity, outcomes among patients initially undiagnosed, differences between experienced and less experienced endoscopists, and the overall costs of implementing GIG. Findings remained broadly consistent with the base case, with no substantial changes to estimated costs or QALY outcomes.

Uncertainty Remains Around Cost-Effectiveness

Despite the favourable base case findings, the indicated that GIG was cost-effective in 53% of simulations at a willingness-to-pay threshold of £20,000 per QALY gained.

Researchers attributed this uncertainty to the relatively small differences in QALYs between the two groups. Consequently, even minor variations in outcomes across individual simulations produced considerable fluctuations in the incremental cost-effectiveness ratio.

Overall, the findings suggest that AI-assisted colonoscopy could offer both economic and clinical benefits when investigating symptomatic patients with suspected CRC. However, the considerable uncertainty identified in the PSA highlights the importance of interpreting the cost-effectiveness estimates cautiously.

Reference

Curtis-Gretton et al. The economic and clinical impact of an AI-assisted tool for colonoscopy to support diagnosis of colorectal cancer in symptomatic patients in England. BMC Digit Health. 2026;4:79.

Featured Image: sudok1 on Adobe Stock.

Each article is made available under the terms of the Creative Commons Attribution-Non Commercial 4.0 License.

Rate this content's potential impact on patient outcomes

Average rating 0 / 5. Vote count: 0

No votes so far! Be the first to rate this content.