Experts in the US are using AI to improve the quality of colonoscopy procedures, monitor surgeons’ performance, and reduce patients’ risk of developing colorectal cancer.
Colonoscopies are a key tool in preventing colon cancer. They allow surgeons to detect and remove precancerous polyps before they become cancerous.
While increasing access to screening is important, the quality of each procedure is equally critical.
Juan Carlos Garcia, medical director of gastroenterology clinical services at UC Davis Health, said: ‘Not all colonoscopies are equal. The goal isn’t just to perform a colonoscopy, but to perform a high-quality colonoscopy that detects precancerous lesions early.’
One of the most important measures of colonoscopy quality is the adenoma detection rate (ADR). ADR represents the percentage of procedures in which a surgeon finds adenomas, a common type of precancerous polyp.
Research shows that for every 1% increase in a surgeon’s adenoma detection rate, their patient’s risk of developing colorectal cancer after a colonoscopy drops by about 3% and dying from colorectal cancer by approximately 5%.
Garcia said: ‘The data clearly shows that early detection leads to better outcomes. Our goal is to identify areas for improvement and make sure patients receive the highest-quality care possible.’
Until recently, accurately tracking ADR required manual data entry. After each colonoscopy, pathologists had to manually flag findings such as tubular adenomas in the electronic medical record. This extra step sometimes led to missing or incomplete data, making consistent performance measurement difficult.
To address this challenge, gastroenterologists at UC Davis Health implemented an AI-supported tool within Epic, the health system’s electronic medical record. The tool automatically analyses pathology reports and identifies the number of adenomatous polyps detected.
By removing the need for manual input, the system produces more accurate, complete and reliable data.
Garcia added: ‘This tool allows us to measure performance in real time. It ensures nothing is missed and gives us a more accurate picture of how well we are doing, as individual physicians and as an institution.’
The tool is designed to support quality improvement.
Surgeons can view their own detection rates and compare them with national benchmarks and department averages.
When detection rates fall below approved benchmarks, the department collaborates to identify opportunities for improvement.
These may include changes to technique, withdrawal time or equipment, while taking into consideration patient factors such as age and cancer risk.
For patients, higher-quality colonoscopies mean a lower chance of developing colon cancer after a screening.
Garcia explained: ‘As an academic medical centre, we are always advancing care through research and innovations. This tool improves patient safety and helps generate insights that can improve care.’
Garcia expects similar tools to become increasingly important as health systems, insurers and referring providers place greater emphasis on quality measures when guiding patient care.
‘When even one patient falls through the cracks, the human cost is enormous. Using tools like this helps ensure fewer patients ever reach that point.’
