Comprehensive Model Predicts CRC Risk After Polypectomy

A comprehensive colorectal cancer (CRC) risk prediction model that considered a number of patient characteristics was superior to a model that considered polyp characteristics alone in predicting postpolypectomy CRC diagnosis, according to a study published in The American Journal of Gastroenterology.

“Colonoscopy surveillance guidelines categorize individuals as high or low risk for future CRC based primarily on their prior polyp characteristics, but this approach is imprecise, and consideration of other risk factors may improve postpolypectomy risk stratification,” wrote corresponding author Jeffrey K. Lee, MD, MPH, of Kaiser Permanente Northern California, Oakland, California, and coauthors in the study introduction.

Researchers developed and tested a model for postpolypectomy CRC risk prediction that factored in a patient’s age, diabetes diagnosis, baseline colonoscopy indication, and prior polyp findings, including adenoma with advanced histology, polyp size of 10 mm or greater, and sessile serrated adenoma or traditional serrated adenoma. They compared its performance with a model that solely featured polyp findings.

The study included data for a total 95,001 patients who underwent a baseline colonoscopy with removal of a conventional adenoma between 2004 and 2016. Among the 66,500 patients in the model development cohort, 495 were subsequently diagnosed with CRC. Among the 28,501 patients in the internal validation cohorts, 141 were diagnosed with CRC.

The comprehensive model was more accurate at predicting postpolypectomy CRC diagnosis than the model based on polyp findings alone, the study found. In the development cohort, areas under the curve were 0.71 for the comprehensive model and 0.61 for the polyp-findings-alone model. In the validation cohort, areas under the curve were 0.70 for the comprehensive and 0.62 for the polyp-findings-alone models.

Reference:

Lee JK, Jensen CD, Udaltsova N, ET AL. Predicting risk of colorectal cancer after adenoma removal in a large community-based setting. Am J Gastroenterol. 2024;119(8):1590-1599. doi: 10.14309/ajg.0000000000002721