Predictive Modeling for Colorectal Polyps in Average-Risk Asymptomatic Adults: Optimizing Screening Colonoscopy Decisions

Abstract Objective: To develop a risk prediction model for colorectal polyps in asymptomatic individuals and provide evidence-based guidance for colonoscopy screening prioritization within health examination cohorts. Methods: We retrospectively analyzed 1,619 participants undergoing health examinations at Ningbo Zhenhai Lianhua Hospital (October 2022-December 2024). Based on endoscopic findings, 847 individuals with colorectal polyps were assigned to the case group, and 772 polyp-free individuals comprised the control group. Risk factors were identified through univariate and multivariate logistic regression analyses. A predictive nomogram was constructed using significant multivariate predictors. Model discrimination was evaluated via the receiver operating characteristic (ROC) curve and concordance index (C-index), while clinical utility was assessed using decision curve analysis (DCA). Results: Multivariate analysis identified the following independent risk factors (all PConclusion: This study establishes a clinically applicable nomogram with moderate predictive performance for colorectal polyps, which may facilitate risk-stratified colonoscopy screening decisions in health examination populations.