A novel nomogram for the prediction of perforation during endoscopic submucosal dissection for colorectal neoplasms

Abstract Purpose High perforation risk hinders the widespread adoption of endoscopic submucosal dissection (ESD) for colorectal neoplasms. This study was performed to determine the predictors of colorectal ESD-induced perforation and develop a predictive model. Methods A total of 1020 colorectal neoplasms in 963 patients were retrospectively enrolled from January 2011 to December 2021 in a single tertiary center as the derivation cohort. We identified independent risk factors for perforation using univariate analysis and multivariate logistic regression. A nomogram was developed based on the logistic regression model and prospectively applied to 266 colorectal neoplasms as the validation cohort. The performance of the predictive model was evaluated with the receiver operating characteristic curve, calibration plot, and decision curve analysis. Results Independent predictors for colorectal ESD-induced perforation were tumor located in the colon (left colon, odds ratio [OR] 2.96, P = 0.006; right colon, OR 2.14, P = 0.040), tumor size ≥ 40 mm (OR 2.27, P = 0.012), LST type (OR 2.57, P = 0.016), submucosal fibrosis (OR 2.96, P < 0.001) and procedure time ≥ 60 min (OR 3.05, P = 0.001). The nomogram model incorporating the above predictors performed well in both the derivation and validation cohorts (area under the curve of 0.796 and 0.797, respectively). Decision curve analysis demonstrated that the clinical benefit of the nomogram was favorable. Conclusions The novel nomogram, developed and prospectively validated, incorporating tumor size, location, morphology, submucosal fibrosis, and procedure time, can successfully predict perforation during endoscopic submucosal dissection for colorectal neoplasms.