Nomogram for the Prediction of Delayed Colorectal Post-Polypectomy Bleeding.

Area of Science:

• Gastroenterology
• Colorectal Surgery
• Medical Informatics

Background:

• Delayed post-polypectomy bleeding (PPB) is a common complication following colorectal polypectomy.
• Accurate prediction of PPB risk is crucial for patient management.

Purpose of the Study:

• To develop and validate a novel nomogram-based predictive model for delayed PPB.
• To identify key risk factors associated with delayed PPB.

Main Methods:

• A cohort of 2494 patients undergoing colonoscopic polypectomy was analyzed.
• Least absolute shrinkage and selection operator (LASSO) regression identified predictive variables.
• Multivariate logistic regression and bootstrapping were used for model development and validation.

Main Results:

• The final model identified 6 predictors: age, gender, polyp location, polyp morphology, antithrombotic use, and polypectomy modality.
• The nomogram demonstrated good predictive performance with an AUC of 0.838.
• Internal validation confirmed the model's reliability (AUC: 0.824) with acceptable calibration and clinical utility.

Conclusions:

• The developed nomogram is a valuable tool for predicting delayed PPB risk.
• This model can aid clinicians in optimizing preoperative decision-making and treatment strategies.
• Further research may refine the model for broader clinical application.