Construction of a Prediction Model for Metachronous Colorectal Adenoma

Construction of a Prediction Model for Metachronous Colorectal Adenoma

The study aimed to explore the independent risk factors for the metachronous colorectal adenoma after endoscopic resection, and construct the prediction model of metachronous colorectal adenoma, in order to provide theoretical basis for postoperative follow-up time of patients, and allocate limited medical resources.

A large cohort of eligible patients were included in the analysis, and classified into derivation and validation cohorts at a ratio of 7:3. Demographic and clinicopathological characteristics of participants were utilized to develop a prediction model for metachronous colorectal adenoma. In the derivation cohort, the LASSO regression method was applied to filter variables and multivariate logistic regression analysis was used to identify important predictors.A prediction model was established based on the results of multivariate logistic regression analysis. The predictive performance of the model was evaluated with respect to its discrimination, calibration and clinical usefulness.

Inclusion Criteria:

• Patients aged ≥18 and ≤75 years old. Patients with complete data on demography and clinicopathology.

Exclusion Criteria:

• Patients with a history of inflammatory bowel disease, enterophthisis, familial adenomatous polyposis, P-J syndrome and intestinal lymphoma.

Patients with a previous history of colorectal neoplasm. Patients with a history of severe systemic diseases. Lack of complete clinical data for analysis.