Answers are grounded in this paper and cite their sources.
Purpose Positive circumferential resection margin (CRM) is an important oncological quality indicator in rectal cancer surgery. This study aimed to explore factors associated with CRM positivity after transanal total mesorectal excision (taTME) using data from a multicenter registry. Methods Patients with rectal cancer who underwent primary taTME between 2017 and 2024 were identified from the Chinese TaTME Registry Collaborative. The primary outcome was pathological CRM positivity. Nine supervised machine learning algorithms were evaluated, including logistic regression, elastic net, decision tree, random forest, XGBoost, radial support vector machine, multilayer perceptron, LightGBM, and k-nearest neighbors. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), and model interpretation was performed using SHapley Additive exPlanations. Results A total of 1,625 patients from 32 institutions were included, and the CRM positivity rate was 2.77%. In the validation cohort, the radial support vector machine model showed the highest apparent AUC of 0.84. SHAP analysis identified pathological N stage, threatened mesorectal fascia on preoperative MRI, and intersphincteric resection as the most influential variables. Conclusion This exploratory analysis identified clinically plausible factors associated with CRM positivity after taTME. Because the models included intraoperative and postoperative variables, they should not be interpreted as preoperative decision-support tools. Further studies using preoperative-only variables and external validation are required.
No takes yet. Share an insight, caveat, or question.
Wei et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: