Development and validation of a nomogram for predicting venous thromboembolism risk in colorectal cancer patients undergoing postoperative chemotherapy.

Cancer-associated venous thromboembolism (VTE) is a common and life-threatening complication in patients with colorectal cancer (CRC) following surgery. This study aims to develop and validate a nomogram for accurately predicting the risk of VTE in CRC patients undergoing postoperative chemotherapy. This study included a total of 1,397 CRC patients who received postoperative chemotherapy at Chongqing University Cancer Hospital. The patients were randomly divided into training cohort and validation cohort in a 7:3 ratio. LASSO regression and multiple logistic regression were employed to identify independent risk factors for VTE and construct a nomogram. The model performance was evaluated using receiver operating characteristic (ROC) curves, area under the curve (AUC), calibration curves and decision curve analysis (DCA). Among the patients, 116 cases (8.30%) developed VTE. Six independent predictors included: Age, Karnofsky performance status (KPS), Surgical level, leukocyte count (WBC), lymphocyte count (LYM), and D-dimer levels. The nomogram demonstrated excellent discriminative ability, with AUCs of 0.868 (95% CI: 0.820-0.915) and 0.831 (95% CI: 0.748-0.914) in the training and validation cohorts, respectively. Calibration curves showed strong agreement between predicted and actual probabilities in both cohorts. DCA confirmed the model's clinical net benefit across a wide range of threshold probabilities. We developed and validated a nomogram incorporating six available clinical variables, which accurately assesses the risk of VTE in CRC patients undergoing postoperative chemotherapy, while demonstrating significant clinical value.