Abstract: OBJECTIVE To explore the influencing factors for surgical site infection (SSI) in elderly patients with colorectal cancer (CRC) after surgery, and to construct and validate a nomogram prediction model. METHODS A total of 1 268 elderly patients with CRC admitted to Liaocheng People's Hospital from Jan. 2021 to May 2025 were selected as the study subjects and randomly assigned to a model training set (n=888 cases) and a validation set (n=380 cases) in a 7∶3 ratio. LASSO-logistic regression was used for variable selection, and a nomogram model was constructed. Receiver operating characteristic (ROC) curves and calibration curves were plotted to internally validate the model performance. RESULTS Diabetes mellitus (OR=2.857, 95%CI: 1.695-4.815), ASA class III (OR=2.081, 95%CI: 1.210-3.580), multiple tumors (OR=5.613, 95%CI: 2.745-11.479), rectal tumors (OR=3.086, 95%CI: 1.809-5.265), carbohydrate antigen 19-9 (CA19-9) >39 U/ml (OR=3.516, 95%CI: 2.026-6.103) and operation duration (OR=1.519, 95%CI: 1.179-1.957) were identified as risk factors for SSI in elderly patients with CRC after surgery. CD₄⁺/CD₈⁺ ratio (OR=0.443, 95%CI: 0.241-0.813), serum albumin (OR=0.901, 95%CI: 0.855-0.950) and elective surgery (OR=0.109, 95%CI: 0.032-0.375) were identified as protective factors for SSI in elderly patients with CRC after surgery. Based on the aforementioned indicators, a nomogram model was constructed. The area under the curve (AUC) of the validation set was 0.797 (95%CI: 0.717-0.865), indicating good discriminatory power of the model. The Hosmer-Lemeshow goodness-of-fit test showed that the model had good accuracy and consistency (χ²=6.315, P=0.097). CONCLUSIONS The nomogram prediction model constructed based on LASSO-logistic in this study has good predictive value, which is helpful for early identification of high-risk patients for SSI before surgery and implementation of targeted infection control measures, optimizing perioperative management.