Objective: Surgical site infection (SSI) is a common and serious complication after scoliosis surgery in adults. This study aims to use a clinical prediction model to assess the likelihood of postoperative SSI, with the goal of early identification of patients at high risk, thereby aiding in the improvement of perioperative management strategies. Methods: This study retrospectively collected data from 743 adult patients who underwent scoliosis surgery at the Second Affiliated Hospital Zhejiang University School of Medicine from April 2013 to December 2023. Two methods (univariate and multivariate Logistic regression, and LASSO regression) were used to select predictive variables. The selected variables were then used to establish a prediction model for postoperative SSI through multivariate Logistic regression, and the model was visualized using a nomogram. The performance of the clinical prediction model was assessed by plotting the ROC curve, calibration curve, and clinical decision analysis curve. Results: Among the 743 patients in the study, a total of 57 cases developed postoperative SSI. Variable selection and model construction were performed using univariate and multivariate Logistic regression as well as LASSO regression. After comparison, the model built with predictive variables selected through LASSO regression analysis was chosen. The predictive model included variables such as preoperative hemoglobin, diabetes mellitus, Cobb angle, and perioperative iron therapy. Internal validation was conducted using the Bootstrap method, with the model's AUC value being 0.846 (95% CI: 0.785, 0.906), sensitivity of 0.684, and specificity of 0.843. The calibration curve and clinical decision curve indicated that the prediction model had good calibration and clinical utility. Conclusions: This study has established a predictive model for surgical site infection (SSI) following adult scoliosis surgery, accompanied by a visually intuitive nomogram. The model incorporates four predictive variables that can estimate the probability of postoperative SSI, potentially offering clinical value in the prevention and treatment of postoperative SSI.