Objective:To identify the factors influencing acute kidney injury (AKI) following abdominal surgery in elderly patients and develop a predictive model based on the LASSO regression.Methods:The medical records of American Society of Anesthesiologists (ASA) Physical Status classificationⅠ-Ⅳ patients, aged ≥60 yr, with operation time ≥ 2 h, undergoing elective abdominal surgery under anesthesia in the General Hospital of Ningxia Medical University from May 2021 to May 2023, were retrospectively collected. AKI was diagnosed based on the Kidney Disease: Improving Global Outcomes organization guidelines. The patients were divided into 2 groups based on whether AKI occurred within 7 days after surgery: AKI group and non-AKI group. The least absolute shrinkage and selection operator algorithm was performed to reduce the dimension of unbalanced factors between AKI group and non-AKI group and the known risk factors for AKI. A nomogram prediction model was developed by integrating the optimized features derived from the LASSO regression model into multivariate logistic regression analysis. Internal validation was performed using the Bootstrap method, and the predictive ability and accuracy of the prediction model were assessed through the calibration curve, area under the receiver operating characteristic curve, Brier index and decision curve analysis.Results:Five hundred and ninety patients were finally included in this study, with 62 cases (10.5%) suffered postoperative AKI. The results of multivariate logistic regression analysis showed that increased age ( OR=1.06, 95% confidence interval [ CI] 1.01-1.11, P=0.048), higher ASA classification ( OR=2.32, 95% CI 1.21-4.45, P=0.011), preoperative coronary heart disease ( OR=1.89, 95% CI 1.01-3.61, P=0.049), and longer surgical duration ( OR=1.01, 95% CI 1.01-1.02, P=0.004) were risk factors for AKI after abdominal surgery, and the intraoperative use of dexmedetomidine ( OR=0.22, 95% CI 0.08-0.59, P=0.003) and increased postoperative albumin concentrations ( OR=0.91, 95% CI 0.85-0.98, P=0.017) were protective factors for postoperative AKI in elderly patients ( P<0.05). A risk prediction model was constructed based on the 9 identified factors of age, ASA classification, Charlson Comorbidity Index, preoperative coronary heart disease, preoperative hemoglobin concentration, preoperative estimated glomerular filtration rate, surgical duration, intraoperative use of dexmedetomidine and postoperative albumin concentration. A nomogram was plotted to visualize the model and verify it, showing that the Brier score of the model was 0.079, with a discrimination of 0.844, sensitivity of 84.4%, and specificity of 70.2%. Two hundred bootstrap resamples were used for internal validation, yielding a receiver operating characteristic curve of 0.821 with a 95% confidence interval of 0.79 to 0.90. The clinical decision curve indicated significant net benefits when the threshold probability of the model was between 0.03 and 0.45. Conclusions:Increased age, higher ASA classification, preoperative coronary heart disease, and longer surgical duration are risk factors, and the intraoperative use of dexmedetomidine and increased postoperative albumin concentrations are protective factors for postoperative AKI in elderly patients. The AKI prediction model following abdominal surgery developed based on age, ASA classification, Charlson Comorbidity Index, preoperative coronary heart disease, preoperative hemoglobin concentration, preoperative estimated glomerular filtration rate, surgical duration, intraoperative use of dexmedetomidine and postoperative albumin concentration has good predictive value in elderly patients.