Objective To analyze the risk factors of acute kidney injury (AKI) in patients with sepsis complicated by acute respiratory distress syndrome (ARDS) and to establish a predictive model for predicting the occurrence of AKI. Methods The clinical data from patients with sepsis and ARDS were extracted from the Medical Information Mart for Intensive Care (MIMIC⁃Ⅲ, Version 1.4) to be used for training and internal validation. Additionally, data were retrospectively collected from sepsis patients with ARDS at Nanjing Gaochun People's Hospital for external validation. Sepsis patients were divided in a 7∶3 ratio into a modeling group (n=760) and an internal validation group (n=325). The cases retrospectively collected formed the external validation group (n=430). Using the data from the 760 patients in the modeling group, the least absolute shrinkage and selection operator (LASSO) was employed to identify the risk factors for AKI in patients with sepsis complicated by ARDS. Variables with non‑zero coefficients from LASSO regression were included in the prediction model. Support vector machine (SVM), adaptive boosting (Adaboost), logistic regression (LR), and extreme gradient boosting (Xgboost) algorithms were used to construct the prediction model. The accuracy of the model was assessed using a calibration curve and by calculating the area under the receiver operating characteristic curve (AUC). The model underwent external validation subsequently. Results Among the 1 085 patients with sepsis and ARDS included in the study, 199 developed AKI, resulting in an incidence rate of 18%. Independent risk factors identified for AKI included the sepsis‑related organ failure assessment (SOFA) score [odds ratio (OR) 1.142 (95% confidence interval (CI)1.071, 1.218), P<0.001], oxygenation index [OR 0.993 (95%CI 0.990, 0.996), P<0.001], first 24‑hour urine output [OR 0.996 (95%CI 0.9993, 0.999), P<0.001], positive end‑expiratory pressure (PEEP) [OR 1.097 (95%CI 1.038, 1.160), P=0.001], hypertension [OR 1.598 (95%CI 1.145, 2.231), P=0.006]. The AUCs for the modeling group across the prediction models using SVM, AdaBoost, LR, and XGBoost algorithm were 0.744 (95%CI 0.706, 0.782), 1.000 (95%CI 1.000, 1.000), 0.742 (95%CI 0.706, 0.779), 0.887 (95%CI 0.863, 0.912) respectively, with AUCs for the internal validation group were 0.704 (95%CI 0.644, 0.765), 0.781 (95%CI 0.728, 0.835), 0.716 (95%CI 0.657, 0.775), 0.799 (95%CI 0.746, 0.853). The model also demonstrated certain predictive ability in the external validation groups, with its corresponding calibration curves showing good consistency. Conclusions The independent risk factors for AKI in sepsis patients with ARDS include SOFA score, oxygenation index, first 24‑hour urine output, PEEP, and hypertension. The constructed predictive model exhibits good predictive performance and shows promising predictive capability in the external validation cohort.