Nomogram analysis of factors associated with prognosis in patients with sepsis-associated acute kidney injury: a case-control study based on LASSO regression.

BACKGROUND

Sepsis-associated acute kidney injury (SA-AKI) is one of the most common and serious complications of sepsis, characterized by high mortality, prolonged hospital stay, substantial healthcare burden, and progression to chronic kidney disease in approximately 30% of survivors. Early identification of high-risk patients and accurate prediction of their prognosis are of great significance for clinical decision-making. Currently, there is a lack of simple, intuitive, and externally validated individualized prognostic prediction tools in clinical practice.

OBJECTIVE

To develop and validate a nomogram model for predicting prognosis in patients with SA-AKI based on clinically accessible indicators.

METHODS

A retrospective case-control study design was employed. Clinical data were collected from 200 patients with SA-AKI hospitalized at The First Affiliated Hospital of Xinjiang Medical University and The Fifth Affiliated Hospital of Xinjiang Medical University from December 2023 to March 2025. Data from The First Affiliated Hospital of Xinjiang Medical University served as the training set (n = 113), while data from The Fifth Affiliated Hospital of Xinjiang Medical University served as the external validation set (n = 87). Key predictive variables were selected using least absolute shrinkage and selection operator (LASSO) regression and subsequently incorporated into multivariate logistic regression analysis to identify independent influencing factors, based on which a nomogram prediction model was constructed. Discrimination of the model was assessed using the receiver operating characteristic curve, calibration was evaluated using the Hosmer-Lemeshow test, and clinical utility was assessed using decision curve analysis.

RESULTS

LASSO regression identified four variables: age, Sequential Organ Failure Assessment (SOFA) score, creatinine, and serum potassium. Multivariate logistic regression analysis showed that all four variables were independent influencing factors for the prognosis of SA-AKI patients (all p < 0.01). Higher levels of age, SOFA score, creatinine, and serum potassium were significantly associated with an unfavorable prognosis: age (OR = 0.94, 95% CI: 0.91-0.97), SOFA score (OR = 0.75, 95% CI: 0.67-0.84), creatinine (OR = 0.60, 95% CI: 0.39-0.91), and serum potassium (OR = 0.51, 95% CI: 0.32-0.80). The nomogram model achieved an AUC of 0.92 (95% CI: 0.86-0.97) in the training set, with a sensitivity of 0.82 and a specificity of 0.90; in the external validation set, the AUC was 0.85 (95% CI: 0.76-0.94), with a sensitivity of 0.90 and a specificity of 0.66. The Hosmer-Lemeshow test indicated good calibration in both the training set (p = 0.41) and the validation set (p = 0.57), and decision curve analysis confirmed the clinical utility of the model.

CONCLUSION

Age, SOFA score, creatinine, and serum potassium are independent predictors of prognosis in SA-AKI patients. The nomogram model constructed based on these indicators demonstrates good discrimination, calibration, and clinical utility, and may serve as a valuable tool for early identification of high-risk patients with poor prognosis and for the development of individualized treatment strategies.