Objective: To develop and validate a parsimonious and clinically applicable nomogram for predicting 28-day mortality in patients with bacterial pneumonia complicated by sepsis and acute kidney injury using data from the Medical Information Mart for Intensive Care-IV database. Methods: A total of 470 eligible patients were enrolled and randomly assigned to a derivation cohort ( n = 330) and a validation cohort ( n = 140). Candidate predictors were screened using least absolute shrinkage and selection operator regression with the λ.1se criterion, followed by multivariable logistic regression to construct the final model. Model performance was assessed in both cohorts using discrimination (area under the receiver operating characteristic curve), calibration plots, calibration statistics, and decision curve analysis. A nomogram was developed based on the final predictors. Results: Least absolute shrinkage and selection operator regression identified three independent predictors—age, Sequential Organ Failure Assessment score, and urine output—which were incorporated into the final nomogram. The model demonstrated good discrimination in the derivation cohort (area under the receiver operating characteristic curve = 0.802; 95% confidence interval: 0.750–0.853) and validation cohort (area under the receiver operating characteristic curve = 0.803; 95% confidence interval: 0.721–0.885). Calibration curves and corresponding intercept and slope values indicated satisfactory agreement between predicted and observed mortality risks in both cohorts. Decision curve analysis showed that the nomogram yielded higher net clinical benefit compared with Sequential Organ Failure Assessment alone across a wide range of threshold probabilities. Conclusion: The nomogram integrating age, Sequential Organ Failure Assessment score, and urine output provides accurate and clinically meaningful prediction of 28-day mortality among patients with bacterial pneumonia complicated by sepsis and acute kidney injury. This tool may facilitate early risk stratification and guide individualized clinical decision-making in the intensive care unit setting.
Li et al. (Sun,) studied this question.