Development and validation of a nomogram for predicting acute kidney injury in elderly patients in intensive care unit.

BACKGROUND

This study aimed to develop and validate a nomogram for predicting acute kidney injury (AKI) in elderly patients in the intensive care unit (ICU).

METHODS

Population data regarding elderly patients in ICU were derived from the Medical Information Mart for Intensive Care IV database from 2008 to 2019. The nomogram model was constructed from the training set using LASSO regression and logistic regression analysis, and the performance of the model was evaluated by decision curve analysis, calibration curve, and receiver operating characteristic (ROC) curve.

RESULTS

According to inclusion and exclusion criteria, 14,373 elderly ICU patients were studied, of which 10,061 (70%) were assigned to the training set, and 4,312 (30%) were allocated to the validation set. Multivariate logistic analysis revealed that age, weight, myocardial infarction, congestive heart failure, dementia, diabetes, paraplegia, cancer, sepsis, body temperature, blood urea nitrogen, mechanical ventilation, urine volume, Sequential Organ Failure Assessment (SOFA) score, and Simplified Acute Physiology Score II (SAPS II) were independent risk factors for AKI in elderly ICU patients. The AUC values for the 15-factor nomogram were 0.812 (95% CI 0.802-0.822) and 0.802 (95% CI 0.787-0.818) in the training and validation sets, respectively. For clinical application, a simplified nomogram was constructed, which included age, weight, urine volume, SOFA score, and SAPS II, with the AUCs of 0.780 (95% CI 0.769-0.790) and 0.776 (95% CI 0.760-0.793), respectively. Calibration curve and decision curve analyses confirmed the models' high prediction accuracy and clinical value.

CONCLUSIONS

The nomogram developed in this study shows excellent predictive performance for AKI in elderly patients in the ICU.