Construction and validation of a nomogram for detecting chronic kidney disease in patients with nonalcoholic fatty liver disease: Insights from the NHANES database

Background and objectives

Fatty liver disease is often associated with renal impairment in many patients. Early detection and prompt intervention are crucial for improving patient quality of life and reducing mortality rates. This study aimed to develop and validate a nomogram for detecting the risk of Chronic Kidney Disease (CKD) comorbidity in adults with Nonalcoholic Fatty Liver Disease (NAFLD) in the United States.

Methods

From the NHANES (2017‒2020) database, the authors enrolled 2848 NAFLD participants, of whom 633 also had CKD. The authors employed the Least Absolute Shrinkage and Selection Operator (LASSO) regression and multivariate logistic regression to identify variables with predictive value. The overlapping features were selected to construct a predictive model, which was presented as a nomogram. The effectiveness of the nomogram was evaluated using Receiver Operating Characteristic (ROC) curves, calibration plots, and decision curve analysis.

Results

Six indicators were included in the model: age, systolic blood pressure, serum albumin, high-sensitivity C-reactive protein, total cholesterol, and triglycerides. The area under the curve of the nomogram for predicting CKD in the training set was 0.772, with a 95 % Confidence Interval (95 % CI) of 0.746 to 0.797. In the validation set, the area under the curve was 0.722, with a 95 % CI of 0.680 to 0.763. The calibration curve analyses demonstrated that the prediction outcomes of the model aligned well with the actual outcomes, indicating good clinical applicability.

Conclusions

The nomogram demonstrated excellent performance and has the potential to serve as an auxiliary tool for detecting CKD in NAFLD patients.