Chronic kidney disease (CKD) patients tend to exhibit a heightened susceptibility to osteoporosis owing to abnormalities in mineral and bone metabolism. The objective of this study was to develop and validate a nomogram for the prediction of osteoporosis risk in patients with CKD. 1498 patients diagnosed with CKD were enrolled from the National Health and Nutrition Examination Survey (NHANES) data spanning 2005-2010, 2013-2014, and 2017-2018. The dataset was randomly divided into a training set and a validation set in a ratio of 7:3. Utilizing the least absolute shrinkage and selection operator (LASSO) regression technique for predictor identification, followed by employing multivariate logistic regression based on the selected predictors to construct a nomogram. The performance of the prediction model was assessed using various metrics, including the area under the receiver operating characteristic curve (AUC), calibration curve, the Hosmer-Lemeshow test, and decision curve analysis (DCA). The construction of the nomogram was based on five predictors, namely age, height, weight, alkaline phosphatase (ALP), and history of fracture. The AUC of 0.8511 in the training set and 0.8184 in the validation set demonstrates robust discriminability. Furthermore, the excellent calibration and clinical applicability of the model have been thoroughly validated. Our study suggests a nomogram, providing nephrologists with a convenient and effective tool for identifying individuals at high risk of osteoporosis and avoiding adverse outcomes related to CKD.
Read full abstract