Volume 4,Issue 2
Objective: To construct a risk prediction model for cognitive frailty in patients with chronic kidney disease (CKD) and draw a nomogram, so as to provide a reference for clinical medical staff to predict the risk of cognitive frailty in these patients and take targeted nursing measures. Methods: In this study, patients with CKD in stages 1–3 were collected as a modeling set from October 2022 to April 2023 in the Nephrology Department of two hospitals in Shanghai. Through univariate analysis and multivariate logistic regression analysis, the risk factors of cognitive frailty in patients with CKD in stages 1–3 were screened out, and the risk prediction model was constructed according to the weight of risk factors, and the nomogram was drawn using Stata15.0 software. Bootstrap self-sampling method is used to repeat sampling 1,000 times to verify the built prediction model internally. According to the same inclusion and exclusion criteria, from October 2022 to April 2023, the patient case data of stages 1–3 CKD in the Nephrology Department, a cooperative hospital in Jiangsu Province, were selected as the verification set, and the model was externally verified. Results: In the modeling set (n = 600), cognitive frailty incidence was 38.8% (n = 233), and in the verification set (n = 200), it was 42.0% (n = 84). Independent risk factors include chronic disease count, depression, sleep quality, C-reactive protein, D-dimer, and parathyroid hormone in CKD patients. Internal test showed corrected C-statistic 0.779 (95% CI 0.742–0.816, P < 0.01), Hosmer–Lemeshow χ2 = 5.794, P = 0.670 > 0.05. DCA indicated the model provides positive benefits for intervention decisions. External verification yielded C-statistic 0.909 (95% CI 0.870–0.948, P < 0.01), Hosmer–Lemeshow χ2 = 3.423, P = 0.904 > 0.05. Conclusion: The incidence of cognitive frailty in patients with CKD is high. Patients with CKD with a large number of chronic diseases, severe depressive symptoms, poor sleep quality, abnormal C-reactive protein, abnormal D-dimer, and abnormal parathyroid hormone have a higher risk of cognitive frailty. The risk prediction model has good prediction efficiency, which can provide a reference for clinical medical staff to predict the risk of cognitive frailty in patients with CKD and formulate nursing countermeasures.