Construction and Validation of a Model for Predicting Fatigue Risk in Patients with Maintenance Hemodialysis
Objective: To establish and verificate a fatigue risk prediction model for maintenance hemodialysis patients. Methods: A convenient sampling method was used to select 217 patients who were undergoing maintenance hemodialysis. According to the 8:2 random separation method, they were randomly divided into the modeling group (173 cases) and the validation group (44 cases). Single factor Logistic regression analysis was used to screen the risk factors of the modeling group, and multi factor Logistic regression analysis was used to determine the final influencing factors; R software was used to build the nomogram model of prediction; the area under curve, calibration curve, Hosmer and lemeshow test were used to evaluate the predictive performance of the model. Results: Age, BMI, marital status, the number of dialysis complications, psychological resilience, PSQI score and serum creatinine were the influencing factors of fatigue in maintenance hemodialysis patients. The area under the ROC curve of the model-ing group and the validation group were 0.888 (95％CI:0.831～0.945) and 0.876 (95％CI:0.775～0.977), respectively. The fitting degree of the calibration curve of the two groups was good. The Hosmer and lemeshow test values were x2=4.290, P=0.892 and x2=10.900, P=0.283, respectively. Conclusion: The risk prediction model constructed in this study has a good prediction effect, and can provide reference for clinical medical staff to identify the fatigue risk of maintenance hemodialysis patients early and formulate effective intervention measures.
万方数据
维普
