Abstract
OBJECTIVE: Based on the NLR, we aim to investigate the prognostic factors of CHF and establish a nomogram model to predict the OS of CHF patients. METHODS: We selected 566 CHF patients from the NHANES database surveyed between 1999 and 2018 as the study population and randomly divided the data into training and validation sets in a 7:3 ratio. We used multivariate Cox regression analysis to determine the factors affecting the prognosis of CHF patients. Additionally, we evaluated the stratification of the NLR and the nomogram total risk score using the Kaplan-Meier survival curves and log-rank tests. To evaluate the predictive accuracy of the nomogram, we used the area under the ROC and the calibration curve method. Finally, we used decision curve analysis to explore the value of the nomogram in clinical applications. RESULTS: Multivariate Cox regression analysis revealed that the NLR, age, and gender were risk factors affecting the OS of CHF patients, whereas hemoglobin and platelets were protective factors. We established a nomogram based on NLR, age, gender, hemoglobin, and platelets and calculated the area under the survival rate curve for 3, 5, and 10 years in both the training and validation sets, indicating good predictive capacity of the model (training set AUCs were 0.822, 0.82, and 0.803, respectively; validation set AUCs were 0.726, 0.769, and 0.775, respectively). Calibration curves and decision curve analysis indicated the model's accuracy and clinical applicability. The risk stratification was performed using NLR and the nomogram total score, and the Kaplan-Meier survival curves and log-rank tests showed that CHF patients with higher NLR had worse prognosis and those with lower nomogram total score had better prognosis than those in high-risk groups. There was a significant difference in OS between the high- and low-risk groups (P < 0.001). CONCLUSION: This study found that NLR, age, gender, hemoglobin, and platelets are closely related to the prognosis of CHF patients. We successfully constructed a nomogram model based on these factors, which can accurately predict the prognosis of CHF patients.