Key result
Integrated clinical, inflammatory, and imaging model predicts five-year CVD risk in advanced CKD with ~0.85 AUC.
Why the study?
Traditional CVD risk factors have diminished predictive utility in advanced CKD, and existing prediction models based solely on traditional risks show limitations and inaccuracies.
Does a risk prediction model integrating clinical, inflammatory, and imaging parameters improve the prediction of 5-year CVD events in patients with CKD stages 3-5 compared to traditional risk factors?
Cohort (n=301)
Does a risk prediction model integrating clinical, inflammatory, and imaging parameters improve the prediction of 5-year CVD events in patients with CKD stages 3-5 compared to traditional risk factors?
Answers are grounded in this paper and cite their sources.
A novel risk prediction model incorporating CRP and interventricular septum thickness alongside traditional risk factors accurately predicts 5-year CVD events in patients with advanced CKD.
Background Cardiovascular disease (CVD) is the leading cause of mortality in chronic kidney disease (CKD) patients. Traditional CVD risk factors exhibit diminished predictive utility in advanced CKD, necessitating integration of non-traditional biomarkers. Previous prediction models based only on traditional CVD risk show limitations and inaccuracies. This study aimed to develop and validate a 5-year CVD risk prediction model combining clinical, laboratory, and imaging parameters for CKD stages 3–5 patients. Methods Three hundred and one patients with CKD stage 3–5 were recruited from January 2010 to January 2022 and followed up until July 2022. Least Absolute Shrinkage and Selection Operator (LASSO) regression and multivariable logistic regression were used to identify baseline predictors for model development including clinical data, medication history and laboratory parameters, regression modeling was performed using logistic regression and internally validated using tenfold cross-validation. Discrimination and calibration of resulting prediction models were assessed using c-statistic and P -value of the Hosmer-Lemeshow test. Decision curve analysis was performed to assess clinical effectiveness. Results During follow-up, 169 (56.1%) experienced a first CVD event within 5 years. The median time of occurrence was 10 months. From 29 candidate variables, 11 independent predictors were identified. Through nested model comparisons, we demonstrated that adding inflammatory marker C-reactive protein (CRP) and echocardiographic marker interventricular septum thickness (IVS) markers to traditional risk factors progressively improved predictive performance. The full model—integrating clinical, inflammatory, and imaging parameters—achieved the highest discrimination (area under the curve (AUC), 0.845, 95% confidence interval (CI), [0.802–0.888]) and best fit (Akaike information criterion (AIC), 311.531), with excellent calibration (Hosmer-Lemeshow P = 0.332). Conclusions This study established and validated a clinical risk prediction model based on readily available variables in clinical practice, aiming to predict the risk of CVD events in patients with CKD stages 3–5 over a 5-year period.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2026) conducted a cohort in Chronic kidney disease stage 3-5 (n=301). Full prediction model integrating clinical, inflammatory (CRP), and imaging (IVS) parameters vs. Traditional risk factors was evaluated on First cardiovascular disease event within 5 years (AUC 0.845, 95% CI 0.802-0.888). A prediction model integrating clinical, inflammatory, and imaging parameters accurately predicted 5-year CVD risk in patients with CKD stages 3-5.
Synapse has enriched 10 related papers. Consider them for comparative context: