Development and Validation of a Predictive Model for Chronic Kidney Disease After Percutaneous Coronary Intervention...

Area of Science:

• Cardiology
• Nephrology
• Medical Prediction Modeling

Background:

• Coronary heart disease (CHD) and chronic kidney disease (CKD) are common comorbidities.
• Percutaneous coronary intervention (PCI) is a standard treatment for CHD.
• Predictive models for major adverse cardiovascular events (MACEs) in patients with both CHD and CKD undergoing PCI are lacking.

Purpose of the Study:

• To develop and validate a predictive model for MACEs in patients with comorbid CHD and CKD undergoing PCI.
• To identify key predictors of MACEs in this patient population.
• To create a clinical tool for improved patient management.

Main Methods:

• A cohort of 1714 CKD patients undergoing PCI between 2008 and 2017 was analyzed.
• Least absolute shrinkage and selection operator (LASSO) regression was used for feature selection.
• Multivariable logistic regression and an independent validation cohort were employed to develop and assess the prediction model's performance (discrimination, calibration, clinical usefulness).

Main Results:

• Key predictors of MACEs included family history of CHD, prior revascularization, ST segment changes, anemia, hyponatremia, transradial intervention, number of diseased vessels, contrast media dose >200 ml, and coronary collateral circulation.
• The model demonstrated good discrimination (AUC 0.612) and calibration (P=0.444) in the validation cohort.
• Decision curve analysis confirmed the model's clinical utility.

Conclusions:

• A nomogram was developed to predict MACEs following PCI in CHD patients with CKD.
• This predictive model can potentially enhance patient screening and optimize treatment strategies.
• The findings highlight the importance of considering multiple clinical factors for risk stratification in this complex patient group.