Multidimensional nomogram for prediction of cardiovascular disease risk in cancer survivors

To identify factors associated with cardiovascular disease (CVD) among cancer survivors using the National Health and Nutrition Examination Survey (NHANES) database, and to construct and validate a clinical model to assess the probability of CVD risk among these patients.

A total of 1766 cancer survivors from the 2011-2018 NHANES database were included. Univariate analysis was used to screen for differential variables, and the XGBoost model was used to assess the importance of variables. A nomogram prediction model was constructed based on multivariate logistic regression and evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analyses.

On univariate analysis, age, marital status, family income poverty index ratio, total cholesterol, hypertension, diabetes, smoking, depression degree, sedentary time, and sleep time were significantly associated with CVD risk (all P < 0.05). The XGBoost model identified age, marital status, total cholesterol, hypertension, diabetes, and depression degree as factors independently associated with CVD. Multivariate analysis showed that increased age, divorced or cohabitation status, hypertension, and moderately severe or severe depression were significantly associated with an increased likelihood of CVD, whereas elevated total cholesterol was associated with a likelihood risk. The area under the ROC curve of the nomogram model for assessing CVD was 0.734. The calibration curve showed high consistency between the predicted and actual risks, and decision curve analysis confirmed that the model had a net clinical benefit over a wide range of thresholds. Due to the cross-sectional design, no causal inferences can be drawn from this study.

This study constructed a CVD risk prediction model for cancer survivors, suggesting the utility of integrating psychosocial variables with traditional biomedical indicators for risk stratification.