To validate the association between kidney stones and cardiovascular disease (CVD) and to develop an interpretable machine learning model for identifying prevalent CVD in individuals with kidney stones, addressing the lack of existing tools.
Key Findings:
Participants with kidney stones had a 47% increased risk of CVD compared to those without (OR = 1.47, 95% CI: 1.20–1.80).
The logistic regression model achieved an area under the receiver operating characteristic curve of 0.801, with sensitivity of 0.721, specificity of 0.771, and accuracy of 0.759.
SHAP analysis identified the importance of 15 predictors in the model.
Interpretation:
The study highlights an association between kidney stones and prevalent CVD, though causality cannot be inferred due to the cross-sectional design, suggesting a need for further research.
Limitations:
Causality cannot be inferred due to the cross-sectional design.
The study relies on data from a specific population, which may limit generalizability.
Potential biases in self-reported data from NHANES may affect the results.
Conclusion:
The logistic regression model demonstrated strong performance in identifying prevalent CVD in patients with kidney stone disease, highlighting the need for clinical awareness and targeted interventions.
