Explainable multimodal imaging–based machine learning for cardiovascular risk stratification in early Parkinson’s disease

Aims: This study aimed to characterize convergent biochemical and cardiovascular imaging endophenotypes of atherosclerotic risk in early PD and to implement an interpretable machine-learning architecture integrating multimodal clinical and imaging parameters for precision cardiovascular risk profiling and cardiometabolic classification. Methods: A total of 125 early-stage idiopathic PD patients and age- and sex-matched controls were analyzed. Feature space was reduced using cross-validated Least Absolute Shrinkage and Selection Operator (LASSO) with penalty tuning and stability selection to mitigate multicollinearity. XGBoost, Random Forest, RBF-kernel Support Vector Machine, and Stochastic Gradient Boosting models were trained under a train–hold-out framework with Bayesian hyperparameter optimization. Model performance was assessed via bootstrapping, and interpretability was provided using SHapley Additive exPlanations (SHAP). Results: PD patients showed increased hypertension (54.4%; OR 3.2, p=0.007) and hypercholesterolemia (OR 2.8, p=0.01), with excess left ventricular systolic dysfunction (28.8% vs 0%, p<0.001), aortic insufficiency (20.0% vs 0%, p=0.001), and high-risk carotid plaques (unstable 40.8% vs 2.0%; calcified 49.6% vs 18.0%; both p<0.001). Inflammation was elevated (CRP 7.70±7.22 vs 3.34±1.31 mg/L, p<0.001) with reduced lymphocyte-to-monocyte ratio (LMR) (3.99±1.94 vs 5.13±1.45, p<0.001). XGBoost achieved superior discrimination (accuracy 0.941, 95% CI 0.911–0.971; sensitivity 0.923; specificity 0.889; PPV 0.960, 95% CI 0.930–0.990; AUC 0.95, 95% CI 0.91–0.983; Brier 0.07), with explainability dominated by LMR (SHAP 100%), followed by CRP (92.6%) and glucose-metabolic markers (65.6%). Conclusion: PD demonstrates a convergent inflammatory–metabolic endophenotype with elevated carotid and cardiac risk burden. An explainable XGBoost-based multimodal framework implicated LMR and C-RP as discriminative biomarkers for targeted surveillance in early PD.