Cardiovascular diseases (CVDs) remain one of the leading causes of mortality worldwide and continue to impose a substantial burden on healthcare systems. Early identification of individuals at risk is important for improving clinical outcomes and supporting timely medical intervention. Electrocardiogram (ECG) signals provide valuable information regarding cardiac electrical activity, while clinical biomarkers offer complementary insights into physiological and pathological conditions associated with cardiovascular disorders. Recent advances in deep learning have demonstrated promising results in automated disease prediction; however, the limited interpretability of many deep learning models remains a challenge for clinical adoption. This study proposes an explainable deep learning framework for the early prediction of cardiovascular diseases using ECG signals and clinical biomarkers. The framework integrates ECG-based feature learning with structured clinical information to improve predictive performance while incorporating explainability mechanisms to support clinical interpretation. ECG signals undergo preprocessing and feature extraction before being combined with patient-specific biomarker data. A deep learning model is trained to classify cardiovascular risk levels, and SHAP-based explainability techniques are employed to identify influential features contributing to prediction outcomes. Experimental evaluation was conducted using publicly available cardiovascular datasets containing ECG recordings and clinical variables. Performance was assessed using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). The results indicate that combining ECG information with clinical biomarkers improves predictive performance compared with single-source approaches. Explainability analysis further provides insight into the relative importance of physiological indicators and ECG characteristics. The proposed framework demonstrates the potential of interpretable deep learning methods for supporting cardiovascular risk assessment and clinical decision-making