Integrating domain-specific metadata and clinical variables into deep learning frameworks remains essential yet challenging for accurate biomedical predictions. Conventional early or late fusion techniques often fail to capture complex interactions between different patient modalities, limiting predictive power and clinical utility. This study presents a novel Adaptive Metadata Encoder (AME) that dynamically embeds structured covariates, such as cholesterol levels, age, race, and other clinical features, directly within deep electrocardiogram (ECG) models. This AME enables cardiovascular risk assessment, specifically targeting the detection of reduced left ventricular ejection fraction (LVEF <40%). Evaluated on a large cohort, our approach adaptively determines the optimal fusion depth for each metadata variable, significantly outperforming traditional fixed fusion strategies. The AME achieves superior metrics, demonstrating robust integration of clinical knowledge into ECG-based predictions. This method offers a scalable, interpretable solution that leverages comprehensive patient data to enable earlier detection and improved clinical management of heart failure.