<![CDATA[Cardiovascular disease (CVD) remains one of the leading causes of mortality globally, thus early risk prediction critical for preventative healthcare. Although machine learning methods have shown promising results in CVD prediction, many existing models are difficult to interpret in clinical practice. This study proposes a CVD risk prediction platform that combines gradient boosting (GB) with fuzzy linguistic representation to improve both predictive performance and interpretability. approach has numerous preprocessing phases, including data cleaning, normalization, outlier handling, and recursive feature elimination (RFE) for feature selection. Numerical clinical attributes are transformed into fuzzy linguistic variables to provide more intuitive risk interpretation for healthcare professionals. The gradient boosting model is trained using both original and fuzzy-transformed feature representations to improve model generalization. The proposed approach is evaluated against several baseline machine learning models using accuracy, precision, recall, and F1-score. Experimental results show that the proposed framework achieves better performance than conventional models, with a maximum accuracy of 94.30%. In addition, the developed platform provides visual risk interpretation and decision-support insights that may assist healthcare practitioners in evaluating cardiovascular risk more effectively.]]>
