Cardiovascular Disease Risk Prediction Based on Deep Feature Extraction

Cardiovascular disease (CVD) is the leading cause of death globally, responsible for millions of deaths each year. Early and accurate prediction of CVD risk is crucial for implementing preventive measures and improving patient outcomes. This study proposes a novel deep learning model for enhanced cardiovascular disease risk prediction. In terms of model construction, an improved 1D-CNN is introduced for feature extraction, coupled with a self-attention mechanism to refine feature representation. Finally, employing Softmax as the activation function, an end-to-end deep learning model is constructed, optimized through cross-entropy loss function. Comparative experimental results demonstrate the superiorperformance of the proposed model in cardiovascular disease prediction tasks, with accuracy, recall, and $\mathbf{F 1}$ scores reaching algorithms. This underscores the significant efficacy and necessity of the proposed deep learning model in feature extraction and prediction, providing a reliable solution for early cardiovascular disease prediction.