Dynamic feature selection and quantum representation for precise heart disease prediction: Quantum-HeartDiseaseNet approach

Cardiovascular disease is a leading cause of mortality, necessitating early and precise prediction for improved patient outcomes. This study proposes Quantum-HeartDiseaseNet, a novel heart disease risk prediction framework that integrates a Dynamic Opposite Pufferfish Optimization Algorithm for feature selection and a Quantum Attention-based Bidirectional Gated Recurrent Unit (QABiGRU) for accurate diagnosis. The feature selection method enhances diagnosis accuracy while reducing dimensionality, and Synthetic Minority Oversampling Technique (SMOTE) addresses data imbalance. Evaluated on three heart disease datasets, the proposed model achieved 98.87% accuracy, 98.74% precision, and 98.56% recall, outperforming conventional methods. Experimental results validate its effectiveness in early disease prediction.