Quantum-inspired cardiac risk assessment using hybrid CSAGGO-Q-SpinalNet algorithm for precise heart disease...

Area of Science:

• Cardiovascular disease research
• Artificial intelligence in healthcare
• Machine learning for medical diagnosis

Background:

• Cardiovascular disease is a leading global cause of mortality.
• Early diagnosis is crucial but hindered by data imbalance and complexity.
• Sophisticated intelligent systems are needed for accurate heart disease prediction.

Purpose of the Study:

• To develop an intelligent system for enhanced heart disease prediction.
• To integrate advanced machine learning techniques for improved classification accuracy.
• To provide explainable insights for clinical decision-making.

Main Methods:

• Data preprocessing with Principal Component Analysis (PCA) and Synthetic Minority Oversampling Technique (SMOTE).
• Feature selection using Least Absolute Shrinkage and Selection Operator (LASSO).
• Hybrid classification model combining Capuchin Search Algorithm Graylag Goal Optimization (CSAGGO) and Quantum-SpinalNet (Q-SpinalNet).
• Interpretability analysis using SHapley Additive exPlanations (SHAP).

Main Results:

• The CSAGGO-Q-SpinalNet model achieved 98.44% accuracy, 96.89% sensitivity, and 96.83% specificity on the Cleveland dataset.
• Demonstrated low error rates: 4.24% False Positive Rate (FPR), 4.38% False Negative Rate (FNR).
• SHAP values provided actionable insights into feature influence on predictions.

Conclusions:

• The proposed intelligent system offers a robust, efficient, and explainable solution for heart disease prediction.
• The hybrid CSAGGO-Q-SpinalNet framework outperforms existing methods.
• This system shows significant promise for early diagnosis and personalized treatment in clinical settings.