Predator crow search optimization with explainable AI for cardiac vascular disease classification.

Area of Science:

• Artificial Intelligence
• Medical Imaging
• Cardiovascular Disease Research

Background:

• Cardiovascular diseases (CVD) pose a significant global health challenge.
• Accurate and early prediction of CVD is crucial for effective patient management.
• Existing prediction models often face limitations in accuracy, robustness, and interpretability.

Purpose of the Study:

• To develop and validate an optimized Explainable AI (XAI) framework for enhanced cardiovascular disease prediction.
• To improve the precision and reliability of AI models in medical diagnostics.
• To provide a clinically relevant and interpretable tool for healthcare professionals.

Main Methods:

• An enhanced U-Net model with context-based partitioning for left ventricular segmentation.
• Predator crow search optimization for refining predictive model performance.
• Information acquisition-based technique for feature selection and overfitting prevention.
• Validation on ACDC challenge and imATFIB datasets.

Main Results:

• Achieved 99.72% accuracy, 96.47% precision, 98.6% recall, and 94.6% F1 measure in CVD prediction.
• Demonstrated significant improvements over existing cardiovascular disease prediction methods.
• Qualitative analysis confirmed the interpretability and clinical relevance of the model's predictions.

Conclusions:

• The proposed AI framework offers superior performance for cardiovascular disease prediction.
• The model's robustness, reliability, and interpretability make it a valuable tool for medical professionals.
• This approach has the potential to improve patient outcomes through early and precise diagnosis.