An automatic diagnostic model for the detection and classification of cardiovascular diseases based on swarm...

Area of Science:

• Medical Informatics
• Machine Learning
• Cardiology

Background:

• Cardiovascular diseases (CVDs) are a leading cause of global mortality, responsible for one in three deaths.
• Early diagnosis of associated ailments is crucial for recovery in most heart disorders.
• Clinical datasets for predicting CVDs pose challenges due to large dimensions and class imbalance.

Purpose of the Study:

• To develop an innovative model for early cardiovascular disease detection and classification.
• To address the challenges of large dimensions and class imbalance in clinical datasets.
• To propose an efficient decision support system for cardiovascular disorder diagnosis.

Main Methods:

• Utilized a combination of an optimization technique and a deep learning classifier.
• Employed data analysis technology for examining patient medical records.
• Synthesized samples and optimized parameters for enhanced classifier prediction.

Main Results:

• Achieved a high accuracy of 99.58% in predicting cardiovascular disease.
• Calculated and compared metrics such as PSNR, sensitivity, and specificity with existing systems.
• Demonstrated the potential of deep learning to reduce mortality rates through early prediction.

Conclusions:

• The proposed model effectively aids in the early detection and classification of cardiovascular disorders.
• The integration of optimization and deep learning offers an advancement over traditional prediction techniques.
• This assistive system can significantly improve patient outcomes by enabling timely diagnosis and intervention.