Machine Learning-Based Automated Diagnostic Systems Developed for Heart Failure Prediction Using Different Types of...

Area of Science:

• Cardiology
• Biomedical Engineering
• Artificial Intelligence

Background:

• Heart disease is a leading global cause of mortality.
• Traditional diagnostic methods like angiography are costly and pose health risks.
• Automated systems using machine learning (ML) offer efficient and reliable alternatives.

Purpose of the Study:

• To systematically review automated heart disease detection methods.
• To analyze ML-based approaches across diverse data modalities (clinical, image, ECG).
• To identify limitations and propose future research directions.

Main Methods:

• Systematic literature review of ML and data mining techniques for heart disease prediction.
• Analysis of studies utilizing clinical features, medical imaging, and electrocardiogram (ECG) data.
• Critical evaluation of existing automated diagnostic systems.

Main Results:

• Machine learning provides affordable and efficient solutions for heart disease detection.
• Previous reviews often focused on single data modalities.
• This study integrates findings from clinical, image, and ECG-based ML approaches.

Conclusions:

• Automated systems leveraging ML and multimodal data show significant promise for heart disease diagnosis.
• Addressing current limitations and exploring multimodal data integration are key future research avenues.
• Developing reliable, cost-effective heart disease detection is crucial for global health.