A systematic review on machine learning approaches for cardiovascular disease prediction using medical big data

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Public Health

Background:

• Cardiovascular diseases (CVD) represent a significant global health challenge.
• Accurate CVD prediction is crucial for early diagnosis and reducing mortality.
• Patient data analytics offers potential for disease forecasting and prognosis.

Purpose of the Study:

• To conduct a comparative analysis of machine learning techniques for cardiovascular disease prediction.
• To identify research gaps in machine learning applications for CVD detection.
• To provide insights for clinical applications and future research in heart disease prediction.

Main Methods:

• Systematic review and comparative analysis of 41 research papers.
• Focus on classification and predictive machine learning algorithms for CVD.
• Evaluation of existing literature on machine learning in cardiovascular health.

Main Results:

• Machine learning, particularly classification and predictive algorithms, shows high potential for accurate CVD detection.
• Analysis identified specific strengths and weaknesses of various ML approaches.
• Gaps in current research were highlighted, indicating areas for future development.

Conclusions:

• Machine learning offers a powerful tool for enhancing the accuracy of cardiovascular disease prediction.
• The findings support the integration of ML models into clinical practice for early heart disease risk assessment.
• Further research is needed to address identified literature gaps and refine ML applications in cardiology.