Comprehensive review of heart disease prediction: A comparative study from 2019 onwards

Area of Science:

• Cardiology
• Artificial Intelligence in Medicine
• Biomedical Informatics

Background:

• Cardiovascular disease (CVD) is the leading global cause of mortality, necessitating improved early diagnostic strategies.
• Traditional diagnostic methods for heart disease face limitations in accuracy and timeliness.
• The rise of advanced computational techniques offers new avenues for predictive modeling.

Purpose of the Study:

• To systematically review the current state-of-the-art in heart disease prediction.
• To analyze the transition from conventional diagnostic techniques to machine learning (ML) and deep learning (DL) approaches.
• To identify challenges and future research directions in CVD prediction.

Main Methods:

• A comprehensive literature review was conducted.
• Effectiveness and limitations of various predictive algorithms were critically assessed.
• The role of risk factors, their interactions, and the influence of comorbidities like kidney stones were examined.

Main Results:

• Machine learning and deep learning methods show significant potential for enhancing heart disease prediction accuracy.
• Challenges include identifying specific risk factors and understanding complex, non-linear interactions.
• The interplay between cardiovascular diseases and kidney stones presents a novel area for predictive model development.

Conclusions:

• Deep learning methods offer promising advancements for improving diagnostic precision in heart disease.
• Optimizing patient management and outcomes can be achieved through enhanced predictive capabilities.
• A roadmap for future research is proposed, focusing on advanced AI applications in cardiology.