Integrating Large-Scale Data Analytics for Cardiovascular Disease Prediction: A Scoping Review.

Area of Science:

• Cardiovascular disease research
• Health informatics
• Data science in medicine

Background:

• Cardiovascular diseases (CVD) pose a significant global health burden.
• Early detection and prevention are crucial for improving patient outcomes.
• Large-scale data analytics and machine learning (ML) show promise in enhancing predictive capabilities for CVD.

Purpose of the Study:

• To synthesize current literature on integrating large-scale data analytics for cardiovascular disease prediction.
• To identify key themes, applications, and challenges in using ML for CVD risk assessment.
• To inform the adoption of predictive analytics for better CVD prevention and early detection.

Main Methods:

• A scoping review methodology was employed.
• Searches conducted across Medline (PubMed), EBSCO, Google Scholar, and Wiley Online Library.
• Keywords included 'large-scale data', 'big data', 'cardiovascular diseases', 'prediction', 'machine-learning algorithms', 'artificial intelligence', and 'mortality' (2020-2024).

Main Results:

• 16 articles were included from 262 retrieved.
• Identified themes: data analysis techniques/ML algorithms, ML/AI applications in CVD prediction, and the role of large-scale data in improving care quality.
• ML shows potential for predicting CVD outcomes.

Conclusions:

• Machine learning offers significant potential for CVD prediction but has limitations.
• ML may not always be optimal, especially when causal inference is critical.
• Addressing bias, data quality, ethics, and implementation challenges is vital for equitable healthcare.
• Interdisciplinary collaboration and methodological refinement are necessary for future advancements.