Objective:

To systematically map the application of big data and machine learning in early detection models for diabetes and cardiovascular diseases.

Approach:

• Research Design: A scoping review was conducted following Arksey and O’Malley’s methodological approach and PRISMA-ScR reporting standards.
• Research Question: The review focused on the use of big data and machine learning techniques for predictive modeling in individuals at risk of or living with diabetes and cardiovascular diseases.
• Eligibility Criteria: Studies were included if they involved predictive modeling for early detection of diabetes or cardiovascular conditions, applied machine learning techniques, utilized large-scale health datasets, and were published in peer-reviewed sources.

Key Findings:

• Chronic diseases like diabetes and cardiovascular ailments are increasing globally, necessitating innovative early detection strategies.
• Big data and machine learning can enhance diagnostic accuracy and support proactive care by identifying high-risk individuals.
• There are challenges in translating predictive modeling from research to routine practice, including methodological consistency and ethical transparency.

Interpretation:

The integration of big data analytics with machine learning holds potential for transforming clinical decision-making and health system planning.

Limitations:

• Challenges in methodological consistency and clinical relevance.
• Variability in data quality and population diversity complicates broader adoption.
• Concerns regarding algorithmic fairness and model interpretability.

Conclusion:

A comprehensive review of existing approaches is essential to inform future research, guide policy, and enhance clinical integration.