Clinical Report: Utilization of Artificial Intelligence for Cardiovascular Risk in Obesity
Overview
This scoping review evaluates the application of artificial intelligence (AI) in identifying and predicting cardiovascular risk in obese adults. Findings indicate that while AI shows promise, challenges such as methodological heterogeneity and limited external validation hinder its clinical implementation.
Background
Obesity significantly elevates cardiovascular risk, which is a leading cause of mortality globally. Traditional risk prediction tools often fail to account for the unique metabolic complexities associated with obesity. The integration of AI into cardiovascular risk assessment may enhance detection and prediction capabilities, addressing these limitations.
Data Highlights
Study Type
Number of Studies
Common AI Methods
Focus Areas
Retrospective
30
Random Forest, Gradient Boosting
Risk Stratification, Disease Detection
Key Findings
Thirty studies were included, primarily retrospective and with heterogeneous populations.
Tree-based ensemble methods, especially Random Forest and gradient boosting, were the most commonly used AI techniques.
Outcomes focused mainly on cardiovascular risk stratification and disease detection.
Prediction of incident cardiovascular events and mortality was less frequently addressed.
External validation of AI models was rarely reported, and model performance was generally moderate.
Clinical Implications
Healthcare professionals should consider the potential of AI as a complementary tool for cardiovascular risk assessment in obese patients. However, the current limitations in methodology and validation must be acknowledged when interpreting AI-generated risk predictions.
Conclusion
AI has the potential to enhance cardiovascular risk assessment in obese adults, but further research is needed to standardize methodologies and validate outcomes for clinical application.
