Applications of artificial intelligence in cardiovascular risk detection and prediction among adults with obesity: a scoping review - Summary - MDSpire
Advertisement
Applications of artificial intelligence in cardiovascular risk detection and prediction among adults with obesity: a scoping review
To map and characterise the available evidence on the application of artificial intelligence for cardiovascular risk detection, prediction, and stratification in adults with obesity, addressing the limitations of conventional tools.
Key Findings:
Thirty studies were included, mostly retrospective and characterized by heterogeneous populations.
Tree-based ensemble methods, particularly Random Forest and gradient boosting algorithms, were most frequently used, along with support vector machines and artificial neural networks.
Outcomes mainly focused on cardiovascular risk stratification and disease detection; prediction of incident cardiovascular events and mortality was less common.
External validation was infrequently reported, and model performance was generally moderate when longitudinal outcomes were assessed.
Interpretation:
Artificial intelligence shows potential as a complementary tool for cardiovascular risk assessment in adults with obesity, but current methodological limitations hinder clinical implementation, emphasizing the need for improved study designs.
Limitations:
Methodological heterogeneity among studies.
Limited external validation of AI models.
Inconsistent outcome definitions across studies.
Potential biases in the studies included in the review.
Conclusion:
Future research should prioritize prospective designs, robust external validation, and standardized outcomes to define the clinical value of AI-based cardiovascular risk models in obesity, highlighting the importance of these advancements.
