A STUDY using machine learning has identified dynapenia, age-related muscle weakness, as a critical but overlooked risk factor for atherosclerotic cardiovascular disease (ASCVD), particularly in females. Researchers analyzed data from over 19,000 participants and found that low grip strength significantly increased ASCVD risk in women, while no such association was observed in men. These findings suggest the need for sex-specific prevention strategies and reinforce the role of muscle health in cardiovascular care.
Published in the Journal of Personalized Medicine, the study examined 19,582 individuals aged 40–79 from the Korean National Health and Nutrition Examination Survey (KNHANES). Using the American College of Cardiology/American Heart Association 10-year risk algorithm, researchers assessed ASCVD risk and defined dynapenia based on handgrip strength. Advanced machine-learning models, including XGBoost (XGB) and Light Gradient Boosting (LGB), were applied to evaluate predictive factors.
Results revealed a striking disparity: 33.4% of women at high ASCVD risk had dynapenia, compared to only 13.9% of men. Logistic regression confirmed that women with dynapenia faced a 47% higher risk of ASCVD (odds ratio: 1.47; 95% confidence interval: 1.20–1.81). Machine learning models demonstrated exceptional predictive accuracy, with XGB achieving an area under the receiver operating characteristic curve (AUROC) of 0.950 for men and 0.963 for women. SHAP analysis identified dynapenia as a key ASCVD risk factor in women, while other influential variables included body mass index, educational status, and household income in both sexes.
These findings highlight the importance of muscle strength in cardiovascular risk assessment, particularly for women. The integration of machine learning into risk prediction models enhances precision, paving the way for more targeted prevention strategies. Given the growing burden of ASCVD, healthcare professionals should consider muscle strength as a crucial component of cardiovascular risk screening and intervention.
Reference: Lee G et al. Sex-Specific Associations Between Dynapenia and Risk of Atherosclerotic Cardiovascular Disease: A Machine-Learning-Based Approach. J Pers Med. 2025;15(3):83.
Anaya Malik | AMJ