Global Co-Occurrence of COPD and Peripheral Artery Disease in Older Adults: A Machine Learning Analysis of Spatial Patterns and Population-Attributable Risks.

Authors

Shen Liu, Xuehong Jia, Tianxu Han, Zeye Liu, Jing Xie, Guojing Han, Chengliang Yin

Published in

International journal of chronic obstructive pulmonary disease. Volume 21. Pages 624329. Epub Oct 12, 2026.

Abstract

Chronic obstructive pulmonary disease (COPD) and peripheral artery disease (PAD) significantly contribute to morbidity and mortality among older adults. The geographic co-occurrence may indicate shared exposures; however, global population-level evidence remains scarce.
Utilizing Global Burden of Disease (GBD) 2021 estimates, the analysis focused on COPD and PAD incidence in adults aged ≥ 70 years across 202 countries and territories. Disease-specific incidence quartiles characterized spatial co-occurrence. Random forest models with SHAP (Shapley Additive Explanations) ranked exposure contributions, while negative binomial regression with population offsets estimated associations and population-attributable fractions (PAFs). A quartile-based composite risk index summarized cumulative exposure.
The global median incidence was 1150.16 per 100,000 for COPD and 695.4 per 100,000 for PAD. High-incidence regions exhibited partial geographic overlap. Smoking, high LDL cholesterol, and kidney dysfunction correlated with the incidence of both diseases, whereas several additional exposures were disease-specific. Elevated LDL cholesterol had the largest positive association with COPD incidence (RR 1.149), whereas high sugar-sweetened beverage intake exhibited the largest positive association among PAD-specific exposures (RR 1.059). Model-derived cumulative PAFs were 29.7% for COPD and 23.7% for PAD.
COPD and PAD demonstrate distinct yet overlapping global spatial patterns among older adults, sharing several population-level exposure correlates. Due to the cross-sectional and ecological nature of this study, the observed associations and PAFs should not be interpreted as individual-level causal effects. These findings may inform regional public health planning and generate hypotheses for prospective validation of integrated cardiopulmonary risk assessment.

PMID:
42890759
Bibliographic data and abstract were imported from PubMed on 18 Oct 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.