Back to all papers

Multidimensional cortical morphological alterations in COPD using explainable machine learning.

April 11, 2026pubmed logopapers

Authors

Chen J,Chen Y,Zhang K,Xu K,Sun G,Hei H,Huo W,Sheng W,Bahadori P,Ma G,Jin C

Affiliations (5)

  • Department of Radiology, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
  • Department of Radiology, Tangdu Hospital, Fourth Military Medical University, Xi'an, China.
  • Department of Radiology, Baoji Central Hospital, Baoji, China.
  • MR Research Collaboration, Siemens Healthineers, Shanghai, China.
  • Department of Radiology, Affiliated Hospital of the Shaanxi University of Traditional Chinese Medicine, Xianyang, China.

Abstract

Cognitive dysfunction is a common extrapulmonary manifestation of chronic obstructive pulmonary disease (COPD). Here, we applied an XGBoost-SHAP machine learning framework to identify cortical morphological features related to cognitive performance in COPD. Pulmonary, cognitive, and structural MRI data from 72 patients with COPD and 68 healthy controls were analyzed. Multidimensional cortical features distinguished COPD from controls, with cortical thickness in bilateral parahippocampal and precentral gyri, and the local gyrification index in the right insula, left middle frontal sulcus, and subcallosal area identified as the most influential features. Notably, right precentral cortical thickness was associated with both pulmonary function (FEV<sub>1</sub>/FVC) and cognition, mediating 29.19% of their relationship. These findings indicate that multidimensional cortical morphology is related to cognitive function in COPD and suggest a structural link within the lung-brain-cognition axis, highlighting the precentral gyrus as a region of interest.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.