Interpretable chronic obstructive pulmonary disease identification using chest X-ray radiomics: a multicenter study
The clinical screening rate for COPD remains severely inadequate. The combined model integrating chest X-ray radiomic features and clinical variables enables accurate differentiation between patients with COPD and non-COPD individuals. Global SHAP analysis reveals that radiomic features are the primary factor influencing COPD identification, followed by age, sex, and smoking status. Local SHAP analysis can intuitively visualize the model's decision-making process at the individual sample level.
Authors
- YanMing Ge
- Yadi Wang (ORCID: https://orcid.org/0000-0002-6758-7470)
- Weihao Zhai
- Fangyi Xu (ORCID: https://orcid.org/0000-0001-6326-4327)
- Heng Zhang (ORCID: https://orcid.org/0000-0002-0103-2173)
- Qian Zhou (ORCID: https://orcid.org/0000-0001-7964-8130)
- XiaoQing Lin
- Yanqing Ma
- Huawei Wu
- Xiuxiu Zhou
- Qi Dai
- Taohu Zhou
- Li Fan
- Jie Li
Institutions
- Weifang Medical University (CN)
- Union Hospital (HK)
- University of Shanghai for Science and Technology (CN)
- Shanghai Jiao Tong University (CN)
- Fudan University (CN)
- Renji Hospital (CN)
- Sir Run Run Shaw Hospital (CN)
- Huadong Hospital (CN)
- Second Affiliated Hospital of Dalian Medical University (CN)
- Ningbo No. 2 Hospital (CN)
- Zhejiang Provincial People's Hospital (CN)
- Fujian Provincial Cancer Hospital (CN)
- Tianjin Chest Hospital (CN)
- Ningbo No.6 Hospital (CN)
- Huazhong University of Science and Technology (CN)
Publication Details
- Journal
- Insights into Imaging
- Published
- 2026-03-27
- DOI
- https://doi.org/10.1186/s13244-026-02254-z
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00