Development and validation of a CT-based radiomics machine learning model for differentiating immune-related interstitial pneumonia.
Authors
Affiliations (9)
Affiliations (9)
- Chronic Airways Diseases Laboratory, Department of Respiratory and Critical Care Medicine, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China.
- Department of Medical Imaging Center, Nanfang Hospital, Southern Medical University, Guangzhou, PR China.
- Department of General Surgery, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China.
- Pulmonary and Critical Care Medicine, Shunde Hospital, Southern Medical University, Foshan, Guangdong, China.
- Department of Pulmonary and Critical Care Medicine, Guangzhou First People's Hospital, South China University of Technology, Guangdong, China.
- Guangdong Second Provincial General Hospital, Guangzhou, Guangdong, China.
- Chronic Airways Diseases Laboratory, Department of Respiratory and Critical Care Medicine, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China.. Electronic address: [email protected].
- Chronic Airways Diseases Laboratory, Department of Respiratory and Critical Care Medicine, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China.. Electronic address: [email protected].
- Chronic Airways Diseases Laboratory, Department of Respiratory and Critical Care Medicine, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China.. Electronic address: [email protected].
Abstract
Immune checkpoint inhibitor-related interstitial pneumonia (CIP) poses a diagnostic challenge due to its radiographic similarity to other pneumonias. We developed a non-invasive model using CT imaging to differentiate CIP from other pneumonias (OTP). We analyzed CIP and OTP patients after the immunotherapy from five medical centers between 2020 and 2023, and randomly divided into training and validation in 7:3. A radiomics model was developed using random forest analysis. A new model was then built by combining independent risk factors for CIP. The models were evaluated using ROC, calibration, and decision curve analysis. A total of 238 patients with pneumonia following immunotherapy were included, with 116 CIP and 122 OTP. After random allocation, the training cohort included 166 patients, and the validation included 72 patients. A radiomics model composed of 11 radiomic features was established using the random forest method, with an AUC of 0.833 for the training cohort and 0.821 for the validation. Univariate and multivariate logistic regression analysis revealed significant differences in smoking history, radiotherapy history, and radiomics score between CIP and OTP (p < 0.05). A new model was constructed based on these three factors and a nomogram was drawn. This model showed good calibration and net benefit in both the training and validation cohorts, with AUCs of 0.872 and 0.860, respectively. Using the random forest method of machine learning, we successfully constructed a CT-based radiomics CIP differential diagnostic model that can accurately, non-invasively, and rapidly provide clinicians with etiological support for pneumonia diagnosis.