Harnessing Artificial Intelligence for Accurate Diagnosis and Radiomics Analysis of Combined Pulmonary Fibrosis and Emphysema: Insights from a Multicenter Cohort Study

Combined Pulmonary Fibrosis and Emphysema (CPFE), recognized as a distinct pulmonary syndrome in 2022, is characterized by unique clinical features and pathogenesis that can lead to respiratory failure and death. However, the diagnosis of CPFE presents significant challenges that impede effective treatment. Here, we assembled a multicenter dataset of three-dimensional (3D) computed tomography (CT) images of patients lungs from multiple hospitals across different provinces in China, including Xiangya Hospital, West China Hospital, and Fujian Provincial Hospital. Utilizing this dataset, we developed CPFENet, a deep learning-assisted diagnostic model specifically designed for CPFE patients. This model accurately classifies patients into CPFE, chronic obstructive pulmonary disease (COPD), and pulmonary fibrosis based on 3D CT data, demonstrating diagnostic performance comparable to that of professional radiologists. Furthermore, we extracted radiomic features from the 3D CT images to generate a CPFE score, a robust and efficient metric for characterizing the presence of CPFE. Using this score, we identified significant differences in CPFE scores between genders. To validate our findings, we retrospectively analyzed the gender distribution of patients across the participating hospitals, corroborating the accuracy of our results. Overall, our study represents the first multicenter systematic investigation of CPFE, providing a diagnostic model and clinical indicators that enable accurate classification and characterization of the syndrome. This research offers a valuable direction and benchmark for future studies on CPFE, potentially facilitating the development of targeted therapeutic strategies and improving patient outcomes.