Abstract Objective While lung aging is a recognized risk factor for chronic lung diseases, no non-invasive method currently exists to accurately quantify its biological progression. We aimed to develop a whole-lung radiomics model to establish a “normal lung aging” baseline and apply it to characterize accelerated aging in combined pulmonary fibrosis and emphysema (CPFE)—a condition with poor prognosis and scarce biomarkers. Methods Using a cohort of healthy, non-smoking adults without lung disease (n = 2,486), we trained an XGBoost model based on 2,671 radiomic features from low-dose CT scans to define a normative lung aging trajectory. This model was then applied to 794 CPFE patients from three centers (mean age 58±7 years) to compute an aging deviation score (ADS), defined as the absolute difference between predicted lung age and chronological age. Multivariable Cox regression was used to assess the association of ADS with all-cause mortality and pulmonary function (FVC%, DLCO%). Results CPFE patients exhibited significantly higher ADS compared to healthy controls (p 0.001), indicating disrupted aging patterns. Each one-unit increase in ADS was independently associated with increased mortality (HR = 2.29, 95% CI: 1.58-3.31). Patients with high ADS (30) showed more rapid declines in FVC% (−3.2% vs. −1.1%, p = 0.002) and DLCO% (−4.1% vs. −1.8%, p = 0.001) compared to those with lower ADS. Conclusion The whole-lung radiomics-based aging deviation score provides a non-invasive measure of pathological lung aging in CPFE, offering potential for improved risk stratification and personalized management. This abstract is funded by: the National Key Technologies Research and Development Program Precision Medicine Research (2021YFC2500700 and 2016YFC0901101), the National Natural Science Foundation of China (82370072), and the National High Level Hos pital Clinical Research Funding (2022-NHLHCRF-LX-01-0104)
Wang et al. (2026) studied this question.