Identification of risk factors for acute exacerbation of idiopathic pulmonary fibrosis based on baseline high-resolution computed tomography: a prospective observational study

Zhaojun Wang et al. evaluated risk factors for acute exacerbation of idiopathic pulmonary fibrosis (AE-IPF) using quantitative HRCT. The study enrolled 102 IPF patients, analyzing baseline parameters like honeycombing, whole lung volume, and pulmonary hypertension (PH). Using deep learning software such as AVIEW, these metrics demonstrated strong predictive potential. Honeycombing and PH emerged as key independent risk factors, and their combination with whole lung volume achieved high diagnostic accuracy (AUC 0.888, sensitivity 90%, specificity 78%). These findings highlight the value of quantitative HRCT in identifying patients at elevated AE-IPF risk, enabling targeted interventions. While limited by its single-center design and sample size, the study underscores the clinical promise of integrating AI tools like AVIEW into IPF management. Future research should aim for larger, multicenter cohorts to refine and validate predictive models, expanding the application of non-invasive diagnostics in pulmonary care.