BibTex format
@article{Nan:2025:10.1183/13993003.00981-2025,
author = {Nan, Y and Felder, FN and Humphries, S and Mackintosh, JA and Grainge, C and Jo, HE and Goh, N and Reynolds, PN and Hopkins, PMA and Navaratnam, V and Moodley, Y and Walters, H and Ellis, S and Keir, G and Zappala, C and Corte, T and Glaspole, I and Wells, AU and Yang, G and Walsh, SLF},
doi = {10.1183/13993003.00981-2025},
journal = {Eur Respir J},
title = {Prognostication in patients with idiopathic pulmonary fibrosis using quantitative airway analysis from HRCT: a retrospective study.},
url = {http://dx.doi.org/10.1183/13993003.00981-2025},
volume = {66},
year = {2025}
}
RIS format (EndNote, RefMan)
TY - JOUR
AB - BACKGROUND: Predicting shorter life expectancy is crucial for prioritising antifibrotic therapy in fibrotic lung diseases (FLDs), where progression varies widely, from stability to rapid deterioration. This heterogeneity complicates treatment decisions, emphasising the need for reliable baseline measures. This study focuses on leveraging an artificial intelligence (AI) model to address heterogeneity in disease outcomes, focusing on mortality as the ultimate measure of disease trajectory. METHODS: This retrospective study included 1744 anonymised patients who underwent high-resolution computed tomography (HRCT) scanning. The AI model, SABRE (Smart Airway Biomarker Recognition Engine), was developed using data from patients with various lung diseases (n=460, including lung cancer, pneumonia, emphysema and fibrosis). Then, 1284 HRCT scans with evidence of diffuse FLD from the Australian Idiopathic Pulmonary Fibrosis Registry and Open Source Imaging Consortium were used for clinical analyses. Airway branches were categorised and quantified by anatomical structures and volumes, followed by multivariable analysis to explore the associations between these categories and patients' progression and mortality, adjusting for disease severity or traditional measurements. RESULTS: Cox regression identified SABRE-based variables as independent predictors of mortality and progression, even adjusting for disease severity (fibrosis extent, traction bronchiectasis extent and interstitial lung disease extent), traditional measures (forced vital capacity percentage predicted, diffusing capacity of the lung for carbon monoxide (D LCO) percentage predicted and composite physiological index), and previously reported deep learning algorithms for fibrosis quantification and morphological analysis. Combining SABRE with D LCO significantly improved prognosis utility, yielding an area under the curve of 0.852 at the first year and a C-index of 0.752. CONCLUSIONS: SABRE-based variables capture p
AU - Nan,Y
AU - Felder,FN
AU - Humphries,S
AU - Mackintosh,JA
AU - Grainge,C
AU - Jo,HE
AU - Goh,N
AU - Reynolds,PN
AU - Hopkins,PMA
AU - Navaratnam,V
AU - Moodley,Y
AU - Walters,H
AU - Ellis,S
AU - Keir,G
AU - Zappala,C
AU - Corte,T
AU - Glaspole,I
AU - Wells,AU
AU - Yang,G
AU - Walsh,SLF
DO - 10.1183/13993003.00981-2025
PY - 2025///
TI - Prognostication in patients with idiopathic pulmonary fibrosis using quantitative airway analysis from HRCT: a retrospective study.
T2 - Eur Respir J
UR - http://dx.doi.org/10.1183/13993003.00981-2025
UR - https://www.ncbi.nlm.nih.gov/pubmed/40744692
VL - 66
ER -