BackgroundMarkers of idiopathic pulmonary fibrosis (IPF) severity are based on measurements of forced vital capacity (FVC), diffusing capacity (DLCO) and CT. The pulmonary vessel volume (PVV) is a novel quantitative and independent prognostic structural indicator derived from automated CT analysis. The current prospective cross-sectional study investigated whether respiratory oscillometry provides complementary data to pulmonary function tests (PFTs) and is correlated with PVV.MethodsFrom September 2019 to March 2020, we enrolled 89 patients with IPF diagnosed according to international guidelines. We performed standard spectral (5–37 Hz) and novel intrabreath tracking (10 Hz) oscillometry followed by PFTs. Patients were characterised with the gender-age-physiology (GAP) score. CT images within 6 months of oscillometry were analysed in a subgroup (26 patients) using automated lung texture analysis. Correlations between PFTs, oscillometry and imaging variables were investigated using different regression models.FindingsThe cohort (29F/60M; age=71.7±7.8 years) had mild IPF (%FVC=70±17, %DLCO=62±17). Spectral oscillometry revealed normal respiratory resistance, low reactance, especially during inspiration at 5 Hz (X5in), elevated reactance area and resonance frequency. Intrabreath oscillometry identified markedly low reactance at end-inspiration (XeI). XeI and X5in strongly correlated with FVC (r2=0.499 and 0.435) while XeI was highly (p=0.004) and uniquely correlated with the GAP score. XeI and PVV exhibited the strongest structural-functional relationship (r2=0.690), which remained significant after adjusting for %FVC, %DLCO and GAP score.InterpretationXeI is an independent marker of IPF severity that offers additional information to standard PFTs. The data provide a cogent rationale for adding oscillometry in IPF assessment.
BackgroundChronic lung allograft dysfunction (CLAD) is the principal cause of graft failure in lung transplant recipients and prognosis depends on CLAD phenotype. We used machine learning computed tomography (CT) lung texture analysis tool at CLAD diagnosis for phenotyping and prognostication compared to radiologists’ scoring.MethodsThis retrospective study included all adult first double-lung transplant patients (01/2010–12/2015) with CLAD (censored 12/2019) and inspiratory CT near CLAD diagnosis. The machine learning tool quantified ground-glass opacity, reticulation, hyperlucent lung, and pulmonary vessel volume (PVV). Two radiologists scored for ground-glass opacity, reticulation, consolidation, pleural effusion, air trapping and bronchiectasis. Receiver operating characteristic curve analysis was used to evaluate the diagnostic performance of machine learning and radiologist for CLAD phenotype. Multivariable Cox proportional-hazards regression analysis for allograft survival controlled for age, sex, native lung disease, cytomegalovirus serostatus, and CLAD phenotype (bronchiolitis obliterans syndrome [BOS] and restrictive allograft syndrome [RAS]/mixed).Results88 patients were included (57 BOS, 20 RAS/mixed, and 11 unclassified/undefined) with CT a median 9.5 days from CLAD onset. Radiologist and machine learning parameters phenotyped RAS/mixed with PVV as the strongest indicator (AUC 0.85). Machine learning hyperlucent lung phenotyped BOS using only inspiratory CT (AUC=0.76). Radiologist and machine learning parameters predicted graft failure in the multivariable analysis, best with PVV (HR=1.23, 95%CI 1.05–1.44, p=0.01).ConclusionsMachine learning discriminated between CLAD phenotypes on CT. Both radiologist and machine learning scoring were associated with graft failure, independent of CLAD phenotype. PVV, unique to machine learning, was the strongest in phenotyping and prognostication.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.