Navigating the COVID-19 pandemic: Experiences and self-management approaches adopted by people with interstitial lung disease.

BACKGROUND: People with interstitial lung disease (ILD) were deemed more vulnerable to the SARS-CoV-2 virus and isolated as a means of reducing risk of infection. This study examined the impact of the pandemic on daily life, psychological wellbeing and access to healthcare and identified approaches undertaken to remain safe. METHODS: Four specialist clinics in tertiary centres in Australia (Victoria: two sites; New South Wales: one site; Western Australia: one site) recruited patients with ILD during an 8-week period from March 2021. Semi-structured telephone interviews were conducted with transcripts analysed using principles of grounded theory. RESULTS: Ninety participants were interviewed between April and December 2021. Participants were predominantly female, former smokers with an average age of 66 years. IPF and connective tissue-ILD being the most common subtypes. Five main themes were identified: vulnerability reduced social interaction and isolation, access to healthcare services and support, staying active, emotional and psychological impact. Self-management strategies included staying active both physically and mentally. DISCUSSION: Self-management was key to managing the impact of the pandemic. In combination with advances in technology, implementation of strategies for monitoring wellbeing and support for self-management provides an opportunity to leverage the lessons learnt to ensure a more individualised model of care for people with ILD.

Treatment of idiopathic pulmonary fibrosis and progressive pulmonary fibrosis: A position statement from the Thoracic Society of Australia and New Zealand 2023 revision.

Idiopathic pulmonary fibrosis (IPF) is a progressive disease leading to significant morbidity and mortality. In 2017 the Thoracic Society of Australia and New Zealand (TSANZ) and Lung Foundation Australia (LFA) published a position statement on the treatment of IPF. Since that time, subsidized anti-fibrotic therapy in the form of pirfenidone and nintedanib is now available in both Australia and New Zealand. More recently, evidence has been published in support of nintedanib for non-IPF progressive pulmonary fibrosis (PPF). Additionally, there have been numerous publications relating to the non-pharmacologic management of IPF and PPF. This 2023 update to the position statement for treatment of IPF summarizes developments since 2017 and reaffirms the importance of a multi-faceted approach to the management of IPF and progressive pulmonary fibrosis.

Predicting New-onset Exertional and Resting Hypoxemia in Fibrotic Interstitial Lung Disease.

Rationale: Hypoxemia in fibrotic interstitial lung disease (ILD) indicates disease progression and is of prognostic significance. The onset of hypoxemia signifies disease progression and predicts mortality in fibrotic ILD. Accurately predicting new-onset exertional and resting hypoxemia prompts appropriate patient discussion and timely consideration of home oxygen. Objectives: We derived and externally validated a risk prediction tool for both new-onset exertional and new-onset resting hypoxemia. Methods: This study used ILD registries from Canada for the derivation cohort and from Australia and the United States for the validation cohort. New-onset exertional and resting hypoxemia were defined as nadir oxyhemoglobin saturation < 88% during 6-minute-walk tests, resting oxyhemoglobin saturation < 88%, or the initiation of ambulatory or continuous oxygen. Candidate predictors included patient demographics, ILD subtypes, and pulmonary function. Time-varying Cox regression was used to identify the top-performing prediction model according to Akaike information criterion and clinical usability. Model performance was assessed using Harrell's C-index and goodness-of-fit (GoF) likelihood ratio test. A categorized risk prediction tool was developed. Results: The best-performing prediction model for both new-onset exertional and new-onset resting hypoxemia included age, body mass index, a diagnosis of idiopathic pulmonary fibrosis, and percent predicted forced vital capacity and diffusing capacity of carbon monoxide. The risk prediction tool exhibited good performance for exertional hypoxemia (C-index, 0.70; GoF, P = 0.85) and resting hypoxemia (C-index, 0.77; GoF, P = 0.27) in the derivation cohort, with similar performance in the validation cohort except calibration for resting hypoxemia (GoF, P = 0.001). Conclusions: This clinically applicable risk prediction tool predicted new-onset exertional and resting hypoxemia at 6 months in the derivation cohort and a diverse validation cohort. Suboptimal GoF in the validation cohort likely reflected overestimation of hypoxemia risk and indicated that the model is not flawed because of underestimation of hypoxemia.

Long-term exposure to low concentrations of air pollution and decline in lung function in people with idiopathic pulmonary fibrosis: Evidence from Australia.

BACKGROUND AND OBJECTIVE: Little is known about the association between ambient air pollution and idiopathic pulmonary fibrosis (IPF) in areas with lower levels of exposure. We aimed to investigate the impact of air pollution on lung function and rapid progression of IPF in Australia. METHODS: Participants were recruited from the Australian IPF Registry (n = 570). The impact of air pollution on changes in lung function was assessed using linear mixed models and Cox regression was used to investigate the association with rapid progression. RESULTS: Median (25th-75th percentiles) annual fine particulate matter (<2.5 µm, PM2.5 ) and nitrogen dioxide (NO2 ) were 6.8 (5.7, 7.9) µg/m3 and 6.7 (4.9, 8.2) ppb, respectively. Compared to living more than 100 m from a major road, living within 100 m was associated with a 1.3% predicted/year (95% confidence interval [CI] -2.4 to -0.3) faster annual decline in diffusing capacity of the lungs for carbon monoxide (DLco). Each interquartile range (IQR) of 2.2 µg/m3 increase in PM2.5 was associated with a 0.9% predicted/year (95% CI -1.6 to -0.3) faster annual decline in DLco, while there was no association observed with NO2 . There was also no association between air pollution and rapid progression of IPF. CONCLUSION: Living near a major road and increased PM2.5 were both associated with an increased rate of annual decline in DLco. This study adds to the evidence supporting the negative effects of air pollution on lung function decline in people with IPF living at low-level concentrations of exposure.

Occupational Interstitial Lung Diseases.

Occupational exposures are directly causal or partially contributory to the development of interstitial lung diseases. A detailed occupational history, relevant high-resolution computed tomography findings, and where relevant additional histopathology, are required to make a diagnosis. Treatment options are limited, and further exposure avoidance is likely to reduce disease progression.

Understanding the telehealth experience of care by people with ILD during the COVID-19 pandemic: what have we learnt?

INTRODUCTION: The COVID-19 pandemic resulted in a rapid transformation of health services. This study aimed to understand the experiences of healthcare by people with interstitial lung disease (ILD), to inform future service delivery. METHODS: Four specialist clinics in tertiary centres in Australia (Victoria:2 sites; New South Wales: 1 site; Western Australia: 1 site) recruited patients with ILD during an 8-week period from March 2021. Participants completed a COVID-specific questionnaire focused on health-related experiences during 2020. RESULTS: Ninety nine (65% of 153) participants completed the questionnaire. 47% had idiopathic pulmonary fibrosis or connective tissue disease-associated ILD, 62% were female and the average age was 66 years. Whilst 56% rated their overall health in 2020 as the same as months prior, 38% indicated a worsening in health attributed to reduced physical activity and fear of contracting the virus. Access to healthcare professionals was 'good' in 61%, and 'fair-to-poor' for 37% due to missed respiratory assessments, with telehealth (mainly telephone) being perceived as less effective. 89% had contact with respiratory physicians, 68% with general practitioners, predominantly via telephone, with few video consultations. High satisfaction with care was reported by 78%, with lower satisfaction attributed to delays in assessments, disruption to usual services such as pulmonary rehabilitation, and dissatisfaction with telehealth. CONCLUSION: People with ILD were generally satisfied with their care during 2020, however reduced access to healthcare professionals was challenging for those experiencing a deterioration in health. Telehealth was largely well received but did not always meet the needs of people with ILD particularly when unwell.

A Composite Serum Biomarker Index for the Diagnosis of Systemic Sclerosis-Associated Interstitial Lung Disease: A Multicenter, Observational Cohort Study.

OBJECTIVE: In patients with systemic sclerosis (SSc), we investigated composite serum biomarker panels for the diagnosis and risk stratification of SSc-associated interstitial lung disease (SSc-ILD). METHODS: We analyzed 28 biomarkers in 640 participants: 259 patients with SSc-ILD and 179 SSc patients without ILD (Australian Scleroderma Cohort Study), 172 patients with idiopathic pulmonary fibrosis (IPF-controls) (Australian IPF Registry), and 30 healthy controls. A composite index was developed from biomarkers associated with ILD in multivariable analysis derived at empirical thresholds. We evaluated the performance of the index to identify ILD, and specifically SSc-ILD, and its association with lung function, disease extent on radiography, and patient health-related quality of life in derivation and validation cohorts. Biomarkers to distinguish SSc-ILD from IPF-controls were identified. RESULTS: A composite biomarker index, comprising surfactant protein D (SP-D), Ca15-3, and intercellular adhesion molecule 1 (ICAM-1), was strongly associated with SSc-ILD diagnosis, independent of age, sex, smoking history, and lung function (for biomarker index score 3, pooled adjusted odds ratio was 12.72 (95% confidence interval 4.59-35.21) (P < 0.001). The composite index strengthened the performance of individual biomarkers for SSc-ILD identification. In SSc patients, a higher index was associated with worse baseline disease severity (for biomarker index score 3 relative to biomarker index score 0, the adjusted absolute change in forced vital capacity percent predicted was -17.84% and the diffusing capacity for carbon monoxide percent predicted was -20.16%; both P < 0.001). CONCLUSION: A composite serum biomarker index, comprising SP-D, Ca15-3, and ICAM-1, may improve the identification and risk stratification of ILD in SSc patients at baseline.

Inhaled pirfenidone solution (AP01) for IPF: a randomised, open-label, dose-response trial.

INTRODUCTION: Oral pirfenidone reduces lung function decline and mortality in patients with idiopathic pulmonary fibrosis (IPF). Systemic exposure can have significant side effects, including nausea, rash, photosensitivity, weight loss and fatigue. Reduced doses may be suboptimal in slowing disease progression. METHODS: This phase 1b, randomised, open-label, dose-response trial at 25 sites in six countries (Australian New Zealand Clinical Trials Registry (ANZCTR) registration number ACTRN12618001838202) assessed safety, tolerability and efficacy of inhaled pirfenidone (AP01) in IPF. Patients diagnosed within 5 years, with forced vital capacity (FVC) 40%-90% predicted, and intolerant, unwilling or ineligible for oral pirfenidone or nintedanib were randomly assigned 1:1 to nebulised AP01 50 mg once per day or 100 mg two times per day for up to 72 weeks. RESULTS: We present results for week 24, the primary endpoint and week 48 for comparability with published trials of antifibrotics. Week 72 data will be reported as a separate analysis pooled with the ongoing open-label extension study. Ninety-one patients (50 mg once per day: n=46, 100 mg two times per day: n=45) were enrolled from May 2019 to April 2020. The most common treatment-related adverse events (frequency, % of patients) were all mild or moderate and included cough (14, 15.4%), rash (11, 12.1%), nausea (8, 8.8%), throat irritation (5, 5.5%), fatigue (4, 4.4%) and taste disorder, dizziness and dyspnoea (three each, 3.3%). Changes in FVC % predicted over 24 and 48 weeks, respectively, were -2.5 (95% CI -5.3 to 0.4, -88 mL) and -4.9 (-7.5 to -2.3,-188 mL) in the 50 mg once per day and 0.6 (-2.2 to 3.4, 10 mL) and -0.4 (-3.2 to 2.3, -34 mL) in the 100 mg two times per day group. DISCUSSION: Side effects commonly associated with oral pirfenidone in other clinical trials were less frequent with AP01. Mean FVC % predicted remained stable in the 100 mg two times per day group. Further study of AP01 is warranted. TRIAL REGISTRATION NUMBER: ACTRN12618001838202 Australian New Zealand Clinical Trials Registry.

Sex- and Race-Based Differences in the Treatment of Interstitial Lung Diseases in North America and Australasia.

BACKGROUND: Biological sex, gender, and race are important considerations in patients with interstitial lung diseases (ILDs). RESEARCH QUESTION: Does a patient's sex assigned at birth, and race, influence ILD treatment initiation? STUDY DESIGN AND METHODS: Patients with ILD from three longitudinal prospective registries were compared in this observational study. ILD-related medications included antifibrotics and immunomodulating medications. Race was dichotomized as "White" vs "non-White." Time to treatment initiation was determined from the date of the initial ILD registry visit to the date of first medication initiation. Proportions of treated patients were compared between groups by χ2 test. Cox proportional analysis was used to determine how sex and race were associated with time to treatment initiation stratified by ILD diagnosis. RESULTS: A total of 4,572 patients were included across all cohorts. The proportion of men who received treatment was higher than for women in the Canadian cohort (47% vs 40%; P < .001), and the proportion of White patients who received treatment was also higher compared with non-White patients (46% vs 36%; P < .001). In contrast, the proportion of treated men in the Chicago cohort was lower compared with women (56% vs 64%; P = .005), and that of White patients was lower compared with non-White patients (56% vs 69%; P < .001). No sex- or race-based differences in proportions of patients treated were found in the Australasian cohort. White race was significantly associated with earlier treatment initiation compared with non-White race across diagnoses in the Canadian cohort, whereas the opposite association was found in the Australasian cohort. INTERPRETATION: Sex- and race-based differences exist in the initiation of ILD treatment, with variability across different cohorts in different countries. Reasons for these differences need to be further explored in future studies.

Idiopathic Pulmonary Fibrosis Is Associated with Common Genetic Variants and Limited Rare Variants.

Rationale: Idiopathic pulmonary fibrosis (IPF) is a rare, irreversible, and progressive disease of the lungs. Common genetic variants, in addition to nongenetic factors, have been consistently associated with IPF. Rare variants identified by candidate gene, family-based, and exome studies have also been reported to associate with IPF. However, the extent to which rare variants, genome-wide, may contribute to the risk of IPF remains unknown. Objectives: We used whole-genome sequencing to investigate the role of rare variants, genome-wide, on IPF risk. Methods: As part of the Trans-Omics for Precision Medicine Program, we sequenced 2,180 cases of IPF. Association testing focused on the aggregated effect of rare variants (minor allele frequency ⩽0.01) within genes or regions. We also identified individual rare variants that are influential within genes and estimated the heritability of IPF on the basis of rare and common variants. Measurements and Main Results: Rare variants in both TERT and RTEL1 were significantly associated with IPF. A single rare variant in each of the TERT and RTEL1 genes was found to consistently influence the aggregated test statistics. There was no significant evidence of association with other previously reported rare variants. The SNP heritability of IPF was estimated to be 32% (SE = 3%). Conclusions: Rare variants within the TERT and RTEL1 genes and well-established common variants have the largest contribution to IPF risk overall. Efforts in risk profiling or the development of therapies for IPF that focus on TERT, RTEL1, common variants, and environmental risk factors are likely to have the largest impact on this complex disease.

Machine learning in radiology: the new frontier in interstitial lung diseases.

Challenges for the effective management of interstitial lung diseases (ILDs) include difficulties with the early detection of disease, accurate prognostication with baseline data, and accurate and precise response to therapy. The purpose of this Review is to describe the clinical and research gaps in the diagnosis and prognosis of ILD, and how machine learning can be applied to image biomarker research to close these gaps. Machine-learning algorithms can identify ILD in at-risk populations, predict the extent of lung fibrosis, correlate radiological abnormalities with lung function decline, and be used as endpoints in treatment trials, exemplifying how this technology can be used in care for people with ILD. Advances in image processing and analysis provide further opportunities to use machine learning that incorporates deep-learning-based image analysis and radiomics. Collaboration and consistency are required to develop optimal algorithms, and candidate radiological biomarkers should be validated against appropriate predictors of disease outcomes.

The relative contribution of co-morbidities to health-related quality of life of people with idiopathic pulmonary fibrosis using the Assessment of Quality of Life-8-Dimension multi-attribute utility instrument.

PURPOSE: Little is known about the impact of co-morbidities on health-related quality of life (HRQoL) for people with idiopathic pulmonary fibrosis (IPF). We aimed to investigate the relative contribution of co-morbidities to HRQoL of people with IPF. METHODS: N = 157 participants were recruited from the Australian IPF Registry (AIPFR). Health state utilities (HSUs), and the super-dimensions of physical and psychosocial scores were measured using the Assessment of Quality of Life-8-Dimensions (AQoL-8D). The impact of co-morbidities on HRQoL was investigated using linear regression and general dominance analyses. RESULTS: A higher number of co-morbidities was associated with lower HSUs (p trend = 0.002). Co-morbidities explained 9.1% of the variance of HSUs, 16.0% of physical super-dimensional scores, and 4.2% of psychosocial super-dimensional scores. Arthritis was associated with a significant reduction on HSUs (ß = - 0.09, 95% confidence interval [CI] - 0.16 to - 0.02), largely driven by reduced scores on the physical super-dimension (ß = - 0.13, 95% CI - 0.20 to - 0.06). Heart diseases were associated with a significant reduction on HSUs (ß = - 0.09, 95% CI - 0.16 to - 0.02), driven by reduced scores on physical (ß = - 0.09, 95% CI - 0.16 to - 0.02) and psychosocial (ß = -0.10, 95% CI - 0.17 to - 0.02) super-dimensions. CONCLUSIONS: Co-morbidities significantly impact HRQoL of people with IPF, with markedly negative impacts on their HSUs and physical health. A more holistic approach to the care of people with IPF is important as better management of these co-morbidities could lead to improved HRQoL in people with IPF.

Clinical utility of a standardized chronic hypersensitivity pneumonitis exposure questionnaire.

BACKGROUND AND OBJECTIVE: Identification of an exposure is integral to the diagnosis, management, and prognostication of chronic hypersensitivity pneumonitis (CHP). Standardized questionnaires may aid in the identification of exposures, however, there currently are no evidence-based patient-validated questionnaires available. Key qualifiers (including duration and frequency) which indicate exposure relevance are also poorly defined. This study assessed the use of a standardized CHP exposure questionnaire in the identification of exposures and diagnostic confidence of CHP. METHODS: People with a multi-disciplinary meeting (MDM) diagnosis from five Australian interstitial lung disease (ILD) expert centres who provided informed consent were included. Participants completed a previously developed standardized CHP Exposure Questionnaire. Responses were collected with the participant's MDM data, including diagnosis, diagnostic confidence, and clinician-elicited exposures. RESULTS: One hundred thirty participants (IPF = 58, CHP = 24, CTD-ILD = 17, unclassifiable = 19, other = 12) were included. In 33% of CHP participants, a standardized questionnaire elicited an exposure where the clinician did not. 63% of these had provisional low confidence CHP; and an exposure history would have increased the diagnostic confidence in these cases. Using the standardized questionnaire, 96% of CHP participants reporting any exposure, compared with 75% of non-HP ILD participants. CHP participants were 3.5 times more likely (p = 0.004) to report their symptoms improved on avoidance, and 2.3 times more likely (p = 0.018) to report daily frequent exposure, compared with non-HP ILDs. CONCLUSION: A standardized questionnaire which elicits exposure characteristics in addition to presence or absence of relevant exposures can increase the diagnostic confidence of CHP and reduce the proportion of antigen-indeterminate CHP.

Safety, tolerability, and efficacy of pirfenidone in patients with rheumatoid arthritis-associated interstitial lung disease: a randomised, double-blind, placebo-controlled, phase 2 study.

BACKGROUND: Interstitial lung disease is a known complication of rheumatoid arthritis, with a lifetime risk of developing the disease in any individual of 7·7%. We aimed to assess the safety, tolerability, and efficacy of pirfenidone for the treatment of patients with rheumatoid arthritis-associated interstitial lung disease (RA-ILD). METHODS: TRAIL1 was a randomised, double-blind, placebo-controlled, phase 2 trial done in 34 academic centres specialising in interstitial lung disease in four countries (the UK, the USA, Australia, and Canada). Adults aged 18-85 years were eligible for inclusion if they met the 2010 American College of Rheumatology and European Alliance of Associations for Rheumatology criteria for rheumatoid arthritis and had interstitial lung disease on a high-resolution CT scan imaging and, when available, lung biopsy. Exclusion criteria include smoking, clinical history of other known causes of interstitial lung disease, and coexistant clinically significant COPD or asthma. Patients were randomly assigned (1:1) to receive 2403 mg oral pirfenidone (pirfenidone group) or placebo (placebo group) daily. The primary endpoint was the incidence of the composite endpoint of a decline from baseline in percent predicted forced vital capacity (FVC%) of 10% or more or death during the 52-week treatment period assessed in the intention-to-treat population. Key secondary endpoints included change in absolute and FVC% over 52 weeks, the proportion of patients with a decline in FVC% of 10% or more, and the frequency of progression as defined by Outcome Measures in Rheumatoid Arthritis Clinical Trials (OMERACT) in the intention-to-treat population. This study is registered with ClinicalTrials.gov, NCT02808871. FINDINGS: From May 15, 2017, to March 31, 2020, 231 patients were assessed for inclusion, of whom 123 patients were randomly assigned (63 [51%] to the pirfenidone group and 60 [49%] to the placebo group). The trial was stopped early (March 31, 2020) due to slow recruitment and the COVID-19 pandemic. The difference in the proportion of patients who met the composite primary endpoint (decline in FVC% from baseline of 10% or more or death) between the two groups was not significant (seven [11%] of 63 patients in the pirfenidone group vs nine [15%] of 60 patients in the placebo group; OR 0·67 [95% CI 0·22 to 2·03]; p=0·48). Compared with the placebo group, patients in the pirfenidone group had a slower rate of decline in lung function, measured by estimated annual change in absolute FVC (-66 vs -146; p=0·0082) and FVC% (-1·02 vs -3·21; p=0·0028). The groups were similar with regards to the decline in FVC% by 10% or more (five [8%] participants in the pirfenidone group vs seven [12%] in the placebo group; OR 0·52 [95% CI 0·14-1·90]; p=0·32) and the frequency of progression as defined by OMERACT (16 [25%] in the pirfenidone group vs 19 [32%] in the placebo group; OR 0·68 [0·30-1·54]; p=0·35). There was no significant difference in the rate of treatment-emergent serious adverse events between the two groups, and there were no treatment-related deaths. INTERPRETATION: Due to early termination of the study and underpowering, the results should be interpreted with caution. Despite not meeting the composite primary endpoint, pirfenidone slowed the rate of decline of FVC over time in patients with RA-ILD. Safety in patients with RA-ILD was similar to that seen in other pirfenidone trials. FUNDING: Genentech.

Matrix metalloproteinase-7 is increased in lung bases but not apices in idiopathic pulmonary fibrosis.

Introduction: Idiopathic pulmonary fibrosis (IPF) is a progressively fibrotic lung condition with poor prognosis. Matrix metalloproteinase-7 (MMP7) is a protein secreted by epithelial cells in IPF lungs. It is not known if MMP7 expression correlates with fibrotic changes in lung tissue. Methods: Tissue samples from lung apices and bases were obtained from 20 IPF patients and 14 non-diseased control (NDC) donors. In formalin-fixed paraffin-embedded sections, histological assessment of fibrosis was performed; overall MMP7 positivity was assessed by immunohistochemistry and MMP7+ cells were quantified using multiplex immunohistochemistry. Protein expression of MMP7 in whole lung lysates was quantified by Western blotting. Bulk tissue transcriptomic profiles of 101 samples were analysed using RNA sequencing technologies. Results: Lung tissue from IPF bases was more fibrotic than in apices. MMP7 protein is elevated in IPF lung base tissue. In IPF whole lung lysates, MMP7 protein levels are increased compared to NDC donors and was increased in IPF lung bases compared to apices. MMP7 protein levels correlated with MMP7 gene expression levels in lung tissue. MMP7 transcript levels were increased in IPF base compared to NDC base lung tissue and increased in IPF base tissue compared to IPF apex tissue. Conclusions: Our cross-sectional study suggests that lung epithelial MMP7 expression increases as the tissue becomes more fibrotic and identifies a potentially nonepithelial or immune-cell source. Mechanisms of disease progression in IPF are still unclear, and our study suggests aberrant MMP7 production may be a histological starting point of lung tissue fibrosis.

Quantitative computed tomography predicts outcomes in idiopathic pulmonary fibrosis.

BACKGROUND AND OBJECTIVE: Prediction of disease course in patients with progressive pulmonary fibrosis remains challenging. The purpose of this study was to assess the prognostic value of lung fibrosis extent quantified at computed tomography (CT) using data-driven texture analysis (DTA) in a large cohort of well-characterized patients with idiopathic pulmonary fibrosis (IPF) enrolled in a national registry. METHODS: This retrospective analysis included participants in the Australian IPF Registry with available CT between 2007 and 2016. CT scans were analysed using the DTA method to quantify the extent of lung fibrosis. Demographics, longitudinal pulmonary function and quantitative CT metrics were compared using descriptive statistics. Linear mixed models, and Cox analyses adjusted for age, gender, BMI, smoking history and treatment with anti-fibrotics were performed to assess the relationships between baseline DTA, pulmonary function metrics and outcomes. RESULTS: CT scans of 393 participants were analysed, 221 of which had available pulmonary function testing obtained within 90 days of CT. Linear mixed-effect modelling showed that baseline DTA score was significantly associated with annual rate of decline in forced vital capacity and diffusing capacity of carbon monoxide. In multivariable Cox proportional hazard models, greater extent of lung fibrosis was associated with poorer transplant-free survival (hazard ratio [HR] 1.20, p < 0.0001) and progression-free survival (HR 1.14, p < 0.0001). CONCLUSION: In a multi-centre observational registry of patients with IPF, the extent of fibrotic abnormality on baseline CT quantified using DTA is associated with outcomes independent of pulmonary function.

Deep Learning-based Outcome Prediction in Progressive Fibrotic Lung Disease Using High-Resolution Computed Tomography.

Rationale: Reliable outcome prediction in patients with fibrotic lung disease using baseline high-resolution computed tomography (HRCT) data remains challenging. Objectives: To evaluate the prognostic accuracy of a deep learning algorithm (SOFIA [Systematic Objective Fibrotic Imaging Analysis Algorithm]), trained and validated in the identification of usual interstitial pneumonia (UIP)-like features on HRCT (UIP probability), in a large cohort of well-characterized patients with progressive fibrotic lung disease drawn from a national registry. Methods: SOFIA and radiologist UIP probabilities were converted to Prospective Investigation of Pulmonary Embolism Diagnosis (PIOPED)-based UIP probability categories (UIP not included in the differential, 0-4%; low probability of UIP, 5-29%; intermediate probability of UIP, 30-69%; high probability of UIP, 70-94%; and pathognomonic for UIP, 95-100%), and their prognostic utility was assessed using Cox proportional hazards modeling. Measurements and Main Results: In multivariable analysis adjusting for age, sex, guideline-based radiologic diagnosis, anddisease severity (using total interstitial lung disease [ILD] extent on HRCT, percent predicted FVC, DlCO, or the composite physiologic index), only SOFIA UIP probability PIOPED categories predicted survival. SOFIA-PIOPED UIP probability categories remained prognostically significant in patients considered indeterminate (n = 83) by expert radiologist consensus (hazard ratio, 1.73; P < 0.0001; 95% confidence interval, 1.40-2.14). In patients undergoing surgical lung biopsy (n = 86), after adjusting for guideline-based histologic pattern and total ILD extent on HRCT, only SOFIA-PIOPED probabilities were predictive of mortality (hazard ratio, 1.75; P < 0.0001; 95% confidence interval, 1.37-2.25). Conclusions: Deep learning-based UIP probability on HRCT provides enhanced outcome prediction in patients with progressive fibrotic lung disease when compared with expert radiologist evaluation or guideline-based histologic pattern. In principle, this tool may be useful in multidisciplinary characterization of fibrotic lung disease. The utility of this technology as a decision support system when ILD expertise is unavailable requires further investigation.