Surg Today. 2021 Feb 12. doi: 10.1007/s00595-021-02232-6. Online ahead of print.

ABSTRACT

PURPOSE: This study was performed to compare the outcome of lung transplantation (LT) for idiopathic pleuroparenchymal fibroelastosis (IPPFE) with that of LT for idiopathic pulmonary fibrosis (IPF).

METHODS: We reviewed, retrospectively, all adult patients who underwent LT for IPPFE or IPF in Japan between 1998 and 2018.

RESULTS: There were 100 patients eligible for this study (31 with IPPFE and 69 with IPF). Patients with IPPFE tended to have a significantly lower body mass index (BMI) than those with IPF (median, 16.7 vs. 22.6 kg/m2, respectively; P < 0.01). However, Kaplan-Meier survival curves showed no significant difference in overall survival between the groups. The BMI did not increase in patients with IPPFE, even 1 year after LT (pretransplant, 16.5 ± 3.2 kg/m2 vs. 1 year post-transplant, 15.6 ± 2.5 kg/m2; P = 0.08). The percent predicted forced vital capacity (%FVC) 1 year after LT was significantly lower in the IPPFE group than in the IPF group (48.4% ± 19.5% vs. 68.6% ± 15.5%, respectively; P < 0.01).

CONCLUSIONS: Despite extrapulmonary problems such as a flat chest, low BMI, and associated restrictive impairment persisting in patients with IPPFE, patient survival after LT for IPPFE or IPF was equivalent.

PMID:33576927 | DOI:10.1007/s00595-021-02232-6

Am J Respir Crit Care Med. 2021 Feb 15;203(4):P10-P11. doi: 10.1164/rccm.2034P10.

NO ABSTRACT

PMID:33576729 | DOI:10.1164/rccm.2034P10

Cancers (Basel). 2021 Jan 31;13(3):539. doi: 10.3390/cancers13030539.

ABSTRACT

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a severe progressive interstitial lung disease. At 5-year follow-up, 15% of IPF patients develop lung cancer, which significantly reduces the survival rate. Here we review the literature on the clinical role of oncomarkers in IPF progression, and describe the trend of routine oncomarkers in IPF patients over the longest follow-up yet reported.

MATERIALS AND METHODS: A systematic search of the literature in PubMed was performed to find relevant studies published up to 24 September 2020. The most common oncomarkers were chosen to select papers related to pulmonary fibrosis. Then, 24 IPF patients and 25 non-IPF patients, followed at Careggi ILD Referral Centre and Siena Regional Referral Centre for ILD, were enrolled consecutively.

RESULTS: A few studies reported an association between serum oncomarkers and severity of IPF. NSE, CEA, Ca19.9, and Ca125 were higher in the IPF, than in the non-IPF, group at every follow-up (p < 0.05). Ca15.3 concentrations were higher in the IPF, than the non-IPF, group at t3 (p = 0.0080) and t4 (p = 0.0168). To improve the specificity and sensitivity of Ca15.3, a panel of biomarkers was analyzed, with the IPF group as dependent variable, and chitotriosidase, Cyfra 21.1, Ca15.3, Ca125, and Ca19.9 as independent variables.

CONCLUSIONS: This study focused on the discovery of multiple biomarker signatures, such as combinations of oncomarkers, that are widely and routinely available in biochemistry laboratories. The combination of clinical parameters and biological markers could help achieve more accurate results regarding prognosis and response to treatment in IPF. Our results could pave the way for a more "personalized" medical approach to patients affected by IPF.

PMID:33572642 | PMC:PMC7867006 | DOI:10.3390/cancers13030539

Cancers (Basel). 2021 Feb 9;13(4):689. doi: 10.3390/cancers13040689.

ABSTRACT

BACKGROUND: Krebs von den Lungen-6 (KL-6) was suggested as ILD biomarker including idiopathic pulmonary fibrosis (IPF). Lung cancer is one of the most severe comorbidity of IPF patients. This study aims to serially analyze KL-6 in IPF patients after 24 months of Nintedanib and to first investigate the biomarker behavior in IPF associated with adenocarcinoma.

MATERIALS AND METHODS: One hundred and forty-two ILD patients (median (IQR), 69 (63-75) years; 86 males) were retrospectively enrolled. Serial serum samples were collected from IPF patients before starting antifibrotic therapy and after 12 months. Serum KL-6 levels were measured by KL-6 reagent assay (Fujirebio Europe, UK).

RESULTS: Increased KL-6 concentrations were identified in IPF-LC patients than IPF, fibrotic hypersensitivity pneumonitis, and pulmonary fibrosis associated with autoimmune disease groups. A cut-off value was calculated to distinguish IPF and IPF-LC patients. IPF patients monitored for 24 months with Nintedanib showed persisted increased levels of KL-6 with a progressive decline of FVC percentages.

CONCLUSION: This preliminary study offers a first demonstration that very high serum concentrations of KL-6 in IPF-LC patients are associated with poor prognosis. Moreover, serial evaluation of serum KL-6 in IPF patients over 24 months of Nintedanib treatment revealed that most patients experienced a stabilization of lung function parameters and of serum concentrations of KL-6.

PMID:33572070 | DOI:10.3390/cancers13040689

PLoS One. 2021 Feb 11;16(2):e0246878. doi: 10.1371/journal.pone.0246878. eCollection 2021.

ABSTRACT

OBJECTIVE: Obstructive sleep apnea (OSA) are increasingly recognized as important features in diffuse parenchymal lung diseases (DPLDs) with differed prevalence and impact reported. The aim of this study is to systematically review the prevalence of comorbid OSA and characterize its impact on clinical and outcome measurements in adults with DPLDs.

METHODS: Publications addressing the prevalence of OSA in DPLDs and its impacts on DPLDs were selected from electronic databases. A random-effect model was used to estimate the pooled prevalence of OSA. Odds ratios (ORs) or mean differences (MDs) were used to assess the associations of OSA with clinical and outcome measurements. Heterogeneity was quantified by I2 with 95% confidence interval (95% CI).

RESULTS: 4 studies comprising 643 participants were included. Overall, the pooled prevalence of OSA among DPLDs was 72% (95% CI: 65-79%; I2 = 75.4%). Moderate-severe OSA was observed in 40% patients (95% CI: 28-52%; I2 = 90.8%). The prevalence was higher as 76% in idiopathic pulmonary fibrosis (IPF) patients than in connective tissue associated-ILD or sarcoidosis (60%). Although oxygen desaturation during sleep was greater in OSA group compared with non-OSA patients, there was no difference in lung function or systematic comorbidities between the two groups. The associations between OSA and the mortality or disease progression of DPLDs were also systematically reviewed.

CONCLUSION: In conclusion, OSA is a common comorbidity in DPLD patients, affecting approximately three in four patients, which may exacerbate the nocturnal desaturation and have negative influence on the outcomes. Larger studies with more homogeneous samples are warranted.

PMID:33571266 | PMC:PMC7877600 | DOI:10.1371/journal.pone.0246878

Hum Hered. 2021 Feb 10:1-13. doi: 10.1159/000513290. Online ahead of print.

ABSTRACT

INTRODUCTION: Studies that examine the role of rare variants in both simple and complex disease are increasingly common. Though the usual approach of testing rare variants in aggregate sets is more powerful than testing individual variants, it is of interest to identify the variants that are plausible drivers of the association. We present a novel method for prioritization of rare variants after a significant aggregate test by quantifying the influence of the variant on the aggregate test of association.

METHODS: In addition to providing a measure used to rank variants, we use outlier detection methods to present the computationally efficient Rare Variant Influential Filtering Tool (RIFT) to identify a subset of variants that influence the disease association. We evaluated several outlier detection methods that vary based on the underlying variance measure: interquartile range (Tukey fences), median absolute deviation, and SD. We performed 1,000 simulations for 50 regions of size 3 kb and compared the true and false positive rates. We compared RIFT using the Inner Tukey to 2 existing methods: adaptive combination of p values (ADA) and a Bayesian hierarchical model (BeviMed). Finally, we applied this method to data from our targeted resequencing study in idiopathic pulmonary fibrosis (IPF).

RESULTS: All outlier detection methods observed higher sensitivity to detect uncommon variants (0.001 < minor allele frequency, MAF > 0.03) compared to very rare variants (MAF <0.001). For uncommon variants, RIFT had a lower median false positive rate compared to the ADA. ADA and RIFT had significantly higher true positive rates than that observed for BeviMed. When applied to 2 regions found previously associated with IPF including 100 rare variants, we identified 6 polymorphisms with the greatest evidence for influencing the association with IPF.

DISCUSSION: In summary, RIFT has a high true positive rate while maintaining a low false positive rate for identifying polymorphisms influencing rare variant association tests. This work provides an approach to obtain greater resolution of the rare variant signals within significant aggregate sets; this information can provide an objective measure to prioritize variants for follow-up experimental studies and insight into the biological pathways involved.

PMID:33567433 | DOI:10.1159/000513290

Ann Am Thorac Soc. 2021 Feb 10. doi: 10.1513/AnnalsATS.202012-1479RL. Online ahead of print.

NO ABSTRACT

PMID:33567231 | DOI:10.1513/AnnalsATS.202012-1479RL

Cureus. 2021 Jan 4;13(1):e12482. doi: 10.7759/cureus.12482.

ABSTRACT

Fibrosis is the result of chronic inflammation and is known to pathologically occur in many organs and systems. Pirfenidone (PFD) is an anti-fibrotic known for its use in idiopathic pulmonary fibrosis (IPF). In addition to being an anti-fibrotic, it acts as an anti-inflammatory and antioxidant as well. There have been studies on PFD in other diseases, some clinical and others preclinical. We have compiled and reviewed them to highlight just how widespread PFD use could be. Among many benefits of PFD in IPF, PFD has effectively improved patients' survival in those who had an acute exacerbation of IPF and has reduced respiratory-related hospitalization, among few others. PFD also has shown an improvement in vital capacity in patients with chronic hypersensitive pneumonitis. Also, it has demonstrated anti-fibrotic effects in systemic sclerosis-associated interstitial lung disease. In other diseases outside the lungs, PFD has reversed insulin resistance and proven to be effective in non-alcoholic steatohepatitis (NASH). It has prevented blindness post-alkali injury to the eye and has proven to decrease the proliferation of mesothelioma cells, just to name a few. This review encourages further research in connection with PFD and its use in other diseases and PFD pros in IPF.

PMID:33564498 | PMC:PMC7861090 | DOI:10.7759/cureus.12482

Cell Death Discov. 2020 Jun 30;6(1):54. doi: 10.1038/s41420-020-0289-9.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is a chronic scarring disease in which aging, environmental exposure(s) and genetic susceptibility have been implicated in disease pathogenesis, however, the causes and mechanisms of the progressive fibrotic cascade are still poorly understood. As epithelial-mesenchymal interactions are essential for normal wound healing, through human 2D and 3D in vitro studies, we tested the hypothesis that IPF fibroblasts (IPFFs) dysregulate alveolar epithelial homeostasis. Conditioned media from IPFFs exaggerated the wound-healing response of primary human Type II alveolar epithelial cells (AECs). Furthermore, AECs co-cultured with IPFFs exhibited irregular epithelialization compared with those co-cultured with control fibroblasts (NHLFs) or AECs alone, suggesting that epithelial homeostasis is dysregulated in IPF as a consequence of the abnormal secretory phenotype of IPFFs. Secretome analysis of IPFF conditioned media and functional studies identified the matricellular protein, SPARC, as a key mediator in the epithelial-mesenchymal paracrine signaling, with increased secretion of SPARC by IPFFs promoting persistent activation of alveolar epithelium via an integrin/focal adhesion/cellular-junction axis resulting in disruption of epithelial barrier integrity and increased macromolecular permeability. These findings suggest that in IPF fibroblast paracrine signaling promotes persistent alveolar epithelial activation, so preventing normal epithelial repair responses and restoration of tissue homeostasis. Furthermore, they identify SPARC-mediated paracrine signaling as a potential therapeutic target to promote the restoration of lung epithelial homoestasis in IPF patients.

PMID:33563935 | DOI:10.1038/s41420-020-0289-9

Chest. 2021 Feb;159(2):475-476. doi: 10.1016/j.chest.2020.09.239.

NO ABSTRACT

PMID:33563432 | DOI:10.1016/j.chest.2020.09.239

Curr Mol Pharmacol. 2021 Feb 4. doi: 10.2174/1874467214666210204212533. Online ahead of print.

ABSTRACT

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a serious disease with high mortality rate. Activation of transforming growth factor (TGF)-β1 production and signalling is considered the corner stone in the epithelial-mesenchymal transition (EMT) process. EMT plays a central role in development of fibrosis in many organs including the lungs. Activated platelets are an important source of TGF-β1 and play a pivotal role in EMT and fibrosis process. The antiplatelet, ticagrelor was previously found to inhibit the EMT in different types of cancer cells, but its ability to serve as an anti-pulmonary fibrosis (PF) agent was not previously investigated.

OBJECTIVE: In this study, we aim to investigate the potential ability of ticagrelor to ameliorate bleomycin-induced fibrosis in rats.

METHODS: PF was induced in rats by intratracheal BLM at a dose of 3 mg/kg. The effect of daily daily 20 mg/kg oral ticagrelor on different histological and biochemical parameters of fibrosis was investigated.

RESULTS: Our results revealed that ticagrelor can alleviate lung fibrosis. We found that ticagrelor inhibited TGF-β1 production and suppressed Smad3 activation and signaling pathway with subsequent inhibition of Slug and Snail. In addition, ticagrelor antagonized PI3K/AKT/mTOR pathway signaling. Moreover, ticagrelor inhibited the EMT that revealed by its ability to up-regulate the epithelial markers as E-cadherin (E-cad) and to decrease the expression of the mesenchymal markers as vimentin (VIM) and alpha-smooth muscle actin (α-SMA).

CONCLUSION: Our results suggest that the P2Y12 inhibitor, ticagrelor may have a therapeutic potential in reducing the progression of PF.

PMID:33563204 | DOI:10.2174/1874467214666210204212533

Aging Cell. 2021 Feb 8:e13314. doi: 10.1111/acel.13314. Online ahead of print.

ABSTRACT

Age-related diseases such as cancer, cardiovascular disease, kidney failure, and osteoarthritis have universal features: Their incidence rises exponentially with age with a slope of 6-8% per year and decreases at very old ages. There is no conceptual model which explains these features in so many diverse diseases in terms of a single shared biological factor. Here, we develop such a model, and test it using a nationwide medical record dataset on the incidence of nearly 1000 diseases over 50 million life-years, which we provide as a resource. The model explains incidence using the accumulation of senescent cells, damaged cells that cause inflammation and reduce regeneration, whose level rise stochastically with age. The exponential rise and late drop in incidence are captured by two parameters for each disease: the susceptible fraction of the population and the threshold concentration of senescent cells that causes disease onset. We propose a physiological mechanism for the threshold concentration for several disease classes, including an etiology for diseases of unknown origin such as idiopathic pulmonary fibrosis and osteoarthritis. The model can be used to design optimal treatments that remove senescent cells, suggeting that treatment starting at old age can sharply reduce the incidence of all age-related diseases, and thus increase the healthspan.

PMID:33559235 | DOI:10.1111/acel.13314

Respir Res. 2021 Feb 8;22(1):49. doi: 10.1186/s12931-021-01640-z.

ABSTRACT

BACKGROUND: Mitochondrial dysfunction has emerged as an important player in the pathogenesis of idiopathic pulmonary fibrosis (IPF), a common cause of idiopathic interstitial lung disease in adults. Hermansky-Pudlak syndrome (HPS) is a rare autosomal recessive disorder that causes a similar type of pulmonary fibrosis in younger adults, although the role of mitochondrial dysfunction in this condition is not understood.

METHODS: We performed a detailed characterization of mitochondrial structure and function in lung tissues and alveolar epithelial cells deficient in the adaptor protein complex 3 beta 1 (Ap3b1) subunit, the gene responsible for causing subtype 2 of HPS (HPS-2).

RESULTS: We observed widespread changes in mitochondrial homeostasis in HPS-2 cells, including the acquisition of abnormally shaped mitochondria, with reduced number of cristae, and markedly reduced activity of the electron transport chain and the tricarboxylic acid cycle. We also found that mitochondrial redox imbalance and activity of the mitochondrial unfolded protein response were dysregulated in HPS-2 cells and this associated with various other changes that appeared to be compensatory to mitochondrial dysfunction. This included an increase in glycolytic activity, an upregulation in the expression of mitochondrial biogenesis factors and enhanced activation of the energy-conserving enzyme AMP-activated protein kinase.

CONCLUSION: In summary, our findings indicate that mitochondrial function is dramatically altered in HPS-2 lung tissues, suggesting dysfunction of this organelle might be a driver of HPS lung disease.

PMID:33557836 | PMC:PMC7871590 | DOI:10.1186/s12931-021-01640-z

Curr Opin Pharmacol. 2021 Feb 5;57:71-80. doi: 10.1016/j.coph.2020.12.007. Online ahead of print.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is a progressive, irreversible fibrotic chronic lung disease affecting predominantly older adults, with a history of smoking. The current model of disease natural course is that recurrent injury of the alveolar epithelium in the context of advanced aging/cellular senescence is followed by defective re-epithelialization and scar tissue formation. Currently, two drugs, nintedanib and pirfenidone, that modify disease progression have been approved worldwide for the treatment of IPF. However, despite treatment, patients with IPF are not cured, and eventually, disease advances in most treated patients. Enhancing biogenomic and metabolic research output, its translation into clinical precision and optimal service delivery through patient-centeredness are key elements to support effective IPF care. In this review, we summarize therapeutic options currently investigated for IPF based on the major pathogenetic pathways and molecular targets that drive pulmonary fibrosis.

PMID:33556824 | DOI:10.1016/j.coph.2020.12.007

Respir Investig. 2021 Feb 4:S2212-5345(21)00005-8. doi: 10.1016/j.resinv.2020.12.008. Online ahead of print.

ABSTRACT

BACKGROUND: The clinical course of idiopathic pulmonary fibrosis (IPF) is characterized by a progressive decline in lung function; however, predicting changes in lung function is difficult. We sought to determine whether the prior 6-month trend in forced vital capacity (FVC) could predict mortality and the subsequent 6-month trend in FVC.

METHODS: We retrospectively analyzed consecutive patients with newly diagnosed IPF who underwent serial pulmonary function tests. The immediate two years after the initial evaluation were divided into four terms of six months each and stratified on the basis of presence or absence of a ≥10% relative decline in FVC at six months (declined and stable groups, respectively).

RESULTS: We included 107 patients with %predicted FVC of 80.8% and %predicted diffusing capacity of the lung for carbon monoxide of 58.9%. In multivariate analysis, a decline in %predicted FVC in the initial six months was found to be an independent prognostic factor (hazard ratio 4.45, 95% confidence interval 2.62-7.56, p < 0.01). Among the 46 terms in which the FVC declined during the initial 1.5-year study period, a decline in FVC was exhibited in 23 (50.0%) of the subsequent terms. Among 231 terms in which FVC remained stable, a decline was observed in 32 (13.9%) of the subsequent terms (relative risk 3.61, p < 0.01). The frequency of FVC decline in each term was 16-27%. FVC was stable or declined in all four terms in 50.5% and 15.9% of cases, respectively.

CONCLUSIONS: Six-month decline in FVC predicts subsequent FVC change and mortality in IPF patients in the era of antifibrotic agents.

PMID:33551330 | DOI:10.1016/j.resinv.2020.12.008

Respir Investig. 2021 Feb 3:S2212-5345(21)00003-4. doi: 10.1016/j.resinv.2020.12.006. Online ahead of print.

ABSTRACT

BACKGROUND: Patients with idiopathic pulmonary fibrosis (IPF) are at risk of acute exacerbations (AEs) that manifest as respiratory distress. However, the clinical course after AEs of IPF (AE-IPFs) has not been well described. Therefore, we aimed to elucidate the clinical course and prognosis in survivors of AE-IPFs.

METHODS: Consecutive patients with IPF who presented to our institution with their first AE-IPFs between January 2008 and December 2019 were included in this study. Data were retrospectively collected, and the clinical course, survival, and cause of death were further analyzed.

RESULTS: Ninety-seven patients were included in this retrospective study. Among them, 67 (69.1%) were discharged alive, with a median survival time after discharge of 1081 days. AE recurrence and pneumonia were the most common causes of death, each accounting for 22.2% of cases among survivors of AE-IPFs. AEs were the most frequent during the first 3 years after discharge, whereas pneumonia was more common thereafter.

CONCLUSIONS: Survivors of AE-IPFs have a relatively favorable long-term prognosis. Among the survivors of first AE-IPFs, AE recurrence and pneumonia were the most common causes of death after discharge. Therefore, preventing AE recurrence and lung infections is crucial for prolonging survival in survivors of AE-IPFs.

PMID:33549542 | DOI:10.1016/j.resinv.2020.12.006

Respir Res. 2021 Feb 6;22(1):44. doi: 10.1186/s12931-021-01632-z.

ABSTRACT

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is the most common interstitial lung diseases with a poor prognosis. Long non-coding RNAs (lncRNAs) have been reported to be involved in IPF in several studies. However, the role of lncRNA SNHG16 in IPF is largely unknown.

METHODS: Firstly, experimental pulmonary fibrosis model was established by using bleomycin (BML). Histology and Western blotting assays were used to determine the different stages of fibrosis and expression of several fibrosis biomarkers. The expression of SNHG16 was detected by quantitative real-time polymerase chain reaction (qRT-PCR). EdU staining and wound-healing assay were utilized to analyze proliferation and migration of lung fibroblast cells. Molecular mechanism of SNHG16 was explored by bioinformatics, dual-luciferase reporter assay, RNA immunoprecipitation assay (RIP), and qRT-PCR.

RESULTS: The expression of SNHG16 was significantly up-regulated in bleomycin-(BLM) induced lung fibrosis and transforming growth factor-β (TGF-β)-induced fibroblast. Knockdown of SNHG16 could attenuate fibrogenesis. Mechanistically, SNHG16 was able to bind and regulate the expression of miR-455-3p. Moreover, SNHG16 also regulated the expression of Notch2 by targeting miR-455-3p. Finally, SNHG16 could promote fibrogenesis by regulating the expression of Notch2.

CONCLUSION: Taken together, our study demonstrated that SNHG16 promoted pulmonary fibrosis by targeting miR-455-3p to regulate the Notch2 pathway. These findings might provide a novel insight into pathologic process of lung fibrosis and may provide prevention strategies in the future.

PMID:33549106 | PMC:PMC7866661 | DOI:10.1186/s12931-021-01632-z

Am J Ind Med. 2021 Feb 5. doi: 10.1002/ajim.23231. Online ahead of print.

ABSTRACT

BACKGROUND: Cigarette smoking and occupational exposures each have been reported to increase the risk of idiopathic pulmonary fibrosis (IPF), a disease previously considered of unknown origin. We investigated the risk of IPF mortality associated with combined smoking and occupational exposures.

METHODS: A registry study of Swedish construction workers (N = 389,132), linked baseline smoking and occupational data with registry data on cause of death and hospital care diagnoses. Occupation was classified by the likelihood of exposure to vapors, gases, dusts, or fumes using a job-exposure matrix. Those likely exposed to asbestos or silica were excluded from the analysis. Age-adjusted relative risks [RRs] were calculated using Poisson regression. Follow-up observation began at age 40 and ended at age 89.

RESULTS: Heavy smokers at baseline who were exposed to inorganic dusts during their working life had an increased risk of IPF mortality (RR 1.70; 95% confidence interval [CI] 1.11-2.60), while there was no statistically increased risk in the other exposure groups. There were dose-response relationships between smoking at baseline and IPF mortality among both unexposed and dust exposed workers, with similar risk for dust exposed and unexposed, except among baseline heavy smokers, where workers exposed to inorganic dust manifested the highest risk (RR 4.22; 95% CI 2.69-6.60). Excluding workers with chronic obstructive pulmonary disease or emphysema did not affect the results substantively.

CONCLUSION: A clear dose-response relationship was seen between smoking at baseline and IPF, supporting a causal relationship. Occupational exposure to inorganic dusts, excluding silica and asbestos, was associated with increased risk of IPF in baseline heavy current smokers.

PMID:33547652 | DOI:10.1002/ajim.23231

Med Phys. 2021 Feb 5. doi: 10.1002/mp.14754. Online ahead of print.

ABSTRACT

PURPOSE: Domain knowledge (DK) acquired from prior studies is important for medical diagnosis. This paper leverages the population-level DK using an optimality design criterion to train a deep learning model in an end-to-end manner. In this study, the problem of interest is at the patient-level to diagnose a subject with idiopathic pulmonary fibrosis (IPF) among subjects with interstitial lung disease (ILD) using a computed tomography (CT). IPF diagnosis is a complicated process with multidisciplinary discussion with experts and is subject to inter-observer variability, even for experienced radiologists. To this end, we propose a new statistical method to construct a time/memory-efficient IPF diagnosis model using axial chest CT and DK, along with an optimality design criterion via a DK-enhanced loss function of deep learning.

METHODS: Four state-of-the-art two-dimensional convolutional neural network (2D-CNN) architectures (MobileNet, VGG16, ResNet-50, and DenseNet-121) and one baseline 2D-CNN are implemented to automatically diagnose IPF among ILD patients. Axial lung CT images are retrospectively acquired from 389 IPF patients and 700 non-IPF ILD patients in five multi-center clinical trials. To enrich the sample size and boost model performance, we sample 20 three-slice samples (triplets) from each CT scan, where these three slices are randomly selected from the top, middle, and bottom of both lungs respectively. Model performance is evaluated using a five-fold cross-validation, where each fold was stratified using a fixed proportion of IPF versus non-IPF.

RESULTS: Using DK-enhanced loss function increases the model performance of the baseline CNN model from 0.77 to 0.89 in terms of study-wise accuracy. Four other well-developed models reach satisfactory model performance with an overall accuracy greater than 0.95 but the benefits brought on by the DK-enhanced loss function is not noticeable.

CONCLUSIONS: We believe this is the first attempt that (1) uses population-level DK with an optimal design criterion to train deep learning-based diagnostic models in an end-to-end manner and (2) focuses on patient-level IPF diagnosis. Further evaluation of using population-level DK on prospective studies is warranted and is underway.

PMID:33547645 | DOI:10.1002/mp.14754

Respir Res. 2021 Feb 5;22(1):40. doi: 10.1186/s12931-021-01634-x.

ABSTRACT

BACKGROUND: Observational data under real-life conditions in idiopathic pulmonary fibrosis (IPF) is scarce. We explored anti-fibrotic treatment, disease severity and phenotypes in patients with IPF from the Swedish IPF Registry (SIPFR).

METHODS: Patients enrolled between September 2014 and April 2020 and followed ≥ 6 months were investigated. Demographics, comorbidities, lung function, composite variables, six-minute walking test (6MWT), quality of life, and anti-fibrotic therapy were evaluated. Agreements between classification of mild physiological impairment (defined as gender-age-physiology (GAP) stage 1) with physiological and composite measures of severity was assessed using kappa values and their impact on mortality with hazard ratios. The factor analysis and the two-step cluster analysis were used to identify phenotypes. Univariate and multivariable survival analyses were performed between variables or groups.

RESULTS: Among 662 patients with baseline data (median age 72.7 years, 74.0% males), 480 had a follow up ≥ 6 months with a 5 year survival rate of 48%. Lung function, 6MWT, age, and BMI were predictors of survival. Patients who received anti-fibrotic treatment ≥ 6 months had better survival compared to untreated patients [p = 0.007, HR (95% CI): 1.797 (1.173-2.753)] after adjustment of age, gender, BMI, smoking status, forced vital capacity (FVC) and diffusion capacity of carbon monoxide (DLCO). Patients with mild physiological impairment (GAP stage 1, composite physiological index (CPI) ≤ 45, DLCO ≥ 55%, FVC ≥ 75%, and total lung capacity (TLC) ≥ 65%, respectively) had better survival, after adjustment for age, gender, BMI and smoking status and treatment. Patients in cluster 1 had the worst survival and consisted mainly of male patients with moderate-severe disease and an increased prevalence of heart diseases at baseline; Cluster 2 was characterized by mild disease with more than 50% females and few comorbidities, and had the best survival; Cluster 3 were younger, with moderate-severe disease and had few comorbidities.

CONCLUSION: Disease severity, phenotypes, and anti-fibrotic treatment are closely associated with the outcome in IPF, with treated patients surviving longer. Phenotypes may contribute to predicting outcomes of patients with IPF and suggest the patients' need for special management, whereas single or composite variables have some limitations as disease predictors.

PMID:33546682 | PMC:PMC7866760 | DOI:10.1186/s12931-021-01634-x