Deep Learning Classification of Usual Interstitial Pneumonia Predicts Outcomes.

Rationale: Computed tomography (CT) enables noninvasive diagnosis of usual interstitial pneumonia (UIP), but enhanced image analyses are needed to overcome the limitations of visual assessment. Objectives: Apply multiple instance learning (MIL) to develop an explainable deep learning algorithm for prediction of UIP from CT and validate its performance in independent cohorts. Methods: We trained an MIL algorithm using a pooled dataset (n = 2,143) and tested it in three independent populations: data from a prior publication (n = 127), a single-institution clinical cohort (n = 239), and a national registry of patients with pulmonary fibrosis (n = 979). We tested UIP classification performance using receiver operating characteristic analysis, with histologic UIP as ground truth. Cox proportional hazards and linear mixed-effects models were used to examine associations between MIL predictions and survival or longitudinal FVC. Measurements and Main Results: In two cohorts with biopsy data, MIL improved accuracy for histologic UIP (area under the curve, 0.77 [n = 127] and 0.79 [n = 239]) compared with visual assessment (area under the curve, 0.65 and 0.71). In cohorts with survival data, MIL-UIP classifications were significant for mortality (n = 239, mortality to April 2021: unadjusted hazard ratio, 3.1; 95% confidence interval [CI], 1.96-4.91; P < 0.001; and n = 979, mortality to July 2022: unadjusted hazard ratio, 3.64; 95% CI, 2.66-4.97; P < 0.001). Individuals classified as UIP positive by the algorithm had a significantly greater annual decline in FVC than those classified as UIP negative (-88 ml/yr vs. -45 ml/yr; n = 979; P < 0.01), adjusting for extent of lung fibrosis. Conclusions: Computerized assessment using MIL identifies clinically significant features of UIP on CT. Such a method could improve confidence in radiologic assessment of patients with interstitial lung disease, potentially enabling earlier and more precise diagnosis.

Utility of a Molecular Classifier as a Complement to High-Resolution Computed Tomography to Identify Usual Interstitial Pneumonia.

Rationale: Usual interstitial pneumonia (UIP) is the defining morphology of idiopathic pulmonary fibrosis (IPF). Guidelines for IPF diagnosis conditionally recommend surgical lung biopsy for histopathology diagnosis of UIP when radiology and clinical context are not definitive. A "molecular diagnosis of UIP" in transbronchial lung biopsy, the Envisia Genomic Classifier, accurately predicted histopathologic UIP.Objectives: We evaluated the combined accuracy of the Envisia Genomic Classifier and local radiology in the detection of UIP pattern.Methods: Ninety-six patients who had diagnostic lung pathology as well as a transbronchial lung biopsy for molecular testing with Envisia Genomic Classifier were included in this analysis. The classifier results were scored against reference pathology. UIP identified on high-resolution computed tomography (HRCT) as documented by features in local radiologists' reports was compared with histopathology.Measurements and Main Results: In 96 patients, the Envisia Classifier achieved a specificity of 92.1% (confidence interval [CI],78.6-98.3%) and a sensitivity of 60.3% (CI, 46.6-73.0%) for histology-proven UIP pattern. Local radiologists identified UIP in 18 of 53 patients with UIP histopathology, with a sensitivity of 34.0% (CI, 21.5-48.3%) and a specificity of 96.9% (CI, 83.8-100%). In conjunction with HRCT patterns of UIP, the Envisia Classifier results identified 24 additional patients with UIP (sensitivity 79.2%; specificity 90.6%).Conclusions: In 96 patients with suspected interstitial lung disease, the Envisia Genomic Classifier identified UIP regardless of HRCT pattern. These results suggest that recognition of a UIP pattern by the Envisia Genomic Classifier combined with HRCT and clinical factors in a multidisciplinary discussion may assist clinicians in making an interstitial lung disease (especially IPF) diagnosis without the need for a surgical lung biopsy.

Molecular Profiling of Vascular Remodeling in Chronic Pulmonary Disease.

Pulmonary hypertension and pulmonary vascular remodeling (PVR) are common in many lung diseases leading to right ventricular dysfunction and death. Differences in PVR result in significant prognostic divergences in both the pulmonary arterial and venous compartments, as in pulmonary arterial hypertension (PAH) and pulmonary veno-occlusive disease (PVOD), respectively. Our goal was to identify compartment-specific molecular hallmarks of PVR, considering the risk of life-threatening pulmonary edema in PVOD, if treated by conventional pulmonary hypertension therapy. Formalin-fixed and paraffin-embedded tissues from fresh explanted human lungs of patients with PVOD (n = 19), PAH (n = 20), idiopathic pulmonary fibrosis (n = 13), and chronic obstructive pulmonary disease (n = 15), were analyzed for inflammation and kinome-related gene regulation. The generated neuronal network differentiated PVOD from PAH samples with a sensitivity of 100% and a specificity of 92% in a randomly chosen validation set, a level far superior to established diagnostic algorithms. Further, various alterations were identified regarding the gene expression of explanted lungs with PVR, compared with controls. Specifically, the dysregulation of microtubule-associated serine/threonine kinase 2 and protein-o-mannose kinase SGK196 in all disease groups suggests a key role in pulmonary vasculopathy for the first time. Our findings promise to help develop novel target-specific interventions and innovative approaches to facilitate clinical diagnostics in an elusive group of diseases.

Comparison of disease progression subgroups in idiopathic pulmonary fibrosis.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive interstitial pneumonia with an unpredictable course. The aims of this study were to retrospectively re-evaluate a cohort of patients with IPF according to the 2011 international IPF guidelines and 1) to characterize the subgroups of patients when classified according to their observed survival times and 2) to evaluate whether Composite Physiologic Index (CPI), Gender-Age-Physiology (GAP) Index or clinical variables could predict mortality. METHODS: Retrospective data was collected and patients were classified into subgroups according to their observed lifespans. Differences in clinical variables, CPI and GAP stages as well as in comorbidities were investigated between the subgroups. Predictors of mortality were identified by COX proportional hazard analyses. RESULTS: A total of 132 patients were included in this study. The disease course was rapid (≤ 2 years) in 30.0%, moderate (2-5 years) in 28.0% and slow (≥ 5 years) in 29.0% of the patients. Pulmonary function tests (PFT) and CPI at baseline differentiated significantly between the rapid disease course group and those patients with longer survival times. However, the predictive accuracy of the investigated clinical variables was mainly less than 0.80. The proportions of patients with comorbidities did not differ between the subgroups, but more patients with a rapid disease course were diagnosed with heart failure after the diagnosis of IPF. Most patients with a rapid disease course were categorized in GAP stages I and II, but all patients in GAP stage III had a rapid disease course. The best predictive multivariable model included age, gender and CPI. GAP staging had slightly better accuracy (0.67) than CPI (0.64) in predicting 2-year mortality. CONCLUSIONS: Although the patients with a rapid disease course could be differentiated at baseline in terms of PFT and CPI, the predictive accuracy of any single clinical variable as well as CPI and GAP remained low. GAP staging was unable to identify the majority of patients with a rapid disease progression. It is challenging to predict disease progression and mortality in IPF even with risk prediction models.

Acute exacerbations of idiopathic pulmonary fibrosis: Does clinical stratification or steroid treatment matter?

Acute exacerbation (AE) of idiopathic pulmonary fibrosis (IPF) is defined as a sudden acceleration of the disease with the appearance of pulmonary infiltrates superimposed on the characteristic pattern of IPF that leads to a significant decline in lung function. It has high in-hospital mortality rates, despite medical treatment with systematic steroids. We sought to investigate whether there were in-hospital mortality differences according to clinical stratification (AE, suspected AE, or AE of known cause) and/or treatment with systemic steroids. We reviewed the clinical characteristics and outcomes of patients with IPF admitted to our hospital during the years 2003-2014 due to a worsening of their clinical status. We identified 50 IPF patients, 9 with AE (18%), 12 with suspected exacerbation (24%), and 29 with AE of known cause (58%), mostly respiratory infections. In-hospital mortality was similar in the three groups (33% vs. 17% vs. 34%, respectively). Likewise, we did not find differences between them with respect to the use of systemic steroids (length of treatment duration or total dose). Nevertheless, there was an independent association between in-hospital mortality and high average daily steroid dose. We did not observe significant differences in prognosis or use of systemic steroids according to current diagnostic stratification groups in patients hospitalized because of an exacerbation of IPF.

What's in a name? That which we call IPF, by any other name would act the same.

Idiopathic pulmonary fibrosis (IPF) remains a truly idiopathic fibrotic disease, with a modest genetic predilection and candidate triggers but no overall explanation for the development of disease in non-familial cases. Agreement on terminology has contributed to major clinical and translational advances since the millennium. It is likely that the entity currently captured by the term "IPF" will be radically reclassified over the next decade, either through "splitting" (into IPF subgroups responding selectively to individual disease-modifying agents) or through "lumping" of IPF with other forms of progressive fibrotic lung disease (with shared pathogenetic mechanisms and IPF-like disease behaviour). In this perspective, we summarise the clinical and pathogenetic justification for a focus on "the progressive fibrotic phenotype" in future clinical and translational research. By this means, we can hope to address the needs of non-IPF patients with inexorably progressive fibrotic disease, currently disenfranchised by lack of access to agents that are efficacious in IPF. In this regard, ongoing trials of anti-fibrotic therapies in non-IPF patients with progressive fibrosis may be highly influential. Future revision of IPF nomenclature may be warranted if there are major conceptual changes but without compelling justification, the benefits of renaming IPF are likely to be outweighed by the resulting confusion.

Overlap of interstitial pneumonia with autoimmune features with undifferentiated connective tissue disease and contribution of UIP to mortality.

BACKGROUND AND OBJECTIVE: Criteria for interstitial pneumonia with autoimmune features (IPAF) were recently established for research purposes in a joint statement from the European Respiratory Society (ERS) and American Thoracic Society (ATS). We reviewed the utility of these criteria in patients previously diagnosed as broadly defined undifferentiated connective tissue disease (UCTD) and noted overlapping IPAF findings. Additional review was given to IPAF patients with usual interstitial pneumonia (UIP) on histopathology or radiology in terms of survival and outcome. METHODS: Patients with prior UCTD-interstitial lung disease (ILD) were screened by ERS/ATS criteria for IPAF. Clinical data along with all-cause mortality were collated and compared with selected idiopathic pulmonary fibrosis (IPF) patients from the same study period. Survival was compared between IPAF subgroups with and without UIP features. RESULTS: One hundred and one UCTD-ILD subjects (91%) evaluated from 2005 to 2012 also met strict criteria for IPAF. Frequent clinical findings included Raynaud's phenomenon, positive anti-nuclear antibody (ANA) and non-specific interstitial pneumonia (NSIP) pattern on chest computed tomography (CT). Nineteen had features of UIP either on histopathology or CT imaging. As compared with IPF, IPAF patients had overall better survival except in those with UIP features. CONCLUSION: Current IPAF criteria encompassed the majority of broadly defined UCTD-ILD and included those with UIP findings. Survival compared with IPF in those with UIP was similar. Further studies are necessary to refine IPAF definitions for clinical use and guide directed management strategies.

Disease progression in idiopathic pulmonary fibrosis with mild physiological impairment: analysis from the Australian IPF registry.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive and fatal fibrosing lung disease of unknown cause. The advent of anti-fibrotic medications known to slow disease progression has revolutionised IPF management in recent years. However, little is known about the natural history of IPF patients with mild physiological impairment. We aimed to assess the natural history of these patients using data from the Australian IPF Registry (AIPFR). METHODS: Using our cohort of real-world IPF patients, we compared FVC criteria for mild physiological impairment (FVC ≥ 80%) against other proposed criteria: DLco ≥ 55%; CPI ≤40 and GAP stage 1 with regards agreement in classification and relationship with disease outcomes. Within the mild cohort (FVC ≥ 80%), we also explored markers associated with poorer prognosis at 12 months. RESULTS: Of the 416 AIPFR patients (mean age 70.4 years, 70% male), 216 (52%) were classified as 'mild' using FVC ≥ 80%. There was only modest agreement between FVC and DLco (k = 0.30), with better agreement with GAP (k = 0.50) and CPI (k = 0.48). Patients who were mild had longer survival, regardless of how mild physiologic impairment was defined. There was, however, no difference in the annual decline in FVC% predicted between mild and moderate-severe groups (for all proposed criteria). For patients with mild impairment (n = 216, FVC ≥ 80%), the strongest predictor of outcomes at 12 months was oxygen desaturation on a 6 min walk test. CONCLUSION: IPF patients with mild physiological impairment have better survival than patients with moderate-severe disease. Their overall rate of disease progression however, is comparable, suggesting that they are simply at different points in the natural history of IPF disease.

Unmet needs in the treatment of idiopathic pulmonary fibrosis-insights from patient chart review in five European countries.

BACKGROUND: Two antifibrotic drugs, pirfenidone and nintedanib, are approved by the European Medicines Agency and the US Food and Drug Administration for the treatment of idiopathic pulmonary fibrosis (IPF). In this analysis, treatment patterns of European patients with IPF were investigated to understand antifibrotic prescribing and identify unmet needs in IPF treatment practice. METHODS: Between February and March 2016, respiratory physicians from France, Germany, Italy, Spain, and the UK participated in an online questionnaire designed to collect information on IPF treatment patterns in patients under their care. Patients were categorized as treated (received approved antifibrotics) or untreated (did not receive approved antifibrotics, but may have received other unapproved therapies). Classification of IPF diagnosis (confirmed/suspected) and severity ('mild'/'moderate'/'severe') for each patient was based on the individual physician's report. Patients' perspectives were not recorded in this study. RESULTS: In total, 290 physicians responded to the questionnaire. Overall, 54% of patients with IPF did not receive treatment with an approved antifibrotic. More patients had a confirmed IPF diagnosis in the treated (84%) versus the untreated (51%) population. Of patients with a confirmed diagnosis, 40% did not receive treatment. The treated population was younger than the untreated population (67 vs 70 years, respectively; p ≤ 0.01), with more frequent multidisciplinary team evaluation (83% vs 57%, respectively; p ≤ 0.01). A higher proportion of untreated patients had forced vital capacity > 80% at diagnosis versus treated patients. Of patients with 'mild' IPF, 71% did not receive an approved antifibrotic versus 41% and 60% of patients with 'moderate' and 'severe' IPF, respectively. CONCLUSIONS: Despite the availability of antifibrotic therapies, many European patients with confirmed IPF do not receive approved antifibrotic treatment. Importantly, there appears to be a reluctance to treat patients with 'mild' or 'stable' disease, and instead adopt a 'watch and wait' approach. More education is required to address diagnostic uncertainty, poor understanding of IPF and its treatments, and issues of treatment access. There is a need to increase physician awareness of the benefits associated with antifibrotic treatment across the spectrum of IPF severity.

Self-Report Daily Life Activity as a Prognostic Marker of Idiopathic Pulmonary Fibrosis.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive disease, leading to substantial physical impairment. The distance walked in 6 min (6MWD) is a measure of exercise tolerance and is of prognostic relevance in IPF. While 6MWD is a punctual measurement which may not be representative, self-reported daily life activity may represent the patients' functional capacity more globally even in less severe affected patients. OBJECTIVES: We evaluated and characterized a simple classification system based on the patients' self-reported daily activity and analyzed if this would add significantly to the prognostic information of the 6MWD alone in IPF patients. METHODS: Daily life activity was assessed in IPF (n = 156) patients with standardized questions and categorized in activity classes (AC I-IV), comprising the less severe impaired in AC I and II. The 6MWD was also assessed. RESULTS: ACs were related to the lung functional impairment and inversely correlated to the 6MWD. Thirty-two patients were in AC I/II, 98 in AC III and 26 patients in AC IV. Thirty-seven (23.7%) patients died during a median follow-up of 14.9 months, comprising 1 patient in AC I/II. In addition, a 6MWD <470 m predicted mortality. Combining AC I/II and a 6MWD >470 m identified a subgroup of patients with favorable outcome. CONCLUSIONS: AC is a novel scoring system which can easily be obtained and correlates with lung functional and physical impairments as well as mortality. Moreover, AC adds prognostic information to the 6MWD.

[Idiopathic pulmonary fibrosis: recent diagnostic and therapeutic advances]. / Fibrose pulmonaire idiopathique: nouveautés diagnostiques et thérapeutiques.

Idiopathic pulmonary fibrosis (IPF) is the most frequent of the idiopathic interstitial pneumonias. It is a progressive disorderwith a poor prognosis. Its diagnosis requires the careful exclusion of potential causes, and a pattern of usual interstitial pneumonia at high-resolution computed tomography or video-assisted surgical lung biopsy. Several recent randomized trials have profoundly modified the therapeutic management of IPF. The combination of prednisone and azathioprine, often prescribed until recently, has been shown to be harmful and is no longer indicated. N-acetylcystein, also used in the past decade, failed to show an efficacy. However, two new antifibrotic drugs, pirfenidone and nintedanib, have for the first time proven effective in slowing disease progression.

A multidimensional classifier to support lung transplant referral in patients with pulmonary fibrosis.

BACKGROUND: Lung transplantation remains the sole curative option for patients with idiopathic pulmonary fibrosis (IPF), but donor organs remain scarce, and many eligible patients die before transplant. Tools to optimize the timing of transplant referrals are urgently needed. METHODS: Least absolute shrinkage and selection operator was applied to clinical and proteomic data generated as part of a prospective cohort study of interstitial lung disease (ILD) to derive clinical, proteomic, and multidimensional logit models of near-term death or lung transplant within 18 months of blood draw. Model-fitted values were dichotomized at the point of maximal sensitivity and specificity, and decision curve analysis was used to select the best-performing classifier. We then applied this classifier to independent IPF and non-IPF ILD cohorts to determine test performance characteristics. Cohorts were restricted to patients aged ≤72 years with body mass index 18 to 32 to increase the likelihood of transplant eligibility. RESULTS: IPF derivation, IPF validation, and non-IPF ILD validation cohorts consisted of 314, 105, and 295 patients, respectively. A multidimensional model comprising 2 clinical variables and 20 proteins outperformed stand-alone clinical and proteomic models. Following dichotomization, the multidimensional classifier predicted near-term outcome with 70% sensitivity and 92% specificity in the IPF validation cohort and 70% sensitivity and 80% specificity in the non-IPF ILD validation cohort. CONCLUSIONS: A multidimensional classifier of near-term outcomes accurately discriminated this end-point with good test performance across independent IPF and non-IPF ILD cohorts. These findings support refinement and prospective validation of this classifier in transplant-eligible individuals.

Idiopathic pulmonary fibrosis: diagnosis and prognostic evaluation.

Idiopathic pulmonary fibrosis (IPF) is the most common type of idiopathic interstitial pneumonia and has a dismal prognosis. Median age at IPF onset is 60-70 years and it is mainly related to cigarette smoke exposure. Its clinical profile is heterogeneous and different clinical phenotypes are now better defined: familial IPF, slow and rapid progressors, combined pulmonary fibrosis and emphysema, anti-neutrophil cytoplasmic antibodies/microscopic polyangiitis and IPF, and IPF associated with lung cancer. Acute exacerbation associated with rapid functional decline is an event that does not happen infrequently and affects survival. Diagnosis requires a typical usual interstitial pneumonia (UIP) pattern on computed tomography in the appropriate clinical setting or morphological confirmation of the UIP pattern when imaging findings are not characteristic enough. Surgical lung biopsy is the gold standard to obtain valuable information for histological analysis. However, less invasive procedures (transbronchial lung biopsy or even improved transbronchial lung biopsy by cryoprobes) are now under consideration. Prognostic indicators are mainly derived by pulmonary function tests. Recently, staging systems have been proposed.

Pulmonary dendritic cell accumulation in usual interstitial pneumonia and nonspecific interstitial pneumonia.

BACKGROUND: Pulmonary dendritic cells (DCs) are key regulators of immune responses. An increased accumulation of DCs was reported in the lungs of patients with idiopathic interstitial pneumonia (IIP). OBJECTIVE: This study aimed to investigate the number of pulmonary DCs in patients with collagen vascular disease associated interstitial lung diseases (CVD-ILDs). DESIGN: Lung tissue samples obtained from 27 patients with IIP and 39 patients with CVD-ILD were detected using monoclonal antibodies against CD1a, CD1c, CD83, Langerin and DC-specific intercellular adhesion molecule-3-grabbing nonintegrin (DC-SIGN). RESULTS: No significant differences in the number or distribution of DCs were observed between patients with IIP and CVD-ILDs. When DC marker expression was analyzed according to pathological subgroup, patients with idiopathic usual interstitial pneumonia (UIP) showed increased DC-SIGN staining when compared with CVD-UIP (p < 0.05). CONCLUSION: Both mature and immature DCs accumulate in CVD-ILDs. The number of DCs expressing DC-SIGN in CVD-UIP was decreased compared with that in idiopathic UIP. The variation in accumulated DC-SIGN-positive cells might help to explain the differences in the development and maintenance of lung inflammation between idiopathic UIP and CVD-UIP.

Identification of the Molecular Subgroups in Idiopathic Pulmonary Fibrosis by Gene Expression Profiles.

BACKGROUND: Idiopathic Pulmonary Fibrosis (IPF) is one of the most common idiopathic interstitial pneumonia, which can occur all over the world. The median survival time of patients is about 3-5 years, and the mortality is relatively high. OBJECTIVE: To reveal the potential molecular characteristics of IPF and deepen the understanding of the molecular mechanism of IPF. In order to provide some guidance for the clinical treatment, new drug development, and prognosis judgment of IPF. Although the preliminary conclusion of this study has certain guiding significance for the treatment of IPF and so on, it needs more accurate analytical approaches and large sample clinical trials to verify. METHODS: 220 patients with IPF were divided into different subgroups according to the gene expression profiles, which were obtained from the Gene Expression Omnibus (GEO) database. In addition, these subgroups present different expression forms and clinical features. Therefore, weighted gene coexpression analysis (WGCNA) was used to seek the differences between subtypes. And six subgroup-specific WGCNA modules were identified. RESULTS: Combined with the characteristics of WGCNA and KEGG enrichment modules, the autophagic pathway was only upregulated in subgroup I and enriched significantly. The differentiation pathways of Th1 and Th2 cells were only upregulated and enriched in subgroup II. At the same time, combined with clinical information, IPF patients in subgroup II were older and more serious, which may be closely related to the differentiation of Th1 and Th2 cells. In contrast, the neuroactive ligand-receptor interaction pathway and Ca+ signaling pathway were significantly upregulated and enriched in subgroup III. Although there was no significant difference in prognosis between subgroup I and subgroup III, their intrinsic biological characteristics were very different. These results suggest that the subtypes may represent risk factors of age and intrinsic biological characteristics and may also partly reflect the severity of the disease. CONCLUSION: In conclusion, current studies have improved our understanding of IPF-related molecular mechanisms. At the same time, because the results show that patients from different subgroups may have their own unique gene expression patterns, it reminds us that patients in each subgroup should receive more personalized treatment.

Diagnostic and prognostic implications of 2018 guideline for the diagnosis of idiopathic pulmonary fibrosis in clinical practice.

The purpose of this study was to evaluate the implications of the 2018 updated guideline for the diagnosis of idiopathic pulmonary fibrosis (IPF) in clinical practice compared to 2011 guideline. This study involved 535 patients including 339 IPF and 196 non-IPF, and we retrospectively evaluated CT classifications of usual interstitial pneumonia (UIP) by two guidelines. Interobserver agreement of 2018 criteria showed moderate reliability (κ = 0.53) comparable to 2011 (κ = 0.56) but interobserver agreement for probable UIP was fair (κ = 0.40). CT pattern of indeterminate for UIP was associated with better prognosis compared with the other groups (adjusted hazard ratio [HR] = 0.36, p < 0.001). Compared to possible UIP, probable UIP demonstrated a lower positive predictive value (PPV, 62.9% vs 65.8%). In analysis of patients with CT patterns of non-definite UIP, diagnosing IPF when CT pattern showed probable UIP with lymphocyte count ≤ 15% in BAL fluid, and either male sex or age ≥ 60 years showed a high specificity of 90.6% and a PPV of 80.8% in the validation cohort. The 2018 criteria provide better prognostic stratification than the 2011 in patients with possible UIP. BAL fluid analysis can improve the diagnostic certainty for IPF diagnosis in patients with probable UIP CT pattern.

[Comparison of the clinical features of idiopathic pulmonary fibrosis in Japan and the U.S.A., based on disease severity].

OBJECTIVES: The aim of this study was to assess the clinical characteristics of idiopathic pulmonary fibrosis (IPF) in patients with stage I disease severity based on the criteria of the Japanese Respiratory Society (JRS), which correspond to moderate or severe U.S.A. criteria. PATIENTS AND METHODS: In 46 consecutive patients with IPF who were admitted to our institution from June 2003 through September 2009, 27 were given diagnoses of stage I disease severity based on JRS criteria. These 27 were classified into 3 groups: Group A (stage I disease severity according to the JRS criteria, corresponding to mild on U.S.A. criteria, n=17), group B (stage I disease severity according to JRS criteria, corresponding to moderate or severe on U.S.A. criteria, n=10), and group C (stage I disease severity based on the JRS criteria, corresponding to severe U.S.A. criteria, n=6). We compared these groups using demographic and spirometric tests, the 6-minute walking test (6MWT), estimated systolic pulmonary arterial pressure (esPAP), and survival rates in each group. RESULTS: stage I disease severity according to the JRS criteria corresponded to the following grade based on U.S.A. criteria: mild, 17 cases; moderate, 4 cases; severe, 6 cases. The values of lowest SpO2 and %DLco in group B and group C were significantly lower than those in group A, and values of the Hugh-Jones score and esPAP were higher than those in group A. In addition, the survival rate in group B and group C was significantly worse than that in group A. The survival rate in patients with stage I disease severity who showed desaturation on exertion with %DLco < or = 50%, was significantly worse than in those who showed SpO2 > or = 90% on exertion with %DLco >50% (23.7 16.5 months vs. 16.6 +/- 11.3 months; P = 0.002). CONCLUSIONS: This study suggested that IPF patients with stage I disease severity according to JRS criteria included the grades of moderate and severe according to U.S.A. criteria. This suggests that we should revise the classification of disease severity for IPF in Japan.