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.

Machine Learning of Plasma Proteomics Classifies Diagnosis of Interstitial Lung Disease.

RATIONALE: Distinguishing connective tissue disease associated interstitial lung disease (CTD-ILD) from idiopathic pulmonary fibrosis (IPF) can be clinically challenging. OBJECTIVES: Identify proteins that separate and classify CTD-ILD from IPF patients. METHODS: Four registries with 1247 IPF and 352 CTD-ILD patients were included in analyses. Plasma samples were subjected to high-throughput proteomics assays. Protein features were prioritized using Recursive Feature Elimination (RFE) to construct a proteomic classifier. Multiple machine learning models, including Support Vector Machine, LASSO regression, Random Forest (RF), and imbalanced-RF, were trained and tested in independent cohorts. The validated models were used to classify each case iteratively in external datasets. MEASUREMENT AND MAIN RESULTS: A classifier with 37 proteins (PC37) was enriched in biological process of bronchiole development and smooth muscle proliferation, and immune responses. Four machine learning models used PC37 with sex and age score to generate continuous classification values. Receiver-operating-characteristic curve analyses of these scores demonstrated consistent Area-Under-Curve 0.85-0.90 in test cohort, and 0.94-0.96 in the single-sample dataset. Binary classification demonstrated 78.6%-80.4% sensitivity and 76%-84.4% specificity in test cohort, 93.5%-96.1% sensitivity and 69.5%-77.6% specificity in single-sample classification dataset. Composite analysis of all machine learning models confirmed 78.2% (194/248) accuracy in test cohort and 82.9% (208/251) in single-sample classification dataset. CONCLUSIONS: Multiple machine learning models trained with large cohort proteomic datasets consistently distinguished CTD-ILD from IPF. Identified proteins involved in immune pathways. We further developed a novel approach for single sample classification, which could facilitate honing the differential diagnosis of ILD in challenging cases and improve clinical decision-making.

The impact of antifibrotic use on long-term clinical outcomes in the pulmonary fibrosis foundation registry.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a devastating interstitial lung disease (ILD) with a high mortality rate. The antifibrotic medications pirfenidone and nintedanib have been in use since 2014 for this disorder and are associated with improved rate of lung function decline. Less is known about their long-term outcomes outside of the clinical trial context. METHODS: The Pulmonary Fibrosis Foundation Patient Registry was used for this study. Patients with an IPF diagnosis made within a year of enrollment were included. The treated group was defined as patients receiving either pirfenidone or nintedanib for at least 180 days. The untreated group did not have any record of antifibrotic use. Demographic data, comorbidities, serial lung function, hospitalization, and vital status data were collected from the registry database. The primary outcomes were transplant-free survival, time to first respiratory hospitalization, and time to 10% absolute FVC decline. Time-to-event analyses were performed utilizing Cox proportional hazards models and the log-rank test. Model covariates included age, gender, smoking history, baseline lung function, comorbidities, and oxygen use. RESULTS: The registry contained 1212 patients with IPF; ultimately 288 patients met inclusion criteria for the treated group, and 101 patients were designated as untreated. Patients treated with antifibrotics were significantly younger (69.8 vs. 72.6 years, p = 0.008) and less likely to have smoked (61.1% ever smokers vs. 72.3% never smokers, p = 0.04). No significant differences were seen in race, gender, comorbidities, or baseline pulmonary function between groups. The primary outcome of transplant-free survival was not significantly different between the two groups (adjusted HR 0.799, 95% CI 0.534-1.197, p = 0.28). Time to respiratory hospitalization was significantly shorter in the treated group (adjusted HR 2.12, 95% CI 1.05-4.30, p = 0.04). No significant difference in time to pulmonary function decline was seen between groups. CONCLUSIONS: This multicenter study demonstrated 63% of newly diagnosed IPF patients had continuous antifibrotic usage. Antifibrotics were not associated with improved transplant-free survival or pulmonary function change but was associated with an increased hazard of respiratory hospitalization. Future studies should further investigate the role of antifibrotic therapy in clinically important outcomes in real-world patients with IPF and other progressive ILDs.

Validation of Proposed Criteria for Progressive Pulmonary Fibrosis.

Rationale: Criteria for progressive pulmonary fibrosis (PPF) have been proposed, but their prognostic value beyond categorical decline in FVC remains unclear. Objectives: To determine whether proposed PPF criteria predict transplant-free survival (TFS) in patients with non-idiopathic pulmonary fibrosis (IPF) forms of interstitial lung disease (ILD). Methods: A retrospective, multicenter cohort analysis was performed. Patients with diagnoses of fibrotic connective tissue disease-associated ILD, fibrotic hypersensitivity pneumonitis, and non-IPF idiopathic interstitial pneumonia from three U.S. centers and one UK center constituted the test and validation cohorts, respectively. Cox proportional hazards regression was used to test the association between 5-year TFS and ⩾10% FVC decline, followed by 13 additional PPF criteria satisfied in the absence of ⩾10% FVC decline. Measurements and Main Results: One thousand three hundred forty-one patients met the inclusion criteria. A ⩾10% relative FVC decline was the strongest predictor of reduced TFS and showed consistent TFS association across cohorts, ILD subtypes, and treatment groups, resulting in a phenotype that closely resembled IPF. Ten additional PPF criteria satisfied in the absence of 10% relative FVC decline were also associated with reduced TFS in the U.S. test cohort, with 6 maintaining TFS associations in the UK validation cohort. Validated PPF criteria requiring a combination of physiologic, radiologic, and symptomatic worsening performed similarly to their stand-alone components but captured a smaller number of patients. Conclusions: An FVC decline of ⩾10% and six additional PPF criteria satisfied in the absence of such decline identify patients with non-IPF ILD at increased risk for death or lung transplantation.

Proteomic Biomarkers of Survival in Idiopathic Pulmonary Fibrosis.

RATIONALE: Idiopathic pulmonary fibrosis (IPF) causes progressive lung scarring and high mortality. Reliable and accurate prognostic biomarkers are urgently needed. OBJECTIVE: To identify and validate circulating protein biomarkers of IPF survival. METHODS: High-throughput proteomic data were generated using prospectively collected plasma samples from patients with IPF from the Pulmonary Fibrosis Foundation Patient Registry (discovery cohort) and the Universities of California-Davis, Chicago, and Virginia (validation cohort). Proteins associated with three-year transplant-free survival (TFS) were identified using multivariable Cox proportional hazards regression. Those associated with TFS after adjustment for false discovery in the discovery cohort were advanced for testing in the validation cohort, with proteins maintaining TFS association with consistent effect direction considered validated. After combining cohorts, functional analyses were performed, and machine learning used to derive a proteomic signature of TFS. MAIN RESULTS: Of 2921 proteins tested in the discovery cohort (n=871), 231 were associated with differential TFS. Of these, 140 maintained TFS association with consistent effect direction in the validation cohort (n=355). After combining cohorts, validated proteins with strongest TFS association were latent-transforming growth factor beta-binding protein 2 (HR 2.43, 95% CI 2.09-2.82), collagen alpha-1(XXIV) chain (HR 2.21; 95% CI 1.86-2.39) and keratin 19 (HR 1.60; 95% CI 1.47-1.74). In decision curve analysis, a proteomic signature of TFS outperformed a similarly derived clinical prediction model. CONCLUSIONS: In largest proteomic investigation of IPF outcomes performed to date, we identified and validated 140 protein biomarkers of TFS. These results shed important light on potential drivers of IPF progression.

Race and Ethnicity in Pulmonary Function Test Interpretation: An Official American Thoracic Society Statement.

Current American Thoracic Society (ATS) standards promote the use of race and ethnicity-specific reference equations for pulmonary function test (PFT) interpretation. There is rising concern that the use of race and ethnicity in PFT interpretation contributes to a false view of fixed differences between races and may mask the effects of differential exposures. This use of race and ethnicity may contribute to health disparities by norming differences in pulmonary function. In the United States and globally, race serves as a social construct that is based on appearance and reflects social values, structures, and practices. Classification of people into racial and ethnic groups differs geographically and temporally. These considerations challenge the notion that racial and ethnic categories have biological meaning and question the use of race in PFT interpretation. The ATS convened a diverse group of clinicians and investigators for a workshop in 2021 to evaluate the use of race and ethnicity in PFT interpretation. Review of evidence published since then that challenges current practice and continued discussion concluded with a recommendation to replace race and ethnicity-specific equations with race-neutral average reference equations, which must be accompanied with a broader re-evaluation of how PFTs are used to make clinical, employment, and insurance decisions. There was also a call to engage key stakeholders not represented in this workshop and a statement of caution regarding the uncertain effects and potential harms of this change. Other recommendations include continued research and education to understand the impact of the change, to improve the evidence for the use of PFTs in general, and to identify modifiable risk factors for reduced pulmonary function.

PCSK6 and Survival in Idiopathic Pulmonary Fibrosis.

Rationale: Idiopathic pulmonary fibrosis (IPF) is a devastating disease characterized by limited treatment options and high mortality. A better understanding of the molecular drivers of IPF progression is needed. Objectives: To identify and validate molecular determinants of IPF survival. Methods: A staged genome-wide association study was performed using paired genomic and survival data. Stage I cases were drawn from centers across the United States and Europe and stage II cases from Vanderbilt University. Cox proportional hazards regression was used to identify gene variants associated with differential transplantation-free survival (TFS). Stage I variants with nominal significance (P < 5 × 10-5) were advanced for stage II testing and meta-analyzed to identify those reaching genome-wide significance (P < 5 × 10-8). Downstream analyses were performed for genes and proteins associated with variants reaching genome-wide significance. Measurements and Main Results: After quality controls, 1,481 stage I cases and 397 stage II cases were included in the analysis. After filtering, 9,075,629 variants were tested in stage I, with 158 meeting advancement criteria. Four variants associated with TFS with consistent effect direction were identified in stage II, including one in an intron of PCSK6 (proprotein convertase subtilisin/kexin type 6) reaching genome-wide significance (hazard ratio, 4.11 [95% confidence interval, 2.54-6.67]; P = 9.45 × 10-9). PCSK6 protein was highly expressed in IPF lung parenchyma. PCSK6 lung staining intensity, peripheral blood gene expression, and plasma concentration were associated with reduced TFS. Conclusions: We identified four novel variants associated with IPF survival, including one in PCSK6 that reached genome-wide significance. Downstream analyses suggested that PCSK6 protein plays a potentially important role in IPF progression.

Tobacco smoking is associated with combined pulmonary fibrosis and emphysema and worse outcomes in interstitial lung disease.

Tobacco smoking is an established cause of pulmonary disease whose contribution to interstitial lung disease (ILD) is incompletely characterized. We hypothesized that compared with nonsmokers, subjects who smoked tobacco would differ in their clinical phenotype and have greater mortality. We performed a retrospective cohort study of tobacco smoking in ILD. We evaluated demographic and clinical characteristics, time to clinically meaningful lung function decline (LFD), and mortality in patients stratified by tobacco smoking status (ever vs. never) within a tertiary center ILD registry (2006-2021) and replicated mortality outcomes across four nontertiary medical centers. Data were analyzed by two-sided t tests, Poisson generalized linear models, and Cox proportional hazard models adjusted for age, sex, forced vital capacity (FVC), diffusion capacity of the lung for carbon monoxide (DLCO), ILD subtype, antifibrotic therapy, and hospital center. Of 1,163 study participants, 651 were tobacco smokers. Smokers were more likely to be older, male, have idiopathic pulmonary fibrosis (IPF), coronary artery disease, CT honeycombing and emphysema, higher FVC, and lower DLCO than nonsmokers (P < 0.01). Time to LFD in smokers was shorter (19.7 ± 20 mo vs. 24.8 ± 29 mo; P = 0.038) and survival time was decreased [10.75 (10.08-11.50) yr vs. 20 (18.67-21.25) yr; adjusted mortality HR = 1.50, 95%CI 1.17-1.92; P < 0.0001] compared with nonsmokers. Smokers had 12% greater odds of death for every additional 10 pack yr of smoking (P < 0.0001). Mortality outcomes remained consistent in the nontertiary cohort (HR = 1.51, 95%CI = 1.03-2.23; P = 0.036). Tobacco smokers with ILD have a distinct clinical phenotype strongly associated with the syndrome of combined PF and emphysema, shorter time to LFD, and decreased survival. Smoking prevention may improve ILD outcomes.NEW & NOTEWORTHY Smoking in ILD is associated with combined pulmonary fibrosis and emphysema and worse clinical outcomes.

Lung function trajectory in progressive fibrosing interstitial lung disease.

BACKGROUND: Proposed criteria for progressive fibrosing interstitial lung disease (PF-ILD) have been linked to increased mortality risk, but lung function trajectory after satisfying individual criteria remains unknown. Because survival is rarely employed as the primary end-point in therapeutic trials, identifying PF-ILD criteria that best predict subsequent change in forced vital capacity (FVC) could improve clinical trial design. METHODS: A retrospective, multicentre longitudinal cohort analysis was performed in consecutive patients with fibrotic connective tissue disease-associated ILD (CTD-ILD), chronic hypersensitivity pneumonitis and idiopathic interstitial pneumonia at three US centres (test cohort) and one UK centre (validation cohort). 1-year change in FVC after satisfying proposed PF-ILD criteria was estimated using joint modelling. Subgroup analyses were performed to determine whether results varied across key subgroups. RESULTS: 1227 patients were included, with CTD-ILD predominating. Six out of nine PF-ILD criteria were associated with differential 1-year change in FVC, with radiological progression of fibrosis, alone and in combination with other features, associated with the largest subsequent decline in FVC. Findings varied significantly by ILD subtype, with CTD-ILD demonstrating little change in FVC after satisfying most PF-ILD criteria, while other ILDs showed significantly larger changes. Findings did not vary after stratification by radiological pattern or exposure to immunosuppressant therapy. Near-term change in FVC after satisfying proposed PF-ILD criteria was heterogeneous depending on the criterion assessed and was strongly influenced by ILD subtype. CONCLUSIONS: These findings may inform future clinical trial design and suggest ILD subtype should be taken into consideration when applying PF-ILD criteria.

Hypersensitivity pneumonitis: Current concepts in pathogenesis, diagnosis, and treatment.

Hypersensitivity pneumonitis is an immune-mediated interstitial lung disease caused by an aberrant response to an inhaled exposure, which results in mostly T cell-mediated inflammation, granuloma formation, and fibrosis in some cases. HP is diagnosed by exposure identification, HRCT findings of ground-glass opacities, centrilobular nodules, and mosaic attenuation, with traction bronchiectasis and honeycombing in fibrotic cases. Additional testing including serum IgG testing for the presence of antigen exposure, bronchoalveolar lavage lymphocytosis, and lung biopsy demonstrating granulomas, inflammation, and fibrosis, increases the diagnostic confidence. Treatment for HP includes avoidance of the implicated exposure, immunosuppression, and anti-fibrotic therapy in select cases. This narrative review presents the recent literature in the understanding of the immunopathological mechanisms, diagnosis, and treatment of HP.

Environmental and occupational exposures in interstitial lung disease.

PURPOSE OF REVIEW: We highlight recent advances in the understanding of how environmental and occupational exposures increase the risk of developing interstitial lung disease (ILD), and how to evaluate a patient for potential exposures. RECENT FINDINGS: A review of emerging literature suggests that environmental and occupational exposures can be directly causal, as in the case of the pneumoconioses and smoking-related ILDs, or one of many contributors to disease, as in the case of idiopathic pulmonary fibrosis (IPF). Regardless of the level of association, exposures are clearly prevalent across all ILD subtypes studied. SUMMARY: Inhalational exposures are increasingly recognized as an important component in the development of ILDs, and novel exposure-disease associations continue to be discovered. These exposures represent potential opportunities for further understanding the pathobiology of disease and for the prevention of these often progressive and debilitating disorders. Prospective, comprehensive data collection regarding occupational and environmental exposures are needed in ILD patients to fully elucidate specific antigens and their relationships to disease incidence and outcomes. Systematically collected exposure information will also inform potential interventions to remediate exposures and thus mitigate the course of frequently progressive and fatal diseases.

Inhalational exposures in patients with fibrotic interstitial lung disease: Presentation, pulmonary function and survival in the Canadian Registry for Pulmonary Fibrosis.

BACKGROUND AND OBJECTIVE: Inhalational exposures are a known cause of interstitial lung disease (ILD), but little is understood about their prevalence across ILD subtypes and their relationship with pulmonary function and survival. METHODS: Patients with fibrotic ILD were identified from the multicentre Canadian Registry for Pulmonary Fibrosis. Patients completed questionnaires regarding ILD-related occupational and environmental exposures. The relationship between exposures and the outcomes of baseline age, gender, family history, pulmonary function and survival was analysed using linear and logistic regression models, linear mixed-effect regression models and survival analysis using multivariable Cox proportional hazards along with the log-rank test. RESULTS: There were 3820 patients included in this study, with 2385 (62%) having ILD-related inhalational exposure. Exposed patients were younger, particularly in the idiopathic pulmonary fibrosis subgroup. Inhalational exposure was associated with male gender (adjusted OR 1.46, 95% CI 1.28-1.68, p < 0.001) and family history of pulmonary fibrosis (adjusted OR 1.73, 95% CI 1.40-2.15, p < 0.001). Patients with any inhalational exposure had improved transplant-free survival (hazard ratio 0.81, 95% CI 0.71-0.92, p = 0.001); this effect persisted across diagnostic subtypes. The relationship between exposures and annual change in forced vital capacity varied by ILD subtype. CONCLUSION: Patients with fibrotic ILD report high prevalence of inhalational exposures across ILD subtypes. These exposures were associated with younger age at diagnosis, male gender and family history of pulmonary fibrosis. Identification of an inhalational exposure was associated with a survival benefit. These findings suggest that inhaled exposures may impact clinical outcomes in patients with ILD, and future work should characterize the mechanisms underlying these relationships.

The other connective tissue disease-associated interstitial lung diseases: Sjogren's syndrome, mixed connective tissue disease, and systemic lupus erythematosus.

PURPOSE OF REVIEW: We review the clinical manifestations of three less common connective tissue disease (CTD)-associated interstitial lung diseases (ILDs): Sjogren's syndrome (SjS), mixed CTD (MCTD), and systemic lupus erythematosus (SLE). RECENT FINDINGS: SjS is classically associated with lymphocytic interstitial pneumonia and cystic lung disease, but the most common type of ILD in Sjogren's patients is nonspecific interstitial pneumonia. ILD is prevalent in MCTD and associated with worse survival. SLE-associated ILD, while rare, is more common in those with CTD overlap syndromes. Regardless of underlying cause, a subset of patients with fibrotic CTD-associated ILD develop a progressive course for which antifibrotic agents and lung transplantation should be considered. SUMMARY: An understanding of the characteristics of ILD in SjS, MCTD, and SLE is important for the pulmonary specialist. Future research should identify risk factors for progression and develop additional treatment modalities for both CTD-related autoimmune features and progressive ILD.

Interstitial Pneumonia with Autoimmune Features: Overview of proposed criteria and recent cohort characterization.

The accurate diagnosis of interstitial lung disease (ILD) is essential for optimal prognostication and management. While connective tissue disease (CTD) is among the most common causes of ILD, some patients have features suggestive of autoimmunity without meeting criteria for a specific CTD. To help define and study this disease entity more uniformly, a 2015 research statement proposed consensus-based criteria and coined the term "interstitial pneumonia with autoimmune features" (IPAF). In this review, we summarize and compare previously proposed criteria to characterize these patients, provide an overview of the IPAF criteria and highlight recent investigations aimed at characterizing IPAF cohorts. We then call attention to questions that have arisen with the application of the IPAF criteria and discuss future areas of study.

Risk Factors for Hospital Readmission in Patients With Interstitial Lung Disease.

BACKGROUND: Little is known about the rates, causes, or risk factors for hospital readmission among patients with interstitial lung disease (ILD). We investigated the prevalence, features, and comorbidities of subjects hospitalized with ILD and their subsequent re-hospitalizations in this retrospective study. METHODS: A retrospective analysis of subjects enrolled in the University of Chicago ILD Natural History registry was conducted. Demographic data, comorbidities, and timing and cause of subsequent hospitalizations were collected from the medical record. The primary outcome was time to first readmission via a cause-specific Cox hazards model with a sensitivity analysis with the Fine-Gray cumulative hazard model; the secondary outcome was the number of hospitalizations per subject via a Poisson multivariable model. RESULTS: Among 1,796 patients with ILD, 443 subjects were hospitalized, with 978 total hospitalizations; 535 readmissions were studied, 282 (53%) for a respiratory indication. For the outcome of time to readmission, Black race was the only subject characteristic associated with an increased hazard of readmission in the Cox model (hazard ratio 1.50, P = .03) while Black race, hypersensitivity pneumonitis, and sarcoidosis were associated with increased hazard of readmission in the Fine-Gray model. Black race, female sex, atrial fibrillation, obstructive lung disease, and pulmonary hypertension were associated with an increased number of hospitalizations in the Poisson model. CONCLUSIONS: We demonstrated that hospital readmission from any cause was a common occurrence in subjects with ILD. Further efforts to improve quality of life among these subjects could focus on risk scores for readmission, mitigating racial health disparities, and treatment of comorbidities.

Scoping review of exposure questionnaires and surveys in interstitial lung disease.

BACKGROUND: Many interstitial lung diseases (ILDs) have clear causal relationships with environmental and occupational exposures. Exposure identification can assist with diagnosis, understanding disease pathogenesis, prognostication and prevention of disease progression and occurrence in others at risk. Despite the importance of exposure identification in ILD, there is no standardised assessment approach. Many questionnaires are in clinical and research use, yet their utility, applicability, relevance and performance characteristics are unknown. OBJECTIVES: This scoping review aimed to summarise the available evidence relating to ILD exposure assessment questionnaires, identify research gaps and inform the content for a future single evidence-based ILD questionnaire. METHODS: A scoping review based on Arksey and O'Malley's methodological framework was conducted. ELIGIBILITY CRITERIA: Any questionnaire that elicited exposures specific to ILD was included. A modified COSMIN Risk of Bias Framework was used to assess quality. SOURCES OF EVIDENCE: Relevant articles were identified from MEDLINE and EMBASE up to 23 July 2023. RESULTS: 22 exposure questionnaires were identified, including 15 generally pertaining to ILD, along with several disease-specific questionnaires for hypersensitivity pneumonitis (n=4), chronic beryllium disease, sarcoidosis and silicosis (1 questionnaire each). For most questionnaires, quality was low, whereby the methods used to determine exposure inclusion and questionnaire validation were not reported or not performed. Collectively the questionnaires covered 158 unique exposures and at-risk occupations, most commonly birds, mould/water damage, wood dust, asbestos, farming, automotive mechanic and miners. Only five questionnaires also provided free-text fields, and 13 queried qualifiers such as temporality or respiratory protection. CONCLUSIONS: Designing a robust ILD-specific questionnaire should include an evidence-based and relevance-based approach to exposure derivation, with clinicians and patients involved in its development and tested to ensure relevance and feasibility.

Phage Immunoprecipitation-Sequencing Reveals CDHR5 Autoantibodies in Select Patients With Interstitial Lung Disease.

OBJECTIVE: Interstitial lung diseases (ILDs) are a heterogeneous group of disorders that can develop in patients with connective tissue diseases. Establishing autoimmunity in ILD impacts prognosis and treatment. Patients with ILD are screened for autoimmunity by measuring antinuclear autoantibodies, rheumatoid factors, and other nonspecific tests. However, this approach may miss autoimmunity that manifests as autoantibodies to tissue antigens not previously defined in ILD. METHODS: We use Phage Immunoprecipitation-Sequencing (PhIP-Seq) to conduct an autoantibody discovery screen of patients with ILD and controls. We screened for novel autoantigen candidates using PhIP-Seq. We next developed a radio-labeled binding assay and validated the leading candidate in 398 patients with ILD recruited from two academic medical centers and 138 blood bank individuals that formed our reference cohort. RESULTS: PhIP-Seq identified 17 novel autoreactive targets, and machine learning classifiers derived from these targets discriminated ILD serum from controls. Among the 17 candidates, we validated CDHR5 and found CDHR5 autoantibodies in patients with rheumatologic disorders and importantly, patients not previously diagnosed with autoimmunity. Using survival and transplant free-survival data available from one of the two centers, patients with CDHR5 autoantibodies showed worse survival compared with other patients with connective tissue disease ILD. CONCLUSION: We used PhIP-Seq to define a novel CDHR5 autoantibody in a subset of select patients with ILD. Our data complement a recent study showing polymorphisms in the CDHR5-IRF7 gene locus strongly associated with titer of anticentromere antibodies in systemic sclerosis, creating a growing body of evidence suggesting a link between CDHR5 and autoimmunity.