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.

Identification of connective tissue disease autoantibodies and a novel autoantibody anti-annexin A11 in patients with "idiopathic" interstitial lung disease.

BACKGROUND: Autoantibodies are a hallmark feature of Connective Tissue Diseases (CTD). Their presence in patients with idiopathic interstitial lung disease (ILD) may suggest covert CTD. We aimed to determine the prevalence of CTD autoantibodies in patients diagnosed with idiopathic ILD. METHODS: 499 patient sera were analysed: 251 idiopathic pulmonary fibrosis (IPF), 206 idiopathic non-specific interstitial pneumonia (iNSIP) and 42 cryptogenic organising pneumonia (COP). Autoantibody status was determined by immunoprecipitation. RESULTS: 2.4% of IPF sera had a CTD-autoantibody compared to 10.2% of iNSIP and 7.3% of COP. 45% of autoantibodies were anti-synthetases. A novel autoantibody targeting an unknown 56 kDa protein was found in seven IPF patients (2.8%) and two NSIP (1%) patients. This was characterised as anti-annexin A11. CONCLUSION: Specific guidance on autoantibody testing and interpretation in patients with ILD could improve diagnostic accuracy. Further work is required to determine the clinical significance of anti-annexin A11.

Adaptive multi-interventional trial platform to improve patient care for fibrotic interstitial lung diseases.

BACKGROUND: Fibrotic interstitial lung diseases (fILDs) are a heterogeneous group of lung diseases associated with significant morbidity and mortality. Despite a large increase in the number of clinical trials in the last 10 years, current regulatory-approved management approaches are limited to two therapies that prevent the progression of fibrosis. The drug development pipeline is long and there is an urgent need to accelerate this process. This manuscript introduces the concept and design of an innovative research approach to drug development in fILD: a global Randomised Embedded Multifactorial Adaptive Platform in fILD (REMAP-ILD). METHODS: Description of the REMAP-ILD concept and design: the specific terminology, design characteristics (multifactorial, adaptive features, statistical approach), target population, interventions, outcomes, mission and values, and organisational structure. RESULTS: The target population will be adult patients with fILD, and the primary outcome will be a disease progression model incorporating forced vital capacity and mortality over 12 months. Responsive adaptive randomisation, prespecified thresholds for success and futility will be used to assess the effectiveness and safety of interventions. REMAP-ILD embraces the core values of diversity, equity, and inclusion for patients and researchers, and prioritises an open-science approach to data sharing and dissemination of results. CONCLUSION: By using an innovative and efficient adaptive multi-interventional trial platform design, we aim to accelerate and improve care for patients with fILD. Through worldwide collaboration, novel analytical methodology and pragmatic trial delivery, REMAP-ILD aims to overcome major limitations associated with conventional randomised controlled trial approaches to rapidly improve the care of people living with fILD.

Clinical presentation, course, and prognosis of patients with mixed connective tissue disease: A multicenter retrospective cohort.

OBJECTIVES: The objective of this study is to better characterize the features and outcomes of a large population of patients with mixed connective tissue disease (MCTD). METHODS: We performed an observational retrospective multicenter cohort study in France. Patients who fulfilled at least one diagnostic criterion set for MCTD and none of the criteria for other differentiated CTD (dCTD) were included. RESULTS: Three hundred and thirty patients (88% females, median [interquartile range] age of 35 years [26-45]) were included. The diagnostic criteria of Sharp or Kasukawa were met by 97.3% and 93.3% of patients, respectively. None met other classification criteria without fulfilling Sharp or Kasukawa criteria. After a median follow-up of 8 (3-14) years, 149 (45.2%) patients achieved remission, 92 (27.9%) had interstitial lung disease, 25 (7.6%) had pulmonary hypertension, and 18 (5.6%) died. Eighty-five (25.8%) patients progressed to a dCTD, mainly systemic sclerosis (15.8%) or systemic lupus erythematosus (10.6%). Median duration between diagnosis and progression to a dCTD was 5 (2-11) years. The presence at MCTD diagnosis of an abnormal pattern on nailfold capillaroscopy (odds ratio [OR] = 2.44, 95% confidence interval [95%CI] [1.11-5.58]) and parotid swelling (OR = 3.86, 95%CI [1.31-11.4]) were statistically associated with progression to a dCTD. Patients who did not progress to a dCTD were more likely to achieve remission at the last follow-up (51.8% vs. 25.9%). CONCLUSIONS: This study shows that MCTD is a distinct entity that can be classified using either Kasukawa or Sharp criteria, and that only 25.8% of patients progress to a dCTD during follow-up.

Anti-U1RNP antibodies are associated with a distinct clinical phenotype and a worse survival in patients with systemic sclerosis.

OBJECTIVES: To clarify the impact of anti-U1RNP antibodies on the clinical features and prognosis of patients with SSc. METHODS: We conducted a monocentric case-control, retrospective, longitudinal study. For each patient with SSc and anti-U1RNP antibodies (SSc-RNP+), one patient with mixed connective tissue disease (MCTD) and 2 SSc patients without anti-U1RNP antibodies (SSc-RNP-) were matched for age, sex, and date of inclusion. RESULTS: Sixty-four SSc-RNP+ patients were compared to 128 SSc-RNP- and 64 MCTD patients. Compared to SSc-RNP-, SSc-RNP+ patients were more often of Afro-Caribbean origin (31.3% vs. 11%, p < 0.01), and more often had an overlap syndrome than SSc-RNP- patients (53.1 % vs. 22.7%, p < 0.0001), overlapping with Sjögren's syndrome (n = 23, 35.9%) and/or systemic lupus erythematosus (n = 19, 29.7%). SSc-RNP+ patients were distinctly different from MCTD patients but less often had joint involvement (p < 0.01). SSc-RNP+ patients more frequently developed interstitial lung disease (ILD) (73.4% vs. 55.5% vs. 31.3%, p < 0.05), pulmonary fibrosis (PF) (60.9% vs. 37.5% vs. 10.9%, p < 0.0001), SSc associated myopathy (29.7% vs. 6.3% vs. 7.8%, p < 0.0001), and kidney involvement (10.9% vs. 2.3% vs. 1.6%, p < 0.05). Over a 200-month follow-up period, SSc-RNP+ patients had worse overall survival (p < 0.05), worse survival without PF occurrence (p < 0.01), ILD or PF progression (p < 0.01 and p < 0.0001). CONCLUSIONS: In SSc patients, anti-U1RNP antibodies are associated with a higher incidence of overlap syndrome, a distinct clinical phenotype, and poorer survival compared to SSc-RNP- and MCTD patients. Our study suggests that SSc-RNP+ patients should be separated from MCTD patients and may constitute an enriched population for progressive lung disease.

Lung imaging patterns in connective tissue disease-associated interstitial lung disease impact prognosis and immunosuppression response.

OBJECTIVES: Interstitial lung disease (ILD) in connective tissue diseases (CTD) have highly variable morphology. We aimed to identify imaging features and their impact on ILD progression, mortality and immunosuppression response. METHODS: Patients with CTD-ILD had high-resolution chest computed tomography (HRCT) reviewed by expert radiologists blinded to clinical data for overall imaging pattern (usual interstitial pneumonia [UIP]; non-specific interstitial pneumonia [NSIP]; organizing pneumonia [OP]; fibrotic hypersensitivity pneumonitis [fHP]; and other). Transplant-free survival and change in percent-predicted forced vital capacity (FVC) were compared using Cox and linear mixed effects models adjusted for age, sex, smoking, and baseline FVC. FVC decline after immunosuppression was compared with pre-treatment. RESULTS: Of 645 CTD-ILD patients, the frequent CTDs were systemic sclerosis (n = 215), rheumatoid arthritis (n = 127), and inflammatory myopathies (n = 100). NSIP was the most common pattern (54%), followed by UIP (20%), fHP (9%), and OP (5%). Compared with UIP, FVC decline was slower for NSIP (1.1%/year, 95%CI 0.2, 1.9) and OP (3.5%/year, 95%CI 2.0, 4.9), and mortality was lower for NSIP (HR 0.65, 95%CI 0.45, 0.93) and OP (HR 0.18, 95%CI 0.05, 0.57), but higher in fHP (HR 1.58, 95%CI 1.01, 2.40). The extent of fibrosis also predicted FVC decline and mortality. After immunosuppression, FVC decline was slower compared with pre-treatment in NSIP (by 2.1%/year, 95%CI 1.4, 2.8), with no change for UIP or fHP. CONCLUSION: Multiple radiologic patterns are possible in CTD-ILD, including a fHP pattern. NSIP and OP were associated with better outcomes and response to immunosuppression, while fHP had worse survival compared with UIP.

Anti-survival motor neuron complex antibodies as a novel biomarker for pulmonary arterial hypertension and interstitial lung disease in mixed connective tissue disease.

OBJECTIVE: The presence of anti-U1 RNP antibodies (Abs) is critical for diagnosing MCTD. The aim of this study is to evaluate the clinical relevance of anti-survival motor neuron (SMN) complex Abs, which often coexist with anti-U1 RNP Abs. METHODS: A total of 158 newly diagnosed consecutive cases of SLE, SSc or MCTD with anti-U1 RNP Abs were enrolled in this multicentre observational study between April 2014 and August 2022. Serum anti-SMN complex Abs were screened by immunoprecipitation of 35S-methionine-labelled cell extracts, and associations between anti-SMN complex Abs positivity and clinical characteristics were analysed. RESULTS: Anti-SMN complex Abs were detected in 36% of MCTD patients, which was significantly higher than that in SLE (8%) or SSc (12%). Among MCTD patients classified based on the combination of the clinical features of SLE, SSc and idiopathic inflammatory myopathies, anti-SMN complex Abs showed the highest prevalence in a subset with clinical features of all three components. Anti-SMN complex Abs-positive MCTD had a higher prevalence of pulmonary arterial hypertension (PAH) and interstitial lung disease (ILD), which are related to poor prognosis, than negative patients. Moreover, all three cases of death within 1 year of the treatment were positive for anti-SMN complex Abs. CONCLUSIONS: Anti-SMN complex Abs is the first biomarker of a typical subset of MCTD which bears organ damages such as PAH and ILD.

Fragmented QRS complex could predict all-cause mortality in patients with connective tissue disease-associated pulmonary arterial hypertension.

OBJECTIVES: To investigate the prognostic impact and pathophysiological characteristics of fragmented QRS complex (fQRS) on patients with connective tissue disease-associated pulmonary arterial hypertension (CTD-PAH). METHODS: This was a multicentre retrospective study recruiting 141 patients with CTD-PAH diagnosed by right heart catheterization (114 cases in the discovery cohort and 27 cases in the validation cohort). fQRS and ST-T change were detected on conventional 12-lead electrocardiogram (ECG). Patients were followed up every 3 months to update their status and the primary end point was all-cause death. Clinical information and ECG characteristics were compared between survival and death groups and Kaplan-Meier curve was used for survival analysis. RESULTS: There were significant differences in age, gender, 6-min walk distance, NT-proBNP, WHO class, presence of fQRS and presence of ST-T change in inferior leads between survival group and death group. Inferior fQRS and ST-T change were significantly associated with right ventricular (RV) dilatation and reduced RV ejection fraction (RVEF). Kaplan-Meier curve showed that all-cause mortality was higher in CTD-PAH with fQRS (p= 0.003) and inferior ST-T change (p= 0.012). Low- and intermediate-risk CTD-PAH with inferior ST-T change had higher all-cause mortality (p= 0.005). The prognostic value of fQRS and inferior ST-T change was validated in external validation cohort. CONCLUSION: The presence of inferior fQRS and ST-T change could predict poor prognosis in CTD-PAH. CLINICAL TRIAL REGISTRATION NUMBER: NCT05980728, https://clinicaltrials.gov.

British Society for Rheumatology guideline on management of adult and juvenile onset Sjögren disease.

Sjögren disease (SD) is a chronic, autoimmune disease of unknown aetiology with significant impact on quality of life. Although dryness (sicca) of the eyes and mouth are the classically described features, dryness of other mucosal surfaces and systemic manifestations are common. The key management aim should be to empower the individual to manage their condition-conserving, replacing and stimulating secretions; and preventing damage and suppressing systemic disease activity. This guideline builds on and widens the recommendations developed for the first guideline published in 2017. We have included advice on the management of children and adolescents where appropriate to provide a comprehensive guideline for UK-based rheumatology teams.

Prospective Assessment of Glucocorticoid Toxicity in Rheumatology Practice: A Focus on the Glucocorticoid Toxicity Index.

OBJECTIVE: The glucocorticoid toxicity index (GTI) is developed to measure glucocorticoid (GC)-related morbidity over time. This study aimed to assess GC-toxicity in patients at a rheumatology outpatient clinic by using the GTI and to identify the factors that interfere with the GTI. METHODS: This prospective study included patients with inflammatory arthritis (IA), connective tissue disease, and vasculitis who were newly prescribed GC-treatment (GC-naive) or have been still on GC-treatment for ≤2 years (GC-experienced). Patient demographics and disease characteristics, aggregate improvement score (GTI-AIS), cumulative worsening score (GTI-CWS), and cumulative GC-doses were recorded at baseline, 3rd month, and 6th month. Generalized estimating equations (GEE) were used to evaluate the GTI scores and associated factors including cumulative GC-doses. RESULTS: The study included 156 (48.7% GC-naive) patients with a mean age of 49.1 ± 17.1 years. More than half of the patients in both groups had a diagnosis of vasculitis. A higher cumulative GC-dose was found to be associated with higher GTI-scores in both groups (p< 0.001). In the GC-naive group, patients with vasculitis showed higher GTI-scores than IA patients (p< 0.001); there was also a significant increase in the GTI-CWS at the 6th month compared with the 3rd month. In the GC-experienced group, GTI-AIS and GTI-CWS were significantly different at 3rd and 6th month (p< 0.05). CONCLUSION: It was shown that GTI scores were associated with cumulative GC-doses and vasculitis patients in the GC-naive patients had higher GTI scores than inflammatory arthritis. The GTI allows individualized assessment and management of adverse effects experienced by patients as a result of GC treatment.

Machine learning-driven immunophenotypic stratification of mixed connective tissue disease corroborating the clinical heterogeneity.

OBJECTIVES: To stratify patients with mixed connective tissue disease (MCTD) based on their immunophenotype. METHODS: We analyzed the immunophenotype and transcriptome of 24 immune cell subsets from patients with MCTD, systemic lupus erythematosus (SLE), idiopathic inflammatory myopathy (IIM), and systemic sclerosis (SSc) from our functional genome database, ImmuNexUT (https://www.immunexut.org/). MCTD patients were stratified by employing machine learning models including Random Forest, trained by immunophenotyping data from SLE, IIM, and SSc patients. Transcriptomes were analyzed with gene set variation analysis (GSVA) and clinical features of MCTD subgroups were compared. RESULTS: This study included 215 patients, including 22 patients with MCTD. Machine learning models, constructed to classify SLE, IIM, and SSc patients based on immunophenotyping, were applied to MCTD patients, resulting in 16 classified as SLE-immunophenotype and 6 as non-SLE-immunophenotype. Among MCTD patients, patients with the SLE-immunophenotype had higher proportions of Th1 cells [2.85% (interquartile range (IQR) 1.54-3.91) vs 1.33% (IQR 0.99-1.74) p= 0.027] and plasmablasts [6.35% (IQR 4.17-17.49) vs 2.00% (IQR 1.20-2.80) p= 0.010]. Notably, the number of SLE-related symptoms was higher in patients with the SLE-immunophenotype [2.0 (IQR 1.0-2.0) vs 1.0 (IQR1.0-1.0) p= 0.038]. Moreover, GSVA scores of interferon-α and -γ responses were significantly higher in patients with the SLE-immunophenotype in central memory CD8+ T cells, while hedgehog signalling was higher in non-SLE-immunophenotype patients in 5 cell subsets. CONCLUSION: This study describes the stratification of MCTD patients based on immunophenotyping, suggesting the presence of distinct immunological processes behind the clinical subtypes of MCTD.

Lymphadenopathy in the rheumatology practice: a pragmatic approach.

Lymphadenopathy is a common clinical finding and diagnostic challenge within general medicine and rheumatology practice. It may represent a primary manifestation of an underlying immune-mediated disease or indicate an infectious or neoplastic complication requiring differing management. Evaluating lymphadenopathy is of particular relevance in rheumatology, given that lymph node enlargement is a common finding within the clinical spectrum of several well-known rheumatologic disorders including RA, SLE and SS. In addition, lymphadenopathy represents a hallmark manifestation of rare immunological diseases such as Castleman disease and IgG4-related disease that must be considered in the differential diagnosis because effective targeted treatments can now impact the prognosis of these conditions. In this review we present an overview of the clinical significance of lymphadenopathy in common and rare rheumatologic diseases and propose a practical approach to lymphadenopathy in the rheumatology practice. Differential diagnosis of Castleman disease and therapeutic options for this condition of increasing rheumatologic interest will be discussed in detail.

Treatment strategies and survival of patients with connective tissue disease and pulmonary arterial hypertension: a COMPERA analysis.

OBJECTIVES: Pulmonary arterial hypertension (PAH) occurs in various connective tissue diseases (CTDs). We sought to assess contemporary treatment patterns and survival of patients with various forms of CTD-PAH. METHODS: We analysed data from COMPERA, a European pulmonary hypertension registry, to describe treatment strategies and survival in patients with newly diagnosed PAH associated with SSc, SLE, MCTD, UCTD and other types of CTD. All-cause mortality was analysed according to the underlying CTD. For patients with SSc-PAH, we also assessed survival according to initial therapy with endothelin receptor antagonists (ERAs), phosphodiesterase type 5 inhibitors (PDE5is) or a combination of these two drug classes. RESULTS: This analysis included 607 patients with CTD-PAH. Survival estimates at 1, 3 and 5 years for SSc-PAH (n = 390) were 85%, 59% and 42%; for SLE-PAH (n = 34) they were 97%, 77% and 61%; for MCTD-PAH (n = 33) they were 97%, 70% and 59%; for UCTD-PAH (n = 60) they were 88%, 67% and 52%; and for other CTD-PAH (n = 90) they were 92%, 69% and 55%, respectively. After multivariable adjustment, the survival of patients with SSc-PAH was significantly worse compared with the other conditions (P = 0.001). In these patients, the survival estimates were significantly better with initial ERA-PDE5i combination therapy than with initial ERA or PDE5i monotherapy (P = 0.016 and P = 0.012, respectively). CONCLUSIONS: Mortality remains high in patients with CTD-PAH, especially for patients with SSc-PAH. However, for patients with SSc-PAH, our results suggest that long-term survival may be improved with initial ERA-PDE5i combination therapy compared with initial monotherapy.

Morphoea presenting histopathologically as mycosis fungoides: an illustrative series of four cases.

AIMS: There have been exceptional reports of morphoea presenting with epidermal changes overlapping histopathologically with cutaneous T cell lymphoma of the mycosis fungoides type (MF). This phenomenon gives rise to an ambiguous clinicopathological scenario in which distinguishing these conditions may be challenging. The aim of this study is to characterise the clinical, histopathological and molecular findings of this phenomenon through a case series. METHODS AND RESULTS: Four patients with classical clinical presentation of morphoea but unusual histopathology displaying typical findings of morphoea, together with intra-epidermal CD8 positive lymphocytes indistinguishable from MF, were identified. The clinical phenotypes of morphoea were varied, and they all presented early in the active phase of the disease. They all exhibited intra-epidermal lymphocytes with tagging and cytological atypia. Pautrier-like microabscesses were also seen. Using molecular analysis, two cases showed clonal TCR gene rearrangement. Follow-up of all cases has been consistent with classical morphoea. CONCLUSION: Early morphoea can seldom present with atypical clonal intra-epidermal lymphocytes indistinguishable from MF. The fact that these changes can occur in several different clinical subtypes of morphoea raises the possibility that this could be a pattern of inflammation in early disease more common than currently appreciated.

An explainable machine learning-based model to predict intensive care unit admission among patients with community-acquired pneumonia and connective tissue disease.

BACKGROUND: There is no individualized prediction model for intensive care unit (ICU) admission on patients with community-acquired pneumonia (CAP) and connective tissue disease (CTD) so far. In this study, we aimed to establish a machine learning-based model for predicting the need for ICU admission among those patients. METHODS: This was a retrospective study on patients admitted into a University Hospital in China between November 2008 and November 2021. Patients were included if they were diagnosed with CAP and CTD during admission and hospitalization. Data related to demographics, CTD types, comorbidities, vital signs and laboratory results during the first 24 h of hospitalization were collected. The baseline variables were screened to identify potential predictors via three methods, including univariate analysis, least absolute shrinkage and selection operator (Lasso) regression and Boruta algorithm. Nine supervised machine learning algorithms were used to build prediction models. We evaluated the performances of differentiation, calibration, and clinical utility of all models to determine the optimal model. The Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) techniques were performed to interpret the optimal model. RESULTS: The included patients were randomly divided into the training set (1070 patients) and the testing set (459 patients) at a ratio of 70:30. The intersection results of three feature selection approaches yielded 16 predictors. The eXtreme gradient boosting (XGBoost) model achieved the highest area under the receiver operating characteristic curve (AUC) (0.941) and accuracy (0.913) among various models. The calibration curve and decision curve analysis (DCA) both suggested that the XGBoost model outperformed other models. The SHAP summary plots illustrated the top 6 features with the greatest importance, including higher N-terminal pro-B-type natriuretic peptide (NT-proBNP) and C-reactive protein (CRP), lower level of CD4 + T cell, lymphocyte and serum sodium, and positive serum (1,3)-ß-D-glucan test (G test). CONCLUSION: We successfully developed, evaluated and explained a machine learning-based model for predicting ICU admission in patients with CAP and CTD. The XGBoost model could be clinical referenced after external validation and improvement.

Emergence of the natural history of Myhre syndrome: 47 patients evaluated in the Massachusetts General Hospital Myhre Syndrome Clinic (2016-2023).

Myhre syndrome is an increasingly diagnosed ultrarare condition caused by recurrent germline autosomal dominant de novo variants in SMAD4. Detailed multispecialty evaluations performed at the Massachusetts General Hospital (MGH) Myhre Syndrome Clinic (2016-2023) and by collaborating specialists have facilitated deep phenotyping, genotyping and natural history analysis. Of 47 patients (four previously reported), most (81%) patients returned to MGH at least once. For patients followed for at least 5 years, symptom progression was observed in all. 55% were female and 9% were older than 18 years at diagnosis. Pathogenic variants in SMAD4 involved protein residues p.Ile500Val (49%), p.Ile500Thr (11%), p.Ile500Leu (2%), and p.Arg496Cys (38%). Individuals with the SMAD4 variant p.Arg496Cys were less likely to have hearing loss, growth restriction, and aortic hypoplasia than the other variant groups. Those with the p.Ile500Thr variant had moderate/severe aortic hypoplasia in three patients (60%), however, the small number (n = 5) prevented statistical comparison with the other variants. Two deaths reported in this cohort involved complex cardiovascular disease and airway stenosis, respectively. We provide a foundation for ongoing natural history studies and emphasize the need for evidence-based guidelines in anticipation of disease-specific therapies.

Clinical characteristics and symptom progression of dermatomyositis subtypes: A retrospective analysis of a prospective database.

BACKGROUND: Disease characteristics of classic dermatomyositis (DM) and clinically amyopathic DM (CADM) are well established, but there exists limited knowledge on the disease progression of these subtypes. OBJECTIVE: The objective of this study was to longitudinally track and characterize classic DM and CADM patients who experience changes in disease presentation. METHODS: We conducted a retrospective review of prospectively collected data on 269 DM patients from a longitudinal database. RESULTS: A total of 51% of the patients had classic DM and 49% had CADM. Forty percent of the classic DM patients became postmyopathic (PmDM). Median Cutaneous Dermatomyositis Disease Area and Severity Index activity (CDASI-A) score was lower in PmDM patients than in classic DM patients (13.0 vs 16.0), but 45% of the PmDM patients had CDASI-A scores > 14. Five percent of the CADM patients developed muscle involvement. Compared with CADM patients, those who developed muscle symptoms had milder skin disease before subtype conversion (median CDASI-A 12.0 vs 16.0) and at subtype conversion (median CDASI-A 9.0 vs 16.0). LIMITATIONS: This was a retrospective study conducted at a single tertiary-care dermatology clinic. CONCLUSIONS: Forty percent of the classic DM patients became PmDM. The majority continue with muscle disease, and many continue to have moderate/severe skin disease. CADM has a low risk of progressing to muscle disease, with the extent of skin disease as a potential predictive factor.

Under the dual effect of inflammation and pulmonary fibrosis, CTD-ILD patients possess a greater susceptibility to VTE.

As an autoimmune disease, the persistent systemic inflammatory response associated with connective tissue disease (CTD) is involved in the development of venous thromboembolism (VTE). However, clinical data showed that the risk of VTE in patients differed between subtypes of CTD, suggesting that different subtypes may have independent mechanisms to promote the development of VTE, but the specific mechanism lacks sufficient research at present. The development of pulmonary fibrosis also contributes to the development of VTE, and therefore, patients with CTD-associated interstitial lung disease (CTD-ILD) may be at higher risk of VTE than patients with CTD alone or patients with ILD alone. In addition, the activation of the coagulation cascade response will drive further progression of the patient's pre-existing pulmonary fibrosis, which will continue to increase the patient's risk of VTE and adversely affect prognosis. Currently, the treatment for CTD-ILD is mainly immunosuppressive and antirheumatic therapy, such as the use of glucocorticoids and janus kinase-inhibitors (JAKis), but, paradoxically, these drugs are also involved in the formation of patients' coagulation tendency, making the clinical treatment of CTD-ILD patients with a higher risk of developing VTE challenging. In this article, we review the potential risk factors and related mechanisms for the development of VTE in CTD-ILD patients to provide a reference for clinical treatment and prevention.

Chronic interstitial lung disease associated with systemic lupus erythematosus: A multicentric study of 89 cases.

BACKGROUND AND OBJECTIVE: Chronic interstitial lung disease (ILD) occurs rarely with systemic lupus erythematosus (SLE) as compared with other connective tissue diseases. This multicentric retrospective study of patients with SLE-ILD from the OrphaLung and French SLE networks during 2005-2020 aimed to describe the characteristics of patients with SLE-ILD and analyse factors associated with prognosis. METHODS: We analysed data for 89 patients with SLE-ILD (82 women, 92.1%) (median age at SLE diagnosis: 35 years [interquartile range 27-47]). All patients met the 2019 EULAR/ACR criteria for the diagnosis of SLE. RESULTS: Forty two (47.2%) patients were positive for anti-ribonuclear protein antibodies and 45 (50.6%) for anti SSA/Ro antibodies. A total of 58 (65.2%) patients had another connective tissue disease: Sjögren's syndrome (n = 33, 37.1%), systemic sclerosis (n = 14, 15.7%), inflammatory myopathy (n = 6, 6.7%), or rheumatoid arthritis (n = 6, 6.7%). ILD was diagnosed along with SLE in 25 (28.1%) patients and at a median of 6 (0-14) years after the SLE diagnosis. The most frequent CT pattern was suggestive of non-specific interstitial pneumonia (n = 41, 46.0%) with or without superimposed organizing pneumonia. After a median follow-up of 86.5 [39.5-161.2] months, 18 (20.2%) patients had died and 6 (6.7%) underwent lung transplantation. The median 5-year and 10-year transplantation-free survival were 96% (92-100) and 87% (78-97). In total, 44 (49.4%) patients showed ILD progression. Cutaneous manifestations and Raynaud's phenomenon were associated with better survival. Only forced vital capacity was significantly associated with survival and ILD progression. CONCLUSION: ILD is a rare manifestation of SLE with good overall prognosis but with possible risk of ILD progression. Patients with SLE-ILD frequently have another connective tissue disease.

Identification of Idiopathic Pulmonary Fibrosis and Prediction of Disease Severity via Machine Learning Analysis of Comprehensive Metabolic Panel and Complete Blood Count Data.

BACKGROUND: Diagnosis of idiopathic pulmonary fibrosis (IPF) typically relies on high-resolution computed tomography imaging (HRCT) or histopathology, while monitoring disease severity is done via frequent pulmonary function testing (PFT). More reliable and convenient methods of diagnosing fibrotic interstitial lung disease (ILD) type and monitoring severity would allow for early identification and enhance current therapeutic interventions. This study tested the hypothesis that a machine learning (ML) ensemble analysis of comprehensive metabolic panel (CMP) and complete blood count (CBC) data can accurately distinguish IPF from connective tissue disease ILD (CTD-ILD) and predict disease severity as seen with PFT. METHODS: Outpatient data with diagnosis of IPF or CTD-ILD (n = 103 visits by 53 patients) were analyzed via ML methodology to evaluate (1) IPF vs CTD-ILD diagnosis; (2) %predicted Diffusing Capacity of Lung for Carbon Monoxide (DLCO) moderate or mild vs severe; (3) %predicted Forced Vital Capacity (FVC) moderate or mild vs severe; and (4) %predicted FVC mild vs moderate or severe. RESULTS: ML methodology identified IPF from CTD-ILD with AUCTEST = 0.893, while PFT was classified as DLCO moderate or mild vs severe with AUCTEST = 0.749, FVC moderate or mild vs severe with AUCTEST = 0.741, and FVC mild vs moderate or severe with AUCTEST = 0.739. Key features included albumin, alanine transaminase, %lymphocytes, hemoglobin, %eosinophils, white blood cell count, %monocytes, and %neutrophils. CONCLUSION: Analysis of CMP and CBC data via proposed ML methodology offers the potential to distinguish IPF from CTD-ILD and predict severity on associated PFT with accuracy that meets or exceeds current clinical practice.