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)-β-D-glucan test (G test).
CONCLUSIONS: 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.

Connective tissue diseases are a heterogeneous group of autoimmune diseases that can affect a variety of organ systems. Lung parenchymal involvement is an important contributor to morbidity and mortality in children with connective tissue disease. Connective tissue disease-associated lung disease in children often manifests as one of several radiologic-pathologic patterns of disease, with certain patterns having a propensity to occur in association with certain connective tissue diseases. In this article, key clinical, histopathologic, and computed tomography (CT) features of typical patterns of connective tissue disease-associated lung disease in children are reviewed, with an emphasis on radiologic-pathologic correlation, to improve recognition of these patterns of lung disease at CT and to empower the pediatric radiologist to more fully contribute to the care of pediatric patients with these conditions.

UNASSIGNED: The purpose of this systematic review is to disclose the impact of autoimmune diseases and their medical treatment on dental implant survival and success.
UNASSIGNED: A literature search was conducted using MEDLINE (PubMed), The Cochrane Library and Embase up to December 6th, 2021. Any clinical study on patients with an autoimmune disease in whom implant therapy was performed was eligible. The quality of included studies was assessed using the Newcastle-Ottawa Scale. For each autoimmune disease group, data synthesis was divided into three groups: 1) overall results of the autoimmune disease, 2) overall results of corresponding control groups and 3) overall results of the autoimmune disease with a concomitant autoimmune disease (a subgroup of group 1). Descriptive statistics were used.
UNASSIGNED: Of 4,865 identified articles, 67 could be included and mainly comprising case reports and retrospective studies with an overall low quality. Implant survival rate was 50 to 100% on patient and implant level after a weighted mean follow-up of 17.7 to 68.1 months. Implant success was sporadically reported. Data on immunosuppressive medication were too heterogeneously reported to allow detailed analysis.
UNASSIGNED: Overall, a high implant survival rate was reported in patients with autoimmune diseases. However, the identified studies were characterized by a low quality. No conclusions could be made regarding implant success and the effect of immunosuppressants due to heterogeneous reporting.

OBJECTIVE: Clinical observation suggests that vascular activation and autoimmunity precede remodelling of the extracellular matrix (ECM) in systemic sclerosis (SSc). We challenge this paradigm by hypothesising that ECM biomarkers are already disturbed in patients with very early SSc (veSSc) when fibrosis is not yet clinically detectable.
METHODS: 42 patients with veSSc, defined as the presence of Raynaud\'s phenomenon and at least one of puffy fingers, positive antinuclear antibodies or pathological nailfold capillaroscopy, not meeting the 2013 American College of Rheumatology/European Alliance of Associations for Rheumatology classification criteria for SSc, were compared with healthy controls (HCs, n=29). ECM degradation (BGM, C3M, C4M and C6M) and ECM formation biomarkers (PRO-C3, PRO-C4 and PRO-C5) were measured in serum using ELISAs. A cross-sectional analysis at baseline and a longitudinal analysis was performed.
RESULTS: Compared with HC, veSSc patients showed a strongly dysregulated turnover of type III and IV collagens (higher C3M, C4M, both p<0.0001 and PRO-C3, p=0.004, lower turnover ratios PRO-C3/C3M and PRO-C4/C4M, both p<0.0001). The biglycan degradation biomarker BGM was higher in veSSc than in HC (p=0.006), whereas the degradation biomarker for type VI collagen, C6M, was lower (p=0.002). In an ROC analysis, biomarkers of type III and IV collagen excellently distinguished between veSSc and HC: C3M, AUC=0.95, p<0.0001; C4M, AUC=0.97, p<0.0001; turnover ratios PRO-C3/C3M, AUC=0.80, p<0.0001; PRO-C4/C4M, AUC=0.97; p<0.0001.
CONCLUSIONS: These findings indicate ECM remodelling as a very early phenomenon of SSc occurring in parallel with microvascular and autoimmune changes. Biomarkers of type III and IV collagens distinguished between veSSc patients and HC, indicating them as potential biomarkers for the detection of veSSc.

BACKGROUND: Classification criteria aim to identify a homogenous population of patients for research. We aimed to quantify how well phase-III trials in connective tissue diseases (CTDs) represent a real-world cohort.
METHODS: A comprehensive review of all major published phase-III trials in CTDs was performed (clinicaltrials.gov). Classification criteria utilised most commonly in clinical trials were applied to a multicentre unselected CTD cohort.
RESULTS: There were 42 CTD trials identified, with no trials in mixed (MCTD) or undifferentiated CTD (UCTD). The majority of trials (N = 38, 90 %) required patients to meet classification criteria for their respective disease. Eight (19.0 %) excluded patients with overlapping CTDs and a further two (4.8 %) excluded specific overlapping features, such as pulmonary arterial hypertension. One study explicitly allowed overlap syndromes. Our real-world CTD cohort included 391 patients. Patients with UCTD or MCTD (91/391, 23.3 %) would be excluded from participation in clinical trials for not having an eligible diagnosis. Of patients with primary Sjögren\'s syndrome (pSS), SLE, systemic sclerosis (SSc) or idiopathic inflammatory myopathy (IIM), 211/300 (70.3 %) met the classification criteria for their respective diagnosis and 24/211 (11.4 %) met criteria for >1 CTD. In total, 187/391 (47.8 %) would be eligible for recruitment, based upon their physician diagnosis, and most stringent trial eligibility criteria.
CONCLUSIONS: In an unselected, real-world CTD cohort, up to half of patients are ineligible for clinical trials due to not meeting classification criteria, overlapping features or a lack of trials within their primary disease. To address this inequality in access to novel therapies, clinical trial design should evolve eligibility criteria in CTDs.

BACKGROUND: Patients with rheumatoid arthritis (RA) are at risk of developing interstitial lung disease (ILD), which is associated with high mortality. Screening tools based on risk factors are needed to decide which patients with RA should be screened for ILD using high-resolution computed tomography (HRCT). The ANCHOR-RA study is a multi-national cross-sectional study that will develop a multivariable model for prediction of RA-ILD, which can be used to inform screening for RA-ILD in clinical practice.
METHODS: Investigators will enrol consecutive patients with RA who have ≥ 2 of the following risk factors for RA-ILD: male; current or previous smoker; age ≥ 60 years at RA diagnosis; high-positive rheumatoid factor and/or anti-cyclic citrullinated peptide (titre > 3 x upper limit of normal); presence or history of certain extra-articular manifestations of RA (vasculitis, Felty\'s syndrome, secondary Sjögren\'s syndrome, cutaneous rheumatoid nodules, serositis, and/or scleritis/uveitis); high RA disease activity in the prior 12 months. Patients previously identified as having ILD, or who have had a CT scan in the prior 2 years, will not be eligible. Participants will undergo an HRCT scan at their local site, which will be assessed centrally by two expert radiologists. Data will be collected prospectively on demographic and RA-related characteristics, patient-reported outcomes, comorbidities and pulmonary function. The primary outcomes will be the development of a probability score for RA-ILD, based on a multivariable model incorporating potential risk factors commonly assessed in clinical practice, and an estimate of the prevalence of RA-ILD in the study population. It is planned that 1200 participants will be enrolled at approximately 30 sites in the USA, UK, Germany, France, Italy, Spain.
CONCLUSIONS: Data from the ANCHOR-RA study will add to the body of evidence to support recommendations for screening for RA-ILD to improve detection of this important complication of RA and enable early intervention.
BACKGROUND: clinicaltrials.gov NCT05855109 (submission date: 3 May 2023).

Nontuberculous mycobacteria (NTM) are environmental and ubiquitous, but only a few species are associated with disease, often presented as nodular/bronchiectatic or cavitary pulmonary forms. Bronchiectasis, airways dilatations characterized by chronic productive cough, is the main presentation of NTM pulmonary disease. The current Cole\'s vicious circle model for bronchiectasis proposes that it progresses from a damaging insult, such as pneumonia, that affects the respiratory epithelium and compromises mucociliary clearance mechanisms, allowing microorganisms to colonize the airways. An important bronchiectasis risk factor is primary ciliary dyskinesia, but other ciliopathies, such as those associated with connective tissue diseases, also seem to facilitate bronchiectasis, as may occur in Lady Windermere syndrome, caused by M. avium infection. Inhaled NTM may become part of the lung microbiome. If the dose is too large, they may grow excessively as a biofilm and lead to disease. The incidence of NTM pulmonary disease has increased in the last two decades, which may have influenced the parallel increase in bronchiectasis incidence. We propose that ciliary dyskinesia is the main promoter of bronchiectasis, and that the bacteria most frequently involved are NTM. Restoration of ciliary function and impairment of mycobacterial biofilm formation may provide effective therapeutic alternatives to antibiotics.

OBJECTIVE: Undifferentiated connective tissue diseases (UCTDs) are systemic autoimmune conditions that cannot be diagnosed nor classified as defined CTD; the majority maintains an undifferentiated profile (stable UCTD, sUCTD) over time. Data on long-term outcomes of sUCTD are lacking.
METHODS: Retrospective longitudinal analysis of an inception cohort of 141 patients with sUCTD.Disease evolution and damage accrual were evaluated at 1, 5 and 10 years. Partial least square (PLS) regression was used to identify the basal variables contributing to damage accrual at 1, 5 and 10 years of follow-up. Trend of damage over time was compared with a cohort of age-matched and sex-matched patients with systemic lupus erythematosus (SLE) by means of Nelson-Aalen analysis.
RESULTS: 11.3% of patients evolved to a definite CTD after a median 11 years (IQR 6-25) from the first symptom. At last visit, 10% were on glucocorticoids and 6% on immunosuppressive therapy. In 27.3%, at least one item of organ damage was recorded according to the SLICC/DI score (mean score 1.19±0.46). At PLS analysis, age at diagnosis and age at first symptoms were related to damage at 1 year, not taking antimalarials and taking immunosuppressants were associated with damage at 5 years.The mean survival without damage was 9.3 years in sUCTD and 8.4 years in SLE. The 10-year probability without damage was 62% and 23% in SLE and sUCTD, respectively (p=0.015).
CONCLUSIONS: Although less significantly impacted than in patients with SLE, in the long-term UCTDs can accumulate organ damage and evolve into defined connective tissue diseases.

OBJECTIVE: To investigate pregnancy outcomes in women with autoimmune rheumatic diseases (ARD) in the Italian prospective cohort study P-RHEUM.it.
METHODS: Pregnant women with different ARD were enrolled for up to 20 gestational weeks in 29 Rheumatology Centres for 5 years (2018-2023). Maternal and infant information were collected in a web-based database.
RESULTS: We analysed 866 pregnancies in 851 patients (systemic lupus erythematosus was the most represented disease, 19.6%). Maternal disease flares were observed in 135 (15.6%) pregnancies. 53 (6.1%) pregnancies were induced by assisted reproduction techniques, 61 (7%) ended in miscarriage and 11 (1.3%) underwent elective termination. Obstetrical complications occurred in 261 (30.1%) pregnancies, including 2.3% pre-eclampsia. Two cases of congenital heart block were observed out of 157 pregnancies (1.3%) with anti-Ro/SSA. Regarding treatments, 244 (28.2%) pregnancies were treated with glucocorticoids, 388 (44.8%) with hydroxychloroquine, 85 (9.8%) with conventional synthetic disease-modifying anti-rheumatic drugs and 122 (14.1%) with biological disease-modifying anti-rheumatic drugs. Live births were 794 (91.7%), mostly at term (84.9%); four perinatal deaths (0.5%) occurred. Among 790 newborns, 31 (3.9%) were small-for-gestational-age and 169 (21.4%) had perinatal complications. Exclusive maternal breast feeding was received by 404 (46.7%) neonates. The Edinburgh Postnatal Depression Scale was compiled by 414 women (52.4%); 89 (21.5%) scored positive for emotional distress.
CONCLUSIONS: Multiple factors including preconception counselling and treat-to-target with pregnancy-compatible medications may have contributed to mitigate disease-related risk factors, yielding limited disease flares, good pregnancy outcomes and frequency of complications which were similar to the Italian general obstetric population. Disease-specific issues need to be further addressed to plan preventative measures.

Interstitial lung disease (ILD) can lead to lung cancer, which brings great challenges to differential diagnosis and comprehensive treatment. However, the clinical features of lung-dominant connective tissue disease (LD-CTD) related ILD combined with lung cancer has not been validated. We report the case of an 80-year-old woman with LD-CTD treated regularly with nintedanib who presented progressive dyspnoea and hypoxemia after recurrent viral infections. Her chest computed tomography (CT) showed aggravated interstitial fibrosis in both lower lungs with moderate right pleural effusion. Clinicians should be alert to lung cancer in patients who are experiencing poor responsiveness to treatment or acute progression of ILD. The available literatures about the differential diagnosis of clinical manifestations, imaging, treatment and prognosis of LD-CTD are reviewed and discussed in this study.