Association between Routine Laboratory Parameters and the Severity and Progression of Systemic Sclerosis

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)-β-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.

Association of serum uric acid with right cardiac chamber remodeling assessed by cardiovascular magnetic resonance feature tracking in patients with connective tissue disease

Background

Right cardiac chamber remodeling is widespread in patients with connective tissue disease (CTD). Serum uric acid (SUA) is considered a potential independent risk factor for cardiovascular disease, and elevated SUA levels are often observed in patients with CTD. The correlation between SUA levels and right cardiac chamber remodeling remains unclear. This study investigated the association of SUA with right cardiac chamber remodeling as assessed by cardiac magnetic resonance feature-tracking (CMR-FT) in CTD patients.

Methods and results

In this cross-sectional study, a total of 104 CTD patients and 52 age- and sex-matched controls were consecutively recruited. All individuals underwent CMR imaging, and their SUA levels were recorded. The patients were divided into three subgroups based on the tertiles of SUA level in the present study. CMR-FT was used to evaluate the right atrial (RA) longitudinal strain and strain rate parameters as well as right ventricular (RV) global systolic peak strain and strain rate in longitudinal and circumferential directions for each subject. Univariable and multivariable linear regression analyses were used to explore the association of SUA with RV and RA strain parameters. Compared with the controls, the CTD patients showed significantly higher SUA levels but a lower RV global circumferential strain (GCS) and RA phasic strain parameters (all p < 0.05), except the RA booster strain rate. RV GCS remained impaired even in CTD patients with preserved RV ejection fraction. Among subgroups, the patients in the third tertile had significantly impaired RV longitudinal strain (GLS), RV GCS, and RA reservoir and conduit strain compared with those in the first tertile (all p < 0.05). The SUA levels were negatively correlated with RV GLS and RV GCS as well as with RA reservoir and conduit strain and strain rates (the absolute values of β were 0.250 to 0.293, all P < 0.05). In the multivariable linear regression analysis, the SUA level was still an independent determinant of RA conduit strain (β = -0.212, P = 0.035) and RV GCS (β = 0.207, P = 0.019).

Conclusion

SUA may be a potential risk factor of right cardiac chamber remodeling and is independently associated with impaired RA conduit strain and RV GCS in CTD patients.

Serum C-reactive protein is associated with earlier mortality across different interstitial lung diseases

BACKGROUND AND OBJECTIVE

The acute-phase protein C-reactive protein (CRP) is known to be associated with poor outcomes in cancer and cardiovascular disease, but there is limited evidence of its prognostic implications in interstitial lung diseases (ILDs). We therefore set out to test whether baseline serum CRP levels are associated with mortality in four different ILDs.

METHODS

In this retrospective study, clinically measured CRP levels, as well as baseline demographics and lung function measures, were collected for ILD patients first presenting to the Royal Brompton Hospital between January 2010 and December 2019. Cox regression analysis was used to determine the relationship with 5-year mortality.

RESULTS

Patients included in the study were: idiopathic pulmonary fibrosis (IPF) n = 422, fibrotic hypersensitivity pneumonitis (fHP) n = 233, rheumatoid arthritis associated ILD (RA-ILD) n = 111 and Systemic Sclerosis associated ILD (SSc-ILD) n = 86. Patients with a recent history of infection were excluded. Higher CRP levels were associated with shorter 5-year survival in all four disease groups on both univariable analyses, and after adjusting for age, gender, smoking history, immunosuppressive therapy and baseline disease severity (IPF: HR (95% CI): 1.3 (1.1-1.5), p = 0.003, fHP: 1.5 (1.2-1.9), p = 0.001, RA-ILD: 1.4 (1.1-1.84), p = 0.01 and SSc-ILD: 2.7 (1.6-4.5), p < 0.001).

CONCLUSION

Higher CRP levels are independently associated with reduced 5-year survival in IPF, fHP, RA-ILD and SSc-ILD.

Heterogeneity of determining disease severity, clinical course and outcomes in systemic sclerosis-associated interstitial lung disease: a systematic literature review

Objective The course of systemic sclerosis-associated interstitial lung disease (SSc-ILD) is highly variable and different from continuously progressive idiopathic pulmonary fibrosis (IPF). Most proposed definitions of progressive pulmonary fibrosis or SSc-ILD severity are based on the research data from patients with IPF and are not validated for patients with SSc-ILD. Our study aimed to gather the current evidence for severity, progression and outcomes of SSc-ILD.Methods A systematic literature review to search for definitions of severity, progression and outcomes recorded for SSc-ILD was performed according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines in Medline, Embase, Web of Science and Cochrane Library up to 1 August 2023.Results A total of 9054 papers were reviewed and 342 were finally included. The most frequent tools used for the definition of SSc-ILD progression and severity were combined changes of carbon monoxide diffusing capacity (DLCO) and forced vital capacity (FVC), isolated FVC or DLCO changes, high-resolution CT (HRCT) extension and composite algorithms including pulmonary function test, clinical signs and HRCT data. Mortality was the most frequently reported long-term event, both from all causes or ILD related.Conclusions The studies presenting definitions of SSc-ILD 'progression', 'severity' and 'outcome' show a large heterogeneity. These results emphasise the need for developing a standardised, consensus definition of severe SSc-ILD, to link a disease specific definition of progression as a surrogate outcome for clinical trials and clinical practice.PROSPERO registration number CRD42022379254.Cite Now.

Biomarkers in the Pathogenesis, Diagnosis, and Treatment of Systemic Sclerosis

Systemic sclerosis (SSc) is a complex autoimmune disease characterized by vascular damage, vasoinstability, and decreased perfusion with ischemia, inflammation, and exuberant fibrosis of the skin and internal organs. Biomarkers are analytic indicators of the biological and disease processes within an individual that can be accurately and reproducibly measured. The field of biomarkers in SSc is complex as recent studies have implicated at least 240 pathways and dysregulated proteins in SSc pathogenesis. Anti-nuclear antibodies (ANA) are classical biomarkers with well-described clinical classifications and are present in more than 90% of SSc patients and include anti-centromere, anti-Th/To, anti-RNA polymerase III, and anti-topoisomerase I antibodies. Transforming growth factor-β (TGF-β) is central to the fibrotic process of SSc and is intimately intertwined with other biomarkers. Tyrosine kinases, interferon-1 signaling, IL-6 signaling, endogenous thrombin, peroxisome proliferator-activated receptors (PPARs), lysophosphatidic acid receptors, and amino acid metabolites are new biomarkers with the potential for developing new therapeutic agents. Other biomarkers implicated in SSc-ILD include signal transducer and activator of transcription 4 (STAT4), CD226 (DNAX accessory molecule 1), interferon regulatory factor 5 (IRF5), interleukin-1 receptor-associated kinase-1 (IRAK1), connective tissue growth factor (CTGF), pyrin domain containing 1 (NLRP1), T-cell surface glycoprotein zeta chain (CD3ζ) or CD247, the NLR family, SP-D (surfactant protein), KL-6, leucine-rich α2-glycoprotein-1 (LRG1), CCL19, genetic factors including DRB1 alleles, the interleukins (IL-1, IL-4, IL-6, IL-8, IL-10 IL-13, IL-16, IL-17, IL-18, IL-22, IL-32, and IL-35), the chemokines CCL (2,3,5,13,20,21,23), CXC (8,9,10,11,16), CX3CL1 (fractalkine), and GDF15. Adiponectin (an indicator of PPAR activation) and maresin 1 are reduced in SSc patients. A new trend has been the use of biomarker panels with combined complex multifactor analysis, machine learning, and artificial intelligence to determine disease activity and response to therapy. The present review is an update of the various biomarker molecules, pathways, and receptors involved in the pathology of SSc.

Biomarkers in Systemic Sclerosis: An Overview

Systemic sclerosis (SSc) is a complex autoimmune disease characterized by significant fibrosis of the skin and internal organs, with the main involvement of the lungs, kidneys, heart, esophagus, and intestines. SSc is also characterized by macro- and microvascular damage with reduced peripheral blood perfusion. Several studies have reported more than 240 pathways and numerous dysregulation proteins, giving insight into how the field of biomarkers in SSc is still extremely complex and evolving. Antinuclear antibodies (ANA) are present in more than 90% of SSc patients, and anti-centromere and anti-topoisomerase I antibodies are considered classic biomarkers with precise clinical features. Recent studies have reported that trans-forming growth factor β (TGF-β) plays a central role in the fibrotic process. In addition, interferon regulatory factor 5 (IRF5), interleukin receptor-associated kinase-1 (IRAK-1), connective tissue growth factor (CTGF), transducer and activator of transcription signal 4 (STAT4), pyrin-containing domain 1 (NLRP1), as well as genetic factors, including DRB1 alleles, are implicated in SSc damage. Several interleukins (e.g., IL-1, IL-6, IL-10, IL-17, IL-22, and IL-35) and chemokines (e.g., CCL 2, 5, 23, and CXC 9, 10, 16) are elevated in SSc. While adiponectin and maresin 1 are reduced in patients with SSc, biomarkers are important in research but will be increasingly so in the diagnosis and therapeutic approach to SSc. This review aims to present and highlight the various biomarker molecules, pathways, and receptors involved in the pathology of SSc.

Enhanced Innate and Acquired Immune Responses in Systemic Sclerosis Primary Peripheral Blood Mononuclear Cells (PBMCs)

Chronic immune activation in systemic sclerosis is supported by the production of a plethora of cytokines with proven regulatory activities of the immune responses. This study aimed to explore PBMCs' cytokine profiles in SSc patients versus controls, as well as to investigate the balance between pro- and anti-inflammatory cytokines in association with disease duration. PBMCs were isolated from 18 SSc patients and 17 controls and further subjected to in vitro stimulation with lipopolysaccharide and heat-killed Candida albicans. Cytokine production was measured after 24 h and 7 days, respectively, using ELISA kits for interleukin (IL)-1β, IL-1 receptor antagonist (IL-1Ra), IL-6, tumor necrosis factor (TNF), IL-10, IL-17, and interferon-gamma (IFN-gamma). IL-1 β, IL-6, and TNF levels were increased in SSc patients compared with healthy volunteers irrespective of the stimulus used. IL-1Ra and Il-17 concentrations were not statistically different between groups, even though a trend toward higher levels in patients compared with their matched controls was also observed. Most cytokines demonstrated a stable course with disease progression, except for IL-10 levels, which declined over time. In conclusion, the results of this pilot study reveal that in patients with SSc a persistently enhanced immune response is established and maintained regardless of stimulus or disease duration.

Scleroderma pulmonary arterial hypertension: the same as idiopathic pulmonary arterial hypertension?

PURPOSE OF REVIEW

Pulmonary arterial hypertension (PAH) is a common complication of systemic sclerosis (SSc), which confers significant morbidity and mortality. The current therapies and treatment strategies for SSc-associated PAH (SSc-PAH) are informed by those used to treat patients with idiopathic PAH (IPAH). There are, however, important differences between these two diseases that impact diagnosis, treatment, and outcomes.

RECENT FINDINGS

Both SSc-PAH and IPAH are incompletely understood with ongoing research into the underlying cellular biology that characterize and differentiate the two diseases. Additional research seeks to improve identification among SSc patients in order to diagnose patients earlier in the course of their disease. Novel therapies specifically for SSc-PAH such as rituximab and dimethyl fumarate are under investigation.

SUMMARY

Although patients with SSc-PAH and IPAH present with similar symptoms, there are significant differences between these two forms of PAH that warrant further investigation and characterization of optimal detection strategies, treatment algorithms, and outcomes assessment.

Antibody-mediated neutralization of galectin-3 as a strategy for the treatment of systemic sclerosis

Systemic sclerosis (SSc) is an autoimmune, inflammatory and fibrotic disease with limited treatment options. Developing new therapies is therefore crucial to address patient needs. To this end, we focused on galectin-3 (Gal-3), a lectin known to be associated with several pathological processes seen in SSc. Using RNA sequencing of whole-blood samples in a cross-sectional cohort of 249 patients with SSc, Gal-3 and its interactants defined a strong transcriptomic fingerprint associated with disease severity, pulmonary and cardiac malfunctions, neutrophilia and lymphopenia. We developed new Gal-3 neutralizing monoclonal antibodies (mAb), which were then evaluated in a mouse model of hypochlorous acid (HOCl)-induced SSc. We show that two of these antibodies, D11 and E07, reduced pathological skin thickening, lung and skin collagen deposition, pulmonary macrophage content, and plasma interleukin-5 and -6 levels. Moreover, E07 changed the transcriptional profiles of HOCl-treated mice, resulting in a gene expression pattern that resembled that of control mice. Similarly, pathological pathways engaged in patients with SSc were counteracted by E07 in mice. Collectively, these findings demonstrate the translational potential of Gal-3 blockade as a therapeutic option for SSc.

Identification of lncRNA-miRNA-mRNA networks in circulating exosomes as potential biomarkers for systemic sclerosis

Objective

This study aimed to analyze potential biomarkers for systemic sclerosis (SSc) by constructing lncRNA-miRNA-mRNA networks in circulating exosomes (cirexos).

Materials and methods

Differentially expressed mRNAs (DEmRNAs) and lncRNAs (DElncRNAs) in SSc cirexos were screened using high-throughput sequencing and detected with real-time quantitative PCR (RT-qPCR). Differentially expressed genes (DEGs) were analyzed using the DisGeNET, GeneCards, GSEA4.2.3, Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) databases. Receiver operating characteristic (ROC) curves, correlation analyses, and a double-luciferase reporter gene detection assay were used to analyze competing endogenous RNA (ceRNA) networks and clinical data.

Results

In this study, 286 DEmRNAs and 192 DElncRNAs were screened, of which 18 DEGs were the same as the SSc-related genes. The main SSc-related pathways included extracellular matrix (ECM) receptor interaction, local adhesion, platelet activation, and IgA production by the intestinal immune network. A hub gene, COL1A1, was obtained by a protein-protein interaction (PPI) network. Four ceRNA networks were predicted through Cytoscape. The relative expression levels of COL1A1, ENST0000313807, and NON-HSAT194388.1 were significantly higher in SSc, while the relative expression levels of hsa-miR-29a-3p, hsa-miR-29b-3p, and hsa-miR-29c-3p were significantly lower in SSc (P < 0.05). The ROC curve showed that the ENST00000313807-hsa-miR-29a-3p-COL1A1 network as a combined biomarker of SSc is more valuable than independent diagnosis, and that it is correlated with high-resolution CT (HRCT), Scl-70, C-reactive protein (CRP), Ro-52, IL-10, IgM, lymphocyte percentage, neutrophil percentage, albumin divided by globulin, urea, and RDW-SD (P < 0.05). Double-luciferase reporter gene detection showed that ENST00000313807 interacts with hsa-miR-29a-3p, which interacts with COL1A1.

Conclusion

The ENST00000313807-hsa-miR-29a-3p-COL1A1 network in plasma cirexos represents a potential combined biomarker for the clinical diagnosis and treatment of SSc.

ABO Blood Groups in Systemic Sclerosis: Distribution and Association with This Disease's Characteristics

Systemic sclerosis (SSc) is an autoimmune disease associated with endothelial activation and fibrosis. Non-O blood group patients carry an increased risk of thrombosis, fibrosis and autoimmune diseases. The aim of our work was to evaluate the distribution of ABO groups in SSc patients and their association with the disease's characteristics. ABO groups were determined in 504 SSc patients (with 131 completed by a genotypic analysis). The distribution of ABO groups and their diplotypes in SSc patients was comparable to that of the general population, except for haplotypes O1 and B (65.6% vs. 61.6% and 8.8% vs. 5.8% in SSc patients vs. the general population, respectively, p = 0.01). The frequency of interstitial lung disease, pulmonary hypertension, calcinosis, digital ulcers, digestive diseases and venous thrombosis, and the Medsger score, were higher in non-O than in O-SSc patients, although they did not display statistical significance. Patients in the non-O group had higher levels of inflammation and endothelial activation biomarkers. In conclusion, the ABO blood group distribution of SSc patients did not differ significantly from that of the general population, but non-O blood groups were associated with inflammation and endothelial activation, and with a non-significant higher frequency of pulmonary and vascular complications in SSc.