Identifying early pulmonary arterial hypertension biomarkers in systemic sclerosis: machine learning on proteomics from the DETECT cohort

Collagen 18A1/Endostatin Expression in the Progression of Right Ventricular Remodeling and Dysfunction in Pulmonary Arterial Hypertension

Numerous studies have demonstrated that endostatin (ES), a potent angiostatic peptide derived from collagen type XVIII α 1 chain and encoded by COL18A1, is elevated in pulmonary arterial hypertension (PAH). It is important to note that elevated ES has consistently been associated with altered hemodynamics, poor functional status, and adverse outcomes in adult and pediatric PAH. This study used serum samples from patients with Group I PAH and plasma and tissue samples derived from the Sugen/hypoxia rat pulmonary hypertension model to define associations between COL18A1/ES and disease development, including hemodynamics, right ventricle (RV) remodeling, and RV dysfunction. Using cardiac magnetic resonance imaging and advanced hemodynamic assessments with pressure-volume loops in patients with PAH to assess RV-pulmonary arterial coupling, we observed a strong relationship between circulating ES levels and metrics of RV structure and function. Specifically, RV mass and the ventricular mass index were positively associated with ES, whereas RV ejection fraction and RV-pulmonary arterial coupling were inversely associated with ES levels. Our animal data demonstrate that the development of pulmonary hypertension is associated with increased COL18A1/ES in the heart as well as the lungs. Disease-associated increases in COL18A1 mRNA and protein were most pronounced in the RV compared with the left ventricle and lung. COL18A1 expression in the RV was strongly associated with disease-associated changes in RV mass, fibrosis, and myocardial capillary density. These findings indicate that COL18A1/ES increases early in disease development in the RV and implicates COL18A1/ES in pathologic RV dysfunction in PAH.

Assessing the precision of machine learning for diagnosing pulmonary arterial hypertension: a systematic review and meta-analysis of diagnostic accuracy studies

Introduction

Pulmonary arterial hypertension (PAH) is a severe cardiovascular condition characterized by pulmonary vascular remodeling, increased resistance to blood flow, and eventual right heart failure. Right heart catheterization (RHC) is the gold standard diagnostic technique, but due to its invasiveness, it poses risks such as vessel and valve injury. In recent years, machine learning (ML) technologies have offered non-invasive alternatives combined with ML for improving the diagnosis of PAH.

Objectives

The study aimed to evaluate the diagnostic performance of various methods, such as electrocardiography (ECG), echocardiography, blood biomarkers, microRNA, chest x-ray, clinical codes, computed tomography (CT) scan, and magnetic resonance imaging (MRI), combined with ML in diagnosing PAH.

Methods

The outcomes of interest included sensitivity, specificity, area under the curve (AUC), positive likelihood ratio (PLR), negative likelihood ratio (NLR), and diagnostic odds ratio (DOR). This study employed the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool for quality appraisal and STATA V.12.0 for the meta-analysis.

Results

A comprehensive search across six databases resulted in 26 articles for examination. Twelve articles were categorized as low-risk, nine as moderate-risk, and five as high-risk. The overall diagnostic performance analysis demonstrated significant findings, with sensitivity at 81% (95% CI = 0.76-0.85, p < 0.001), specificity at 84% (95% CI = 0.77-0.88, p < 0.001), and an AUC of 89% (95% CI = 0.85-0.91). In the subgroup analysis, echocardiography displayed outstanding results, with a sensitivity value of 83% (95% CI = 0.72-0.91), specificity value of 93% (95% CI = 0.89-0.96), PLR value of 12.4 (95% CI = 6.8-22.9), and DOR value of 70 (95% CI = 23-231). ECG demonstrated excellent accuracy performance, with a sensitivity of 82% (95% CI = 0.80-0.84) and a specificity of 82% (95% CI = 0.78-0.84). Moreover, blood biomarkers exhibited the highest NLR value of 0.50 (95% CI = 0.42-0.59).

Conclusion

The implementation of echocardiography and ECG with ML for diagnosing PAH presents a promising alternative to RHC. This approach shows potential, as it achieves excellent diagnostic parameters, offering hope for more accessible and less invasive diagnostic methods.

Systematic Review Registration

PROSPERO (CRD42024496569).

Prediction of prognosis in patients with systemic sclerosis based on a machine-learning model

OBJECTIVE

The clinical manifestations of systemic sclerosis (SSc) are highly variable, resulting in varied outcomes and complications. Diverse fibrosis of the skin and internal organs, vasculopathy, and dysregulated immune system lead to poor and varied prognoses in patients with SSc subtypes. Therefore, this study aimed to develop a personalized tool for predicting the prognosis of patients with SSc.

METHODS

A cohort of 517 patients with SSc were recruited between January 2009 and November 2021 at Xijing Hospital in China, and 266 patients completed the follow-up and performed in the survival analysis. Risk factors for death were identified using Cox survival analysis and random survival forest-based machine-learning methods separately. The consistency index, area under the curve (AUC), and integrated Brier scores were used to compare the predictive performance of the different prognostic models.

RESULTS

The results of Cox-based multivariate regression analysis suggested that pulmonary arterial hypertension, digital ulcer, and Modified Rodnan Skin Score (mRSS) were independent risk factors for poor prognosis in patients with SSc and significant risk factors in random survival forest (RSF) surveys. A nomogram was plotted to evaluate the prognostic risk to facilitate clinical assessment; the RSF model had better predictive performance than the Cox model, with 3- and 5-year AUCs of 0.74 and 0.78, respectively.

CONCLUSION

Machine-learning models can help us better understand the prognosis of patients with SSc and comprehensively evaluate the clinical characteristics of each individual. The early identification of the characteristics of high-risk patients can improve the prognosis of those with SSc. Key Points • Regarding predictive performance, the random survival forest model was more effective than the Cox model and had unique advantages in analyzing nonlinear effects and variable importance. • Machine learning using the simple clinical features of patients with systemic sclerosis (SSc) to predict mortality can guide attending physicians, and the early identification of high-risk patients with SSc and referral to experts will assist rheumatologists in monitoring and management planning.

Insulin-like Growth Factor-Binding Protein 2 in Severe Aortic Valve Stenosis and Pulmonary Hypertension: A Gender-Based Perspective

Severe aortic valve stenosis (AS) and pulmonary hypertension (PH) are life-threatening cardiovascular conditions, necessitating early detection and intervention. Recent studies have explored the role of Insulin-like Growth Factor-Binding Protein 2 (IGF-BP2) in cardiovascular pathophysiology. Understanding its involvement may offer novel insights into disease mechanisms and therapeutic targets for these conditions. A total of 102 patients (46 female, 56 male) with severe AS undergoing a transcatheter aortic valve replacement (TAVR) in a single-center study were classified using echocardiography tests to determine systolic pulmonary artery pressure (sPAP) and the presence (sPAP ≥ 40 mmHg) or absence (sPAP < 40 mmHg) of PH. Additionally, serial laboratory determinations of IGF-BP2 before, and at 24 h, 96 h, and 3 months after intervention were conducted in all study participants. Considering the entire cohort, patients with PH had significant and continuously higher serum IGF-BP2 concentrations over time than patients without PH. After subdivision by sex, it could be demonstrated that the above-mentioned results were only verifiable in males, but not in females. In the male patients, baseline IGF-BP2 levels before the TAVR was an isolated risk factor for premature death after intervention and at 1, 3, and 5 years post-intervention. The same was valid for the combination of male and echocardiographically established PH patients. The predictive role of IGF-BP2 in severe AS and concurrent PH remains unknown. A more profound comprehension of IGF-BP2 mechanisms, particularly in males, could facilitate the earlier consideration of the TAVR as a more effective and successful treatment strategy.

The state of artificial intelligence for systemic dermatoses: Background and applications for psoriasis, systemic sclerosis, and much more

Artificial intelligence (AI) has been steadily integrated into dermatology, with AI platforms already attempting to identify skin cancers and diagnose benign versus malignant lesions. Although not as widely known, AI programs have also been utilized as diagnostic and prognostic tools for dermatologic conditions with systemic or extracutaneous involvement, especially for diseases with autoimmune etiologies. We have provided a primer on commonly used AI platforms and the practical applicability of these algorithms in dealing with psoriasis, systemic sclerosis, and dermatomyositis as a microcosm for future directions in the field. With a rapidly changing landscape in dermatology and medicine as a whole, AI could be a versatile tool to support clinicians and enhance access to care.

Resistin predicts disease severity and survival in patients with pulmonary arterial hypertension

BACKGROUND

Abnormal remodeling of distal pulmonary arteries in patients with pulmonary arterial hypertension (PAH) leads to progressively increased pulmonary vascular resistance, followed by right ventricular hypertrophy and failure. Despite considerable advancements in PAH treatment prognosis remains poor. We aim to evaluate the potential for using the cytokine resistin as a genetic and biological marker for disease severity and survival in a large cohort of patients with PAH.

METHODS

Biospecimens, clinical, and genetic data for 1121 adults with PAH, including 808 with idiopathic PAH (IPAH) and 313 with scleroderma-associated PAH (SSc-PAH), were obtained from a national repository. Serum resistin levels were measured by ELISA, and associations between resistin levels, clinical variables, and single nucleotide polymorphism genotypes were examined with multivariable regression models. Machine-learning (ML) algorithms were applied to develop and compare risk models for mortality prediction.

RESULTS

Resistin levels were significantly higher in all PAH samples and PAH subtype (IPAH and SSc-PAH) samples than in controls (P < .0001) and had significant discriminative abilities (AUCs of 0.84, 0.82, and 0.91, respectively; P < .001). High resistin levels (above 4.54 ng/mL) in PAH patients were associated with older age (P = .001), shorter 6-min walk distance (P = .001), and reduced cardiac performance (cardiac index, P = .016). Interestingly, mutant carriers of either rs3219175 or rs3745367 had higher resistin levels (adjusted P = .0001). High resistin levels in PAH patients were also associated with increased risk of death (hazard ratio: 2.6; 95% CI: 1.27-5.33; P < .0087). Comparisons of ML-derived survival models confirmed satisfactory prognostic value of the random forest model (AUC = 0.70, 95% CI: 0.62-0.79) for PAH.

CONCLUSIONS

This work establishes the importance of resistin in the pathobiology of human PAH. In line with its function in rodent models, serum resistin represents a novel biomarker for PAH prognostication and may indicate a new therapeutic avenue. ML-derived survival models highlighted the importance of including resistin levels to improve performance. Future studies are needed to develop multi-marker assays that improve noninvasive risk stratification.

Differentiation between descending thoracic aortic diseases using machine learning and plasma proteomic signatures

BACKGROUND

Descending thoracic aortic aneurysms and dissections can go undetected until severe and catastrophic, and few clinical indices exist to screen for aneurysms or predict risk of dissection.

METHODS

This study generated a plasma proteomic dataset from 75 patients with descending type B dissection (Type B) and 62 patients with descending thoracic aortic aneurysm (DTAA). Standard statistical approaches were compared to supervised machine learning (ML) algorithms to distinguish Type B from DTAA cases. Quantitatively similar proteins were clustered based on linkage distance from hierarchical clustering and ML models were trained with uncorrelated protein lists across various linkage distances with hyperparameter optimization using fivefold cross validation. Permutation importance (PI) was used for ranking the most important predictor proteins of ML classification between disease states and the proteins among the top 10 PI protein groups were submitted for pathway analysis.

RESULTS

Of the 1,549 peptides and 198 proteins used in this study, no peptides and only one protein, hemopexin (HPX), were significantly different at an adjusted p < 0.01 between Type B and DTAA cases. The highest performing model on the training set (Support Vector Classifier) and its corresponding linkage distance (0.5) were used for evaluation of the test set, yielding a precision-recall area under the curve of 0.7 to classify between Type B from DTAA cases. The five proteins with the highest PI scores were immunoglobulin heavy variable 6-1 (IGHV6-1), lecithin-cholesterol acyltransferase (LCAT), coagulation factor 12 (F12), HPX, and immunoglobulin heavy variable 4-4 (IGHV4-4). All proteins from the top 10 most important groups generated the following significantly enriched pathways in the plasma of Type B versus DTAA patients: complement activation, humoral immune response, and blood coagulation.

CONCLUSIONS

We conclude that ML may be useful in differentiating the plasma proteome of highly similar disease states that would otherwise not be distinguishable using statistics, and, in such cases, ML may enable prioritizing important proteins for model prediction.

Systemic Sclerosis-Associated Pulmonary Arterial Hypertension: From Bedside to Bench and Back Again

Systemic sclerosis (SSc) is a heterogeneous disease characterized by autoimmunity, vasculopathy, and fibrosis which affects the skin and internal organs. One key aspect of SSc vasculopathy is pulmonary arterial hypertension (SSc-PAH) which represents a leading cause of morbidity and mortality in patients with SSc. The pathogenesis of pulmonary hypertension is complex, with multiple vascular cell types, inflammation, and intracellular signaling pathways contributing to vascular pathology and remodeling. In this review, we focus on shared molecular features of pulmonary hypertension and those which make SSc-PAH a unique entity. We highlight advances in the understanding of the clinical and translational science pertinent to this disease. We first review clinical presentations and phenotypes, pathology, and novel biomarkers, and then highlight relevant animal models, key cellular and molecular pathways in pathogenesis, and explore emerging treatment strategies in SSc-PAH.

[Research progress on bioinformatics in pulmonary arterial hypertension]

Pulmonary arterial hypertension (PAH) is a severe disease characterized by abnormal pulmonary vascular remodeling and increased right ventricular pressure load, posing a significant threat to patient health. While some pathological mechanisms of PAH have been revealed, the deeper mechanisms of pathogenesis remain to be elucidated. In recent years, bioinformatics has provided a powerful tool for a deeper understanding of the complex mechanisms of PAH through the integration of techniques such as multi-omics analysis, artificial intelligence, and Mendelian randomization. This review focuses on the bioinformatics methods and technologies used in PAH research, summarizing their current applications in the study of disease mechanisms, diagnosis, and prognosis assessment. Additionally, it analyzes the existing challenges faced by bioinformatics and its potential applications in the clinical and basic research fields of PAH in the future.

Discrimination of Etiologically Different Cholestasis by Modeling Proteomics Datasets

Cholestasis is characterized by disrupted bile flow from the liver to the small intestine. Although etiologically different cholestasis displays similar symptoms, diverse factors can contribute to the progression of the disease and determine the appropriate therapeutic option. Therefore, stratifying cholestatic patients is essential for the development of tailor-made treatment strategies. Here, we have analyzed the liver proteome from cholestatic patients of different etiology. In total, 7161 proteins were identified and quantified, of which 263 were differentially expressed between control and cholestasis groups. These differential proteins point to deregulated cellular processes that explain part of the molecular framework of cholestasis progression. However, the clustering of different cholestasis types was limited. Therefore, a machine learning pipeline was designed to identify a panel of 20 differential proteins that segregate different cholestasis groups with high accuracy and sensitivity. In summary, proteomics combined with machine learning algorithms provides valuable insights into the molecular mechanisms of cholestasis progression and a panel of proteins to discriminate across different types of cholestasis. This strategy may prove useful in developing precision medicine approaches for patient care.

Immune Profiling of Patients with Systemic Sclerosis through Targeted Proteomic Analysis

High-throughput proteomic analysis could offer new insights into the pathogenesis of systemic sclerosis (SSc) and reveal non-invasive biomarkers for diagnosis and severity. This study aimed to assess the protein signature of patients with SSc compared to that of healthy volunteers, decipher various disease endotypes using circulating proteins, and determine the diagnostic performance of significantly expressed plasma analytes. We performed targeted proteomic profiling in a cohort of fifteen patients with SSc and eighteen controls using the Olink® (Olink Bioscience, Uppsala, Sweden)Target 96 Inflammation Panels. Seventeen upregulated proteins involved in angiogenesis, innate immunity, and co-stimulatory pathways discriminated between patients with SSc and healthy controls (HCs) and further classified them into two clusters, a low-inflammatory and a high-inflammatory endotype. Younger age, shorter disease duration, and lack of reflux esophagitis characterized patients in the low-inflammatory endotype. TNF, CXCL9, TNFRSF9, and CXCL10 positively correlated with disease progression, while the four-protein panel comprising TNF, CXCL9, CXCL10, and CX3CL1 showed high diagnostic performance. Collectively, this study identified a distinct inflammatory signature in patients with SSc that reflects a persistent T helper type 1 (Th 1) immune response irrespective of disease duration, while the multi-protein panel might improve early diagnosis in SSc.

Differentiation between Descending Thoracic Aortic Diseases using Machine Learning and Plasma Proteomic Signatures

Background

Descending thoracic aortic aneurysms and dissections can go undetected until severe and catastrophic, and few clinical indices exist to screen for aneurysms or predict risk of dissection.

Methods

This study generated a plasma proteomic dataset from 75 patients with descending type B dissection (Type B) and 62 patients with descending thoracic aortic aneurysm (DTAA). Standard statistical approaches were compared to supervised machine learning (ML) algorithms to distinguish Type B from DTAA cases. Quantitatively similar proteins were clustered based on linkage distance from hierarchical clustering and ML models were trained with uncorrelated protein lists across various linkage distances with hyperparameter optimization using 5-fold cross validation. Permutation importance (PI) was used for ranking the most important predictor proteins of ML classification between disease states and the proteins among the top 10 PI protein groups were submitted for pathway analysis.

Results

Of the 1,549 peptides and 198 proteins used in this study, no peptides and only one protein, hemopexin (HPX), were significantly different at an adjusted p-value <0.01 between Type B and DTAA cases. The highest performing model on the training set (Support Vector Classifier) and its corresponding linkage distance (0.5) were used for evaluation of the test set, yielding a precision-recall area under the curve of 0.7 to classify between Type B from DTAA cases. The five proteins with the highest PI scores were immunoglobulin heavy variable 6-1 (IGHV6-1), lecithin-cholesterol acyltransferase (LCAT), coagulation factor 12 (F12), HPX, and immunoglobulin heavy variable 4-4 (IGHV4-4). All proteins from the top 10 most important correlated groups generated the following significantly enriched pathways in the plasma of Type B versus DTAA patients: complement activation, humoral immune response, and blood coagulation.

Conclusions

We conclude that ML may be useful in differentiating the plasma proteome of highly similar disease states that would otherwise not be distinguishable using statistics, and, in such cases, ML may enable prioritizing important proteins for model prediction.

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.

Nailfold capillaroscopy and candidate-biomarker levels in systemic sclerosis-associated pulmonary hypertension: A cross-sectional study

Objectives

Pulmonary hypertension is one of the leading causes of death in systemic sclerosis. Early detection and treatment of pulmonary hypertension in systemic sclerosis is crucial. Nailfold capillaroscopy microscopy, vascular autoantibodies AT1R and ETAR, and several candidate-biomarkers have the potential to serve as noninvasive tools to identify systemic sclerosis patients at risk for developing pulmonary hypertension. Here, we explore the classifying potential of nailfold capillaroscopy microscopy characteristics and serum levels of selected candidate-biomarkers in a sample of systemic sclerosis patients with and without different forms of pulmonary hypertension.

Methods

A total of 81 consecutive systemic sclerosis patients were included, 40 with systemic sclerosis pulmonary hypertension and 41 with no pulmonary hypertension. In each group, quantitative and qualitative nailfold capillaroscopy microscopy characteristics, vascular autoantibodies AT1R and ETAR, and serum levels of 24 soluble serum factors were determined. For evaluation of the nailfold capillaroscopy microscopy characteristics, linear regression analysis accounting for age, sex, and diffusing capacity of the lungs for carbon monoxide percentage predicted was used. Autoantibodies and soluble serum factor levels were compared using two-sample t test with equal variances.

Results

No statistically significant differences were observed in quantitative or qualitative nailfold capillaroscopy microscopy characteristics, or vascular autoantibody ETAR and AT1R titer between systemic sclerosis-pulmonary hypertension and systemic sclerosis-no pulmonary hypertension. In contrast, several serum levels of soluble factors differed between groups: Endostatin, sVCAM, and VEGFD were increased, and CXCL4, sVEGFR2, and PDGF-AB/BB were decreased in systemic sclerosis-pulmonary hypertension. Random forest classification identified Endostatin and CXCL4 as the most predictive classifiers to distinguish systemic sclerosispulmonary hypertension from systemic sclerosis-no pulmonary hypertension.

Conclusion

This study shows the potential for several soluble serum factors to distinguish systemic sclerosis-pulmonary hypertension from systemic sclerosis-no pulmonary hypertension. We found no classifying potential for qualitative or quantitative nailfold capillaroscopy microscopy characteristics, or vascular autoantibodies.

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.

Proteomic aptamer analysis reveals serum biomarkers associated with disease mechanisms and phenotypes of systemic sclerosis

Background

Systemic sclerosis (SSc) is an autoimmune connective tissue disease that affects multiple organs, leading to elevated morbidity and mortality with limited treatment options. The early detection of organ involvement is challenging as there is currently no serum marker available to predict the progression of SSc. The aptamer technology proteomic analysis holds the potential to correlate SSc manifestations with serum proteins up to femtomolar concentrations.

Methods

This is a two-tier study of serum samples from women with SSc (including patients with interstitial lung disease - ILD - at high-resolution CT scan) and age-matched healthy controls (HC) that were first analyzed with aptamer-based proteomic analysis for over 1300 proteins. Proposed associated proteins were validated by ELISA first in an independent cohort of patients with SSc and HC, and selected proteins subject to further validation in two additional cohorts.

Results

The preliminary aptamer-based proteomic analysis identified 33 proteins with significantly different concentrations in SSc compared to HC sera and 9 associated with SSc-ILD, including proteins involved in extracellular matrix formation and cell-cell adhesion, angiogenesis, leukocyte recruitment, activation, and signaling. Further validations in independent cohorts ultimately confirmed the association of specific proteins with early SSc onset, specific organ involvement, and serum autoantibodies.

Conclusions

Our multi-tier proteomic analysis identified serum proteins discriminating patients with SSc and HC or associated with different SSc subsets, disease duration, and manifestations, including ILD, skin involvement, esophageal disease, and autoantibodies.

Machine learning for clustering and postclosure outcome of adult CHD-PAH patients with borderline hemodynamics

BACKGROUND

Patients with uncorrected isolated simple shunts associated pulmonary arterial hypertension (PAH) had increased mortality. Treatment strategies for borderline hemodynamics remain controversial. This study aims to investigate preclosure characteristics and its association with postclosure outcome in this group of patients.

METHODS

Adults with uncorrected isolated simple shunts associated PAH were included. Peak tricuspid regurgitation velocity<2.8 m/sec with normalized cardiac structures was defined as the favorable study outcome. We applied unsupervised and supervised machine learning for clustering analysis and model constructions.

RESULTS

Finally, 246 patients were included. During a median follow-up of 414days, 58.49% (62/106) of patients with pretricuspid shunts achieved favorable outcome while 32.22% (46/127) of patients with post-tricuspid shunts. In unsupervised learning, two clusters were identified in both types of shunts. Generally, the oxygen saturation, pulmonary blood flow, cardiac index, dimensions of the right and left atrium, were the major features that characterized the identified clusters. Specifically, mean right atrial pressure, right ventricular dimension, and right ventricular outflow tract helped differentiate clusters in pretricuspid shunts while age, aorta dimension, and systemic vascular resistance helped differentiate clusters for post-tricuspid shunts. Notably, cluster 1 had better postclosure outcome than cluster 2 (70.83% vs 32.55%, p < .001 for pretricuspid and 48.10% vs 16.67%, p < .001 for post-tricuspid). However, models constructed from supervised learning methods did not achieve good accuracy for predicting the postclosure outcome.

CONCLUSIONS

There were two main clusters in patients with borderline hemodynamics, in which one cluster had better postclosure outcome than the other.

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.

The soluble receptor for advanced glycation end products is potentially predictive of pulmonary arterial hypertension in systemic sclerosis

Introduction

Pulmonary arterial hypertension (PAH) and interstitial lung disease (ILD) are the leading causes of death in systemic sclerosis (SSc). Until now, no prospective biomarker to predict new onset of SSc-ILD or SSc-PAH in patients with SSc has reached clinical application. In homeostasis, the receptor for advanced glycation end products (RAGE) is expressed in lung tissue and involved in cell-matrix adhesion, proliferation and migration of alveolar epithelial cells, and remodeling of the pulmonary vasculature. Several studies have shown that sRAGE levels in serum and pulmonary tissue vary according to the type of lung-related complication. Therefore, we investigated levels of soluble RAGE (sRAGE) and its ligand high mobility group box 1 (HMGB1) in SSc and their abilities to predict SSc-related pulmonary complications.

Methods

One hundred eighty-eight SSc patients were followed retrospectively for the development of ILD, PAH, and mortality for 8 years. Levels of sRAGE and HMGB1 were measured in serum by ELISA. Kaplan-Meier survival curves were performed to predict lung events and mortality and event rates were compared with a log-rank test. Multiple linear regression analysis was performed to examine the association between sRAGE and important clinical determinants.

Results

At baseline, levels of sRAGE were significantly higher in SSc-PAH-patients (median 4099.0 pg/ml [936.3-6365.3], p = 0.011) and lower in SSc-ILD-patients (735.0 pg/ml [IQR 525.5-1988.5], p = 0.001) compared to SSc patients without pulmonary involvement (1444.5 pg/ml [966.8-2276.0]). Levels of HMGB1 were not different between groups. After adjusting for age, gender, ILD, chronic obstructive pulmonary disease, anti-centromere antibodies, the presence of puffy fingers or sclerodactyly, use of immunosuppression, antifibrotic therapy, or glucocorticoids, and use of vasodilators, higher sRAGE levels remained independently associated with PAH. After a median follow-up of 50 months (25-81) of patients without pulmonary involvement, baseline sRAGE levels in the highest quartile were predictive of development of PAH (log-rank p = 0.01) and of PAH-related mortality (p = 0.001).

Conclusions

High systemic sRAGE at baseline might be used as a prospective biomarker for patients with SSc at high risk to develop new onset of PAH. Moreover, high sRAGE levels could predict lower survival rates due to PAH in patients with SSc.

Signaling pathways in vascular function and hypertension: molecular mechanisms and therapeutic interventions

Hypertension is a global public health issue and the leading cause of premature death in humans. Despite more than a century of research, hypertension remains difficult to cure due to its complex mechanisms involving multiple interactive factors and our limited understanding of it. Hypertension is a condition that is named after its clinical features. Vascular function is a factor that affects blood pressure directly, and it is a main strategy for clinically controlling BP to regulate constriction/relaxation function of blood vessels. Vascular elasticity, caliber, and reactivity are all characteristic indicators reflecting vascular function. Blood vessels are composed of three distinct layers, out of which the endothelial cells in intima and the smooth muscle cells in media are the main performers of vascular function. The alterations in signaling pathways in these cells are the key molecular mechanisms underlying vascular dysfunction and hypertension development. In this manuscript, we will comprehensively review the signaling pathways involved in vascular function regulation and hypertension progression, including calcium pathway, NO-NOsGC-cGMP pathway, various vascular remodeling pathways and some important upstream pathways such as renin-angiotensin-aldosterone system, oxidative stress-related signaling pathway, immunity/inflammation pathway, etc. Meanwhile, we will also summarize the treatment methods of hypertension that targets vascular function regulation and discuss the possibility of these signaling pathways being applied to clinical work.

WGCNA combined with machine learning algorithms for analyzing key genes and immune cell infiltration in heart failure due to ischemic cardiomyopathy

Background

Ischemic cardiomyopathy (ICM) induced heart failure (HF) is one of the most common causes of death worldwide. This study aimed to find candidate genes for ICM-HF and to identify relevant biomarkers by machine learning (ML).

Methods

The expression data of ICM-HF and normal samples were downloaded from Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) between ICM-HF and normal group were identified. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment and gene ontology (GO) annotation analysis, protein–protein interaction (PPI) network, gene pathway enrichment analysis (GSEA), and single-sample gene set enrichment analysis (ssGSEA) were performed. Weighted gene co-expression network analysis (WGCNA) was applied to screen for disease-associated modules, and relevant genes were derived using four ML algorithms. The diagnostic values of candidate genes were assessed using receiver operating characteristic (ROC) curves. The immune cell infiltration analysis was performed between the ICM-HF and normal group. Validation was performed using another gene set.

Results

A total of 313 DEGs were identified between ICM-HF and normal group of GSE57345, which were mainly enriched in biological processes and pathways related to cell cycle regulation, lipid metabolism pathways, immune response pathways, and intrinsic organelle damage regulation. GSEA results showed positive correlations with pathways such as cholesterol metabolism in the ICM-HF group compared to normal group and lipid metabolism in adipocytes. GSEA results also showed a positive correlation with pathways such as cholesterol metabolism and a negative correlation with pathways such as lipolytic presentation in adipocytes compared to normal group. Combining multiple ML and cytohubba algorithms yielded 11 relevant genes. After validation using the GSE42955 validation sets, the 7 genes obtained by the machine learning algorithm were well verified. The immune cell infiltration analysis showed significant differences in mast cells, plasma cells, naive B cells, and NK cells.

Conclusion

Combined analysis using WGCNA and ML identified coiled-coil-helix-coiled-coil-helix domain containing 4 (CHCHD4), transmembrane protein 53 (TMEM53), acid phosphatase 3 (ACPP), aminoadipate-semialdehyde dehydrogenase (AASDH), purinergic receptor P2Y1 (P2RY1), caspase 3 (CASP3) and aquaporin 7 (AQP7) as potential biomarkers of ICM-HF. ICM-HF may be closely related to pathways such as mitochondrial damage and disorders of lipid metabolism, while the infiltration of multiple immune cells was identified to play a critical role in the progression of the disease.

Benchmarking of Machine Learning classifiers on plasma proteomic for COVID-19 severity prediction through interpretable artificial intelligence

The SARS-CoV-2 pandemic highlighted the need for software tools that could facilitate patient triage regarding potential disease severity or even death. In this article, an ensemble of Machine Learning (ML) algorithms is evaluated in terms of predicting the severity of their condition using plasma proteomics and clinical data as input. An overview of AI-based technical developments to support COVID-19 patient management is presented outlining the landscape of relevant technical developments. Based on this review, the use of an ensemble of ML algorithms that analyze clinical and biological data (i.e., plasma proteomics) of COVID-19 patients is designed and deployed to evaluate the potential use of AI for early COVID-19 patient triage. The proposed pipeline is evaluated using three publicly available datasets for training and testing. Three ML "tasks" are defined, and several algorithms are tested through a hyperparameter tuning method to identify the highest-performance models. As overfitting is one of the typical pitfalls for such approaches (mainly due to the size of the training/validation datasets), a variety of evaluation metrics are used to mitigate this risk. In the evaluation procedure, recall scores ranged from 0.6 to 0.74 and F1-score from 0.62 to 0.75. The best performance is observed via Multi-Layer Perceptron (MLP) and Support Vector Machines (SVM) algorithms. Additionally, input data (proteomics and clinical data) were ranked based on corresponding Shapley additive explanation (SHAP) values and evaluated for their prognosticated capacity and immuno-biological credence. This "interpretable" approach revealed that our ML models could discern critical COVID-19 cases predominantly based on patient's age and plasma proteins on B cell dysfunction, hyper-activation of inflammatory pathways like Toll-like receptors, and hypo-activation of developmental and immune pathways like SCF/c-Kit signaling. Finally, the herein computational workflow is corroborated in an independent dataset and MLP superiority along with the implication of the abovementioned predictive biological pathways are corroborated. Regarding limitations of the presented ML pipeline, the datasets used in this study contain less than 1000 observations and a significant number of input features hence constituting a high-dimensional low-sample (HDLS) dataset which could be sensitive to overfitting. An advantage of the proposed pipeline is that it combines biological data (plasma proteomics) with clinical-phenotypic data. Thus, in principle, the presented approach could enable patient triage in a timely fashion if used on already trained models. However, larger datasets and further systematic validation are needed to confirm the potential clinical value of this approach. The code is available on Github: https://github.com/inab-certh/Predicting-COVID-19-severity-through-interpretable-AI-analysis-of-plasma-proteomics.

Biomarkers of haemodynamic severity of systemic sclerosis-associated pulmonary arterial hypertension by serum proteome analysis

OBJECTIVES

To mine the serum proteome of patients with systemic sclerosis-associated pulmonary arterial hypertension (SSc-PAH) and to detect biomarkers that may assist in earlier and more effective diagnosis and treatment.

METHODS

Patients with limited cutaneous SSc, no extensive interstitial lung disease and no PAH-specific therapy were included. They were classified as cases if they had PAH confirmed by right heart catheterisation (RHC) and serum collected on the same day as RHC; and as controls if they had no clinical evidence of PAH.

RESULTS

Patients were mostly middle-aged females with anticentromere-associated SSc. Among 1129 proteins assessed by a high-throughput proteomic assay (SOMAscan), only 2 were differentially expressed and correlated significantly with pulmonary vascular resistance (PVR) in SSc-PAH patients (n=15): chemerin (ρ=0.62, p=0.01) and SET (ρ=0.62, p=0.01). To validate these results, serum levels of chemerin were measured by ELISA in an independent cohort. Chemerin levels were confirmed to be significantly higher (p=0.01) and correlate with PVR (ρ=0.42, p=0.04) in SSc-PAH patients (n=24). Chemerin mRNA expression was detected in fibroblasts, pulmonary artery smooth muscle cells (PA-SMCs)/pericytes and mesothelial cells in SSc-PAH lungs by single-cell RNA-sequencing. Confocal immunofluorescence revealed increased expression of a chemerin receptor, CMKLR1, on SSc-PAH PA-SMCs. SSc-PAH serum seemed to induce higher PA-SMC proliferation than serum from SSc patients without PAH. This difference appeared neutralised when adding the CMKLR1 inhibitor α-NETA.

CONCLUSION

Chemerin seems an interesting surrogate biomarker for PVR in SSc-PAH. Increased chemerin serum levels and CMKLR1 expression by PA-SMCs may contribute to SSc-PAH pathogenesis by inducing PA-SMC proliferation.

Serum Biomarkers in Connective Tissue Disease-Associated Pulmonary Arterial Hypertension

Pulmonary arterial hypertension (PAH) is a life-threatening complication of connective tissue diseases (CTDs) characterised by increased pulmonary arterial pressure and pulmonary vascular resistance. CTD-PAH is the result of a complex interplay among endothelial dysfunction and vascular remodelling, autoimmunity and inflammatory changes, ultimately leading to right heart dysfunction and failure. Due to the non-specific nature of the early symptoms and the lack of consensus on screening strategies-except for systemic sclerosis, with a yearly transthoracic echocardiography as recommended-CTD-PAH is often diagnosed at an advanced stage, when the pulmonary vessels are irreversibly damaged. According to the current guidelines, right heart catheterisation is the gold standard for the diagnosis of PAH; however, this technique is invasive, and may not be available in non-referral centres. Hence, there is a need for non-invasive tools to improve the early diagnosis and disease monitoring of CTD-PAH. Novel serum biomarkers may be an effective solution to this issue, as their detection is non-invasive, has a low cost and is reproducible. Our review aims to describe some of the most promising circulating biomarkers of CTD-PAH, classified according to their role in the pathophysiology of the disease.

Current Trends in Vascular Biomarkers for Systemic Sclerosis: A Narrative Review

Systemic sclerosis (SSc, scleroderma) is a multifaceted rare connective tissue disease whose pathogenesis is dominated by immune dysregulation, small vessel vasculopathy, impaired angiogenesis, and both cutaneous and visceral fibrosis. Microvascular impairment represents the initial event of the disease, preceding fibrosis by months or years and accounting for the main disabling and/or life-threatening clinical manifestations, including telangiectasias, pitting scars, periungual microvascular abnormalities (e.g., giant capillaries, hemorrhages, avascular areas, ramified/bushy capillaries) clinically detectable by nailfold videocapillaroscopy, ischemic digital ulcers, pulmonary arterial hypertension, and scleroderma renal crisis. Despite a variety of available treatment options, treatment of SSc-related vascular disease remains problematic, even considering SSc etherogenity and the quite narrow therapeutic window. In this context, plenty of studies have highlighted the great usefulness in clinical practice of vascular biomarkers allowing clinicians to assess the evolution of the pathological process affecting the vessels, as well as to predict the prognosis and the response to therapy. The current narrative review provides an up-to-date overview of the main candidate vascular biomarkers that have been proposed for SSc, focusing on their main reported associations with characteristic clinical vascular features of the disease.

Tensions in Taxonomies: Current Understanding and Future Directions in the Pathobiologic Basis and Treatment of Group 1 and Group 3 Pulmonary Hypertension

In the over 100 years since the recognition of pulmonary hypertension (PH), immense progress and significant achievements have been made with regard to understanding the pathophysiology of the disease and its treatment. These advances have been mostly in idiopathic pulmonary arterial hypertension (IPAH), which was classified as Group 1 Pulmonary Hypertension (PH) at the Second World Symposia on PH in 1998. However, the pathobiology of PH due to chronic lung disease, classified as Group 3 PH, remains poorly understood and its treatments thus remain limited. We review the history of the classification of the five groups of PH and aim to provide a state-of-the-art review of the understanding of the pathogenesis of Group 1 PH and Group 3 PH including insights gained from novel high-throughput omics technologies that have revealed heterogeneities within these categories as well as similarities between them. Leveraging the substantial gains made in understanding the genomics, epigenomics, proteomics, and metabolomics of PAH to understand the full spectrum of the complex, heterogeneous disease of PH is needed. Multimodal omics data as well as supervised and unbiased machine learning approaches after careful consideration of the powerful advantages as well as of the limitations and pitfalls of these technologies could lead to earlier diagnosis, more precise risk stratification, better predictions of disease response, new sub-phenotype groupings within types of PH, and identification of shared pathways between PAH and other types of PH that could lead to new treatment targets. © 2023 American Physiological Society. Compr Physiol 13:4295-4319, 2023.

Computational platform for doctor-artificial intelligence cooperation in pulmonary arterial hypertension prognostication: a pilot study

Background

Pulmonary arterial hypertension (PAH) is a heterogeneous and complex pulmonary vascular disease associated with substantial morbidity. Machine-learning algorithms (used in many PAH risk calculators) can combine established parameters with thousands of circulating biomarkers to optimise PAH prognostication, but these approaches do not offer the clinician insight into what parameters drove the prognosis. The approach proposed in this study diverges from other contemporary phenotyping methods by identifying patient-specific parameters driving clinical risk.

Methods

We trained a random forest algorithm to predict 4-year survival risk in a cohort of 167 adult PAH patients evaluated at Stanford University, with 20% withheld for (internal) validation. Another cohort of 38 patients from Sheffield University were used as a secondary (external) validation. Shapley values, borrowed from game theory, were computed to rank the input parameters based on their importance to the predicted risk score for the entire trained random forest model (global importance) and for an individual patient (local importance).

Results

Between the internal and external validation cohorts, the random forest model predicted 4-year risk of death/transplant with sensitivity and specificity of 71.0-100% and 81.0-89.0%, respectively. The model reinforced the importance of established prognostic markers, but also identified novel inflammatory biomarkers that predict risk in some PAH patients.

Conclusion

These results stress the need for advancing individualised phenotyping strategies that integrate clinical and biochemical data with outcome. The computational platform presented in this study offers a critical step towards personalised medicine in which a clinician can interpret an algorithm's assessment of an individual patient.

Advancing cardiovascular medicine with machine learning: Progress, potential, and perspective

Recent advances in machine learning (ML) have made it possible to analyze high-dimensional and complex data-such as free text, images, waveforms, videos, and sound-in an automated manner by successfully learning complex associations within these data. Cardiovascular medicine is particularly well poised to take advantage of these ML advances, due to the widespread digitization of medical data and the large number of diagnostic tests used to evaluate cardiovascular disease. Various ML approaches have successfully been applied to cardiovascular tests and diseases to automate interpretation, accurately perform measurements, and, in some cases, predict novel diagnoses from less invasive tests, effectively expanding the utility of more widely accessible diagnostic tests. Here, we present examples of some impactful advances in cardiovascular medicine using ML across a variety of modalities, with a focus on deep learning applications.

A signal recognition particle-related joint model of LASSO regression, SVM-RFE and artificial neural network for the diagnosis of systemic sclerosis-associated pulmonary hypertension

Background: Systemic sclerosis-associated pulmonary hypertension (SSc-PH) is one of the most common causes of death in patients with systemic sclerosis (SSc). The complexity of SSc-PH and the heterogeneity of clinical features in SSc-PH patients contribute to the difficulty of diagnosis. Therefore, there is a pressing need to develop and optimize models for the diagnosis of SSc-PH. Signal recognition particle (SRP) deficiency has been found to promote the progression of multiple cancers, but the relationship between SRP and SSc-PH has not been explored. Methods: First, we obtained the GSE19617 and GSE33463 datasets from the Gene Expression Omnibus (GEO) database as the training set, GSE22356 as the test set, and the SRP-related gene set from the MSigDB database. Next, we identified differentially expressed SRP-related genes (DE-SRPGs) and performed unsupervised clustering and gene enrichment analyses. Then, we used least absolute shrinkage and selection operator (LASSO) regression and support vector machine-recursive feature elimination (SVM-RFE) to identify SRP-related diagnostic genes (SRP-DGs). We constructed an SRP scoring system and a nomogram model based on the SRP-DGs and established an artificial neural network (ANN) for diagnosis. We used receiver operating characteristic (ROC) curves to identify the SRP-related signature in the training and test sets. Finally, we analyzed immune features, signaling pathways, and drugs associated with SRP and investigated SRP-DGs' functions using single gene batch correlation analysis-based GSEA. Results: We obtained 30 DE-SRPGs and found that they were enriched in functions and pathways such as "protein targeting to ER," "cytosolic ribosome," and "coronavirus disease-COVID-19". Subsequently, we identified seven SRP-DGs whose expression levels and diagnostic efficacy were validated in the test set. As one signature, the area under the ROC curve (AUC) values for seven SRP-DGs were 0.769 and 1.000 in the training and test sets, respectively. Predictions made using the nomogram model are likely beneficial for SSc-PH patients. The AUC values of the ANN were 0.999 and 0.860 in the training and test sets, respectively. Finally, we discovered that some immune cells and pathways, such as activated dendritic cells, complement activation, and heme metabolism, were significantly associated with SRP-DGs and identified ten drugs targeting SRP-DGs. Conclusion: We constructed a reliable SRP-related ANN model for the diagnosis of SSc-PH and investigated the possible role of SRP in the etiopathogenesis of SSc-PH by bioinformatics methods to provide a basis for precision and personalized medicine.

Predicting the Progression of Very Early Systemic Sclerosis: Current Insights

Systemic sclerosis (SSc) is a complex autoimmune connective tissue disease with distinct pathological hallmarks (ie, inflammation, vasculopathy, fibrosis) that may predominate at different stages in the disease course with varying severity. Initial efforts to classify patients with SSc identified a subset of patients with very early SSc. These patients possessed signs of SSc (eg, Raynaud phenomenon, SSc specific autoantibodies and/or nailfold capillary abnormalities) without fulfilling complete SSc classification criteria. Recognizing the inherent value in early diagnosis and intervention in SSc, researchers have endeavored to identify risk factors for progression from very early SSc to definite SSc. The present review summarizes the clinical phenotype of patients with very early and early SSc. Through a scoping review of recent literature, this review also describes risk factors for progression to definite SSc with a focus on the specific clinical features that arise early in the SSc disease course (eg, diffuse cutaneous sclerosis, interstitial lung disease, esophageal dysfunction, renal crisis, cardiac involvement). In addition to clinical risk factors, this review provides evidence for how biological data (ie, serological, genomic, proteomic profiles, skin bioengineering methods) can be integrated into risk assessment models in the future. Furthering our understanding of biological features of very early SSc will undoubtedly provide novel insights into SSc pathogenesis and may illuminate new therapeutic targets to prevent progression of SSc.

The Use and Utility of Machine Learning in Achieving Precision Medicine in Systemic Sclerosis: A Narrative Review

BACKGROUND

Systemic sclerosis (SSc) is a rare connective tissue disease that can affect different organs and has extremely heterogenous presentations. This complexity makes it difficult to perform an early diagnosis and a subsequent subclassification of the disease. This hinders a personalized approach in clinical practice. In this context, machine learning (ML), a branch of artificial intelligence (AI), is able to recognize relationships in data and predict outcomes.

METHODS

Here, we performed a narrative review concerning the application of ML in SSc to define the state of art and evaluate its role in a precision medicine context.

RESULTS

Currently, ML has been used to stratify SSc patients and identify those at high risk of severe complications. Additionally, ML may be useful in the early detection of organ involvement. Furthermore, ML might have a role in target therapy approach and in predicting drug response.

CONCLUSION

Available evidence about the utility of ML in SSc is sparse but promising. Future improvements in this field could result in a big step toward precision medicine. Further research is needed to define ML application in clinical practice.

Circulating Neurovascular Guidance Molecules and Their Relationship with Peripheral Microvascular Impairment in Systemic Sclerosis

Systemic sclerosis (SSc, scleroderma) is a complex connective tissue disease whose earliest clinical manifestations are microvascular tone dysregulation and peripheral microcirculatory abnormalities. Following previous evidence of an association between circulating neurovascular guidance molecules and SSc disturbed angiogenesis, here, we measured the levels of soluble neuropilin 1 (sNRP1), semaphorin 3E (Sema3E), and Slit2 by enzyme-linked immunosorbent assay in serum samples from a large case series of 166 SSc patients vs. 110 healthy controls. We focused on their possible correlation with vascular disease clinical features and applied logistic regression analysis to determine which of them could better reflect disease activity and severity. Our results demonstrate that, in SSc: (i) sNRP1 is significantly decreased, with lower sNRP1 serum levels correlating with the severity of nailfold videocapillaroscopy (NVC) abnormalities and the presence of ischemic digital ulcers (DUs); (ii) both Sema3E and Slit2 are increased, with Sema3E better reflecting early NVC abnormalities; and (iii) higher Sema3E correlates with the absence of DUs, while augmented Slit2 associates with the presence of DUs. Receiver operator characteristics curve analysis revealed that both circulating sNRP1 and Sema3E show a moderate diagnostic accuracy. Moreover, logistic regression analysis allowed to identify sNRP1 and Sema3E as more suitable independent biomarkers reflecting the activity and severity of SSc-related peripheral microvasculopathy.

Development of an Electronic Frailty Index for Predicting Mortality and Complications Analysis in Pulmonary Hypertension Using Random Survival Forest Model

Background

The long-term prognosis of the cardio-metabolic and renal complications, in addition to mortality in patients with newly diagnosed pulmonary hypertension, are unclear. This study aims to develop a scalable predictive model in the form of an electronic frailty index (eFI) to predict different adverse outcomes.

Methods

This was a population-based cohort study of patients diagnosed with pulmonary hypertension between January 1st, 2000 and December 31st, 2017, in Hong Kong public hospitals. The primary outcomes were mortality, cardiovascular complications, renal diseases, and diabetes mellitus. The univariable and multivariable Cox regression analyses were applied to identify the significant risk factors, which were fed into the non-parametric random survival forest (RSF) model to develop an eFI.

Results

A total of 2,560 patients with a mean age of 63.4 years old (interquartile range: 38.0–79.0) were included. Over a follow-up, 1,347 died and 1,878, 437, and 684 patients developed cardiovascular complications, diabetes mellitus, and renal disease, respectively. The RSF-model-identified age, average readmission, anti-hypertensive drugs, cumulative length of stay, and total bilirubin were among the most important risk factors for predicting mortality. Pair-wise interactions of factors including diagnosis age, average readmission interval, and cumulative hospital stay were also crucial for the mortality prediction. Patients who developed all-cause mortality had higher values of the eFI compared to those who survived (P < 0.0001). An eFI ≥ 9.5 was associated with increased risks of mortality [hazard ratio (HR): 1.90; 95% confidence interval [CI]: 1.70–2.12; P < 0.0001]. The cumulative hazards were higher among patients who were 65 years old or above with eFI ≥ 9.5. Using the same cut-off point, the eFI predicted a long-term mortality over 10 years (HR: 1.71; 95% CI: 1.53–1.90; P < 0.0001). Compared to the multivariable Cox regression, the precision, recall, area under the curve (AUC), and C-index were significantly higher for RSF in the prediction of outcomes.

Conclusion

The RSF models identified the novel risk factors and interactions for the development of complications and mortality. The eFI constructed by RSF accurately predicts the complications and mortality of patients with pulmonary hypertension, especially among the elderly.

Using the Plasma Proteome for Risk Stratifying Patients with Pulmonary Arterial Hypertension

Rationale: NT-proBNP (N-terminal pro-brain natriuretic peptide), a biomarker of cardiac origin, is used to risk stratify patients with pulmonary arterial hypertension (PAH). Its limitations include poor sensitivity to early vascular pathology. Other biomarkers of vascular or systemic origin may also be useful in the management of PAH. Objectives: Identify prognostic proteins in PAH that complement NT-proBNP and clinical risk scores. Methods: An aptamer-based assay (SomaScan version 4) targeting 4,152 proteins was used to measure plasma proteins in patients with idiopathic, heritable, or drug-induced PAH from the UK National Cohort of PAH (n = 357) and the French EFORT (Evaluation of Prognostic Factors and Therapeutic Targets in PAH) study (n = 79). Prognostic proteins were identified in discovery-replication analyses of UK samples. Proteins independent of 6-minute-walk distance and NT-proBNP entered least absolute shrinkage and selection operator modeling, and the best combination in a single score was evaluated against clinical targets in EFORT. Measurements and Main Results: Thirty-one proteins robustly informed prognosis independent of NT-proBNP and 6-minute-walk distance in the UK cohort. A weighted combination score of six proteins was validated at baseline (5-yr mortality; area under the curve [AUC], 0.73; 95% confidence interval [CI], 0.63-0.85) and follow-up in EFORT (AUC, 0.84; 95% CI, 0.75-0.94; P = 9.96 × 10^-6). The protein score risk stratified patients independent of established clinical targets and risk equations. The addition of the six-protein model score to NT-proBNP improved prediction of 5-year outcomes from AUC 0.762 (0.702-0.821) to 0.818 (0.767-0.869) by receiver operating characteristic analysis (P = 0.00426 for difference in AUC) in the UK replication and French samples combined. Conclusions: The plasma proteome informs prognosis beyond established factors in PAH and may provide a more sensitive measure of therapeutic response.

Harnessing Big Data to Advance Treatment and Understanding of Pulmonary Hypertension

Pulmonary hypertension is a complex disease with multiple causes, corresponding to phenotypic heterogeneity and variable therapeutic responses. Advancing understanding of pulmonary hypertension pathogenesis is likely to hinge on integrated methods that leverage data from health records, imaging, novel molecular -omics profiling, and other modalities. In this review, we summarize key data sets generated thus far in the field and describe analytical methods that hold promise for deciphering the molecular mechanisms that underpin pulmonary vascular remodeling, including machine learning, network medicine, and functional genetics. We also detail how genetic and subphenotyping approaches enable earlier diagnosis, refined prognostication, and optimized treatment prediction. We propose strategies that identify functionally important molecular pathways, bolstered by findings across multi-omics platforms, which are well-positioned to individualize drug therapy selection and advance precision medicine in this highly morbid disease.

An evolutionary machine learning for pulmonary hypertension animal model from arterial blood gas analysis

Pulmonary hypertension (PH) is a rare and fatal condition that leads to right heart failure and death. The pathophysiology of PH and potential therapeutic approaches are yet unknown. PH animal models' development and proper evaluation are critical to PH research. This work presents an effective analysis technology for PH from arterial blood gas analysis utilizing an evolutionary kernel extreme learning machine with multiple strategies integrated slime mould algorithm (MSSMA). In MSSMA, two efficient bee-foraging learning operators are added to the original slime mould algorithm, ensuring a suitable trade-off between intensity and diversity. The proposed MSSMA is evaluated on thirty IEEE benchmarks and the statistical results show that the search performance of the MSSMA is significantly improved. The MSSMA is utilised to develop a kernel extreme learning machine (MSSMA-KELM) on PH from arterial blood gas analysis. Comprehensively, the proposed MSSMA-KELM can be used as an effective analysis technology for PH from arterial Blood gas analysis with an accuracy of 93.31%, Matthews coefficient of 90.13%, Sensitivity of 91.12%, and Specificity of 90.73%. MSSMA-KELM can be treated as an effective approach for evaluating mouse PH models.

Effect of Levosimendan on Acute Decompensated Right Heart Failure in Patients With Connective Tissue Disease-Associated Pulmonary Arterial Hypertension

Aims

Acute decompensated right heart failure (RHF) in chronic precapillary pulmonary hypertension is often typified by a swiftly progressive syndrome involving systemic congestion. This results from the impairment of the right ventricular filling and/or a reduction in the flow output of the right ventricle, which has been linked to a dismal prognosis of short duration. Despite this, there are limited therapeutic data regarding these acute incidents. This study examined the effect of levosimendan on acute decompensated RHF in patients with connective tissue disease-associated pulmonary arterial hypertension (CTD-PAH).

Methods

This retrospective study included 87 patients with confirmed CTD-PAH complicated acute decompensated RHF between November 2015 and April 2021. We collected biological, clinical, and demographic data, as well as therapy data, from patients with acute decompensated RHF who required levosimendan treatment in the cardiac care unit (CCU) for CTD-PAH. The patients were divided into two groups according to the levosimendan treatment. Patient information between the two groups was systematically compared in hospital and at follow-up.

Results

Oxygen saturation of mixed venose blood (SvO₂), estimated glomerular filtration rate (eGFR), 24-h urine output, and tricuspid annular plane systolic excursion (TAPSE) were found to be considerably elevated in the levosimendan cohort compared with the control cohort. Patients in the levosimendan cohort exhibited considerably reduced levels of C-reactive protein (CRP), white blood cell (WBC), troponin I, creatinine, NT-proBNP, and RV diameter compared with those in the control cohort. A higher survival rate was observed in the levosimendan cohort.

Conclusions

Levosimendan treatment could effectively improve acute decompensated RHF and systemic hemodynamics in CTD-PAH patients, with positive effects on survival in hospital and can, therefore, be considered as an alternative treatment option for improving clinical short-term outcomes.

Diagnostic value of cardiac natriuretic peptide on pulmonary hypertension in systemic sclerosis: A systematic review and meta-analysis

OBJECTIVE

Pulmonary arterial hypertension (PAH) is a major cause of morbidity and mortality in systemic sclerosis (SSc). Many risk factors and predictors of outcomes have been identified in these patients. B-type natriuretic peptide (BNP) and N-terminal pro-BNP (NT-proBNP) serum levels are often elevated in SSc patients with early PAH. We conducted this systematic review and meta-analysis to estimate the diagnostic value of BNP/NT-proBNP in systemic sclerosis secondary pulmonary arterial hypertension (SSc-PAH).

METHODS

A systematic search was performed through PubMed, Embase, and Cochrane Library databases up to January 30, 2021. Stata 16.0 (Stata Corp, College Station, TX) was used to conduct the meta-analysis.

RESULTS

A total of 9 studies involving 220 SSc-PAH patients and 259 non-SSc-PAH controls were included. The values of sensitivity and specificity using BNP and NT-ProBNP as diagnostic tools were pooled in the diagnostic meta-analysis. The overall performance of BNP/NT-ProBNP detection was: pooled sensitivity, 0.67 (95% CI: 0.52 to 0.79); pooled specificity, 0.84 (95% CI: 0.75 to 0.91); pooled positive likelihood ratio, 4.3 (95% CI: 3 to 6.1); and pooled negative likelihood ratio, 0.39 (95% CI: 0.28 to 0.55). The subgroup analysis showed similar results. Funnel plots indicate that there is no evidence for publication bias.

CONCLUSIONS

Our results revealed that NT-proBNP has certain diagnostic value for PAH due to its better specificity and moderate sensitivity, but its clinical application value remains suboptimal and can not be a stand-alone decision-making diagnostic tool of SSc-PAH.

Diagnostic and prognostic significance of serum angiopoietin-1 and -2 concentrations in patients with pulmonary hypertension

Several biomarkers for detecting pulmonary hypertension (PH) have been reported. However, these biomarkers are deemed insufficient to detect PH in its early stages. We evaluated the utility of serum angiopoietin (ANGP), a glycoprotein related to angiogenesis, as a diagnostic and prognostic biomarker of PH. Patients with PH who underwent right-heart catheterization, were retrospectively studied. Serum concentrations of ANGP-1 and ANGP-2 were measured using an enzyme-linked immunosorbent assay in patients with PH (n = 32), those with idiopathic pulmonary fibrosis (IPF) without PH (as a disease control, n = 75), and age-matched healthy controls (HC, n = 60). Nineteen patients (59.4%) with PH had World Health Organization group 3 PH. Serum ANGP-2 concentration, but not ANGP-1, in patients with PH was significantly higher compared with that in HC (p = 0.025) and in patients with IPF without PH (p = 0.008). Serum ANGP-2 concentration in patients with PH positively and significantly correlated with N-terminal pro-B-type natriuretic peptide (r = 0.769, p < 0.001), right ventricular diameter on echocardiography (r = 0.565, p = 0.035), and mean pulmonary arterial pressure (r = 0.449, p = 0.032) and pulmonary vascular resistance (r = 0.451, p = 0.031) on right-heart catheterization. ANGP-1 and ANGP-2 were expressed on lung vascular endothelial cells, as shown by immunohistochemistry. Patients with PH with higher ANGP-2 concentration (≥ 2.48 ng/mL) had significantly worse survival (p = 0.022). Higher ANGP-2 concentration was a significant worse prognostic factor (hazard ratio = 6.063, p = 0.037), while serum ANGP-1 concentration was not. In conclusion, serum ANGP-2 may be a useful diagnostic and prognostic biomarker in patients with PH, especially in patients with group 3 PH.

What's new in pulmonary hypertension clinical research: lessons from the best abstracts at the 2020 American Thoracic Society International Conference

In this conference paper, we review the 2020 American Thoracic Society International Conference session titled, "What's New in Pulmonary Hypertension Clinical Research: Lessons from the Best Abstracts". This virtual mini-symposium took place on 21 October 2020, in lieu of the annual in-person ATS International Conference which was cancelled due to the COVID-19 pandemic. Seven clinical research abstracts were selected for presentation in the session, which encompassed five major themes: (1) standardizing diagnosis and management of pulmonary hypertension, (2) improving risk assessment in pulmonary arterial hypertension, (3) evaluating biomarkers of disease activity, (4) understanding metabolic dysregulation across the spectrum of pulmonary hypertension, and (5) advancing knowledge in chronic thromboembolic pulmonary hypertension. Focusing on these five thematic contexts, we review the current state of knowledge, summarize presented research abstracts, appraise their significance and limitations, and then discuss relevant future directions in pulmonary hypertension clinical research.