Discovery of Distinct Immune Phenotypes Using Machine Learning in Pulmonary Arterial Hypertension

Abstract

In December 2018, the average time from submission to first decision for all original research papers submitted to Circulation Research was 14.99 days. ABSTRACTRationale: Accumulating evidence implicates inflammation in pulmonary arterial hypertension (PAH) and therapies targeting immunity are under investigation, though it remains unknown if distinct immune phenotypes exist.Objective: Identify PAH immune phenotypes based on unsupervised analysis of blood proteomic profiles. Methods and Results:In a prospective observational study of Group 1 PAH patients evaluated at Stanford University (discovery cohort, n=281) and University of Sheffield (validation cohort, n=104) between 2008-2014, we measured a circulating proteomic panel of 48 cytokines, chemokines, and factors using multiplex immunoassay. Unsupervised machine learning (consensus clustering) was applied in both cohorts independently to classify patients into proteomic immune clusters, without guidance from clinical features. To identify central proteins in each cluster, we performed partial correlation network analysis. Clinical characteristics and outcomes were subsequently compared across clusters. Four PAH clusters with distinct proteomic immune profiles were identified in the discovery cohort. Cluster 2 (n=109) had low cytokine levels similar to controls. Other clusters had unique sets of upregulated proteins central to immune networks-cluster 1 (n=58)(TRAIL, CCL5, CCL7, CCL4, MIF), cluster 3 (n=77)(IL-12, IL-17, IL-10, IL-7, VEGF), and cluster 4 (n=37)(IL-8, IL-4, PDGF-, IL-6, CCL11). Demographics, PAH etiologies, comorbidities, and medications were similar across clusters. Non-invasive and hemodynamic surrogates of clinical risk identified cluster 1 as high-risk and cluster 3 as low-risk groups. Five-year transplant-free survival rates were unfavorable for cluster 1 (47.6%, CI 35.4-64.1%) and favorable for cluster 3 (82.4%, CI 72.0-94.3%)(across-cluster p<0.001). Findings were replicated in the validation cohort, where machine learning classified four immune clusters with comparable proteomic, clinical, and prognostic features.Conclusions: Blood cytokine profiles distinguish PAH immune phenotypes with differing clinical risk that are independent of World Health Organization Group 1 subtypes. These phenotypes could inform mechanistic studies of disease pathobiology and provide a framework to examine patient responses to emerging therapies targeting immunity. Nonstandard Abbreviations and Acronyms: CI confidence interval 95% EC pulmonary artery endothelial cell IQR interquartile range 25-75% K cluster number in unsupervised consensus clustering MFI median fluorescence intensity mPAP mean pulmonary arterial pressure NT-proBNP N-terminal pro b-type natriuretic peptide PAH pulmonary arterial hypertension PVDOMICS Pulmonary Vascular Disease Phenomics Program PVR pulmonary vascular resistance REVEAL Registry to Evaluate Early and Long-term PAH Disease Management SMC pulmonary artery smooth muscle cell SQL structured query language TAPSE tricuspid annular pla...

Pulmonary Arterial Hypertension and Chronic Thromboembolic Pulmonary Hypertension: An Immunological Perspective

“…In a recent study, cytokine clusters were made in PAH patients using machine learning. The analyses showed that the immune phenotypes were not dependent upon the subtypes within the WHO Group 1 PAH classification [108], indicating that immune phenotypes may vary within the WHO Group 1 subtypes. Furthermore, these findings might provide a framework to examine patient responses to emerging therapies targeting immunity in the future.…”

IL-6 in pulmonary hypertension: why novel is not always best

“…In murine models, overexpression of IL-6 leads to the development of pulmonary vascular lesions [5], IL-6 deficient mice are protected [6] and administration of an IL-6R neutralising antibody attenuates the development of experimental PAH [7]. Looking wider than IL-6 signalling, there is broad acceptance that inflammation plays an integral part in PAH pathobiology [8,9]. The wealth of preclinical data provided a solid platform from which the clinical tractability of inflammation in patients with PAH was to be explored.…”

2-Methoxyestradiol in Pulmonary Arterial Hypertension: A New Disease Modifier

“…This may explain why various immune diseases are remarkably more frequent in women and why many immune diseases, such as systemic sclerosis (SSc), lupus, and mixed connective tissue disease, are associated with increased risk of PAH [117]. Furthermore, recently distinct immune phenotypes have been reported in PAH patients [118]. In experimental PH, dysregulated immunity in the form of deficient regulatory T-cell (Treg) activity contributes to increased inflammation [20].…”