Unsupervised clustering to differentiate rheumatoid arthritis patients based on proteomic signatures

Autores da FMUP

• António Sousa Barros

  Autor

• João Pedro Melo Marques Pinho Ferreira

  Autor

Participantes de fora da FMUP

• Ferreira, MB
• Kobayashi, M
• Costa, RQ
• Fonseca, T
• Brandao, M
• Oliveira, JC
• Marinho, A
• Carvalho, HC
• Rodrigues, P
• Zannad, F
• Rossignol, P

Unidades de investigação

• Cirurgia e Fisiologia

• Laboratório Associado RISE- Rede de Investigação em Saúde

  

  Investigador

  Fernando Carlos De Landér Schmitt

• RISE-Health

  

  Investigador

  Fernando Carlos De Landér Schmitt

Abstract

ObjectivePatients with rheumatoid arthritis (RA) have different presentations and prognoses. Cluster analysis based on proteomic signatures creates independent phenogroups of patients with different pathophysiological backgrounds. We aimed to identify distinct pathophysiological clusters of RA patients based on circulating proteomic biomarkers.MethodThis was a cohort study including 399 RA patients. Clustering was performed on 94 circulating proteins (92 CVDII Olink (R), high-sensitivity troponin T, and C-reactive protein). Unsupervised clustering was performed using a partitioning cluster algorithm.ResultsThe clustering algorithm identified two distinct clusters: cluster 1 (n = 223) and cluster 2 (n = 176). Compared with cluster 1, cluster 2 included older patients with a higher burden of comorbidities (cardiovascular and RA related), more erosive and longer RA duration, more dyspnoea and fatigue, walking a shorter distance in the Six-Minute Walk Test, with more severe diastolic dysfunction, and a 4.5-fold higher risk of death or hospitalization for cardiovascular reasons. Tumour necrosis factor (TNF) receptor superfamily-related pathways were mainly responsible for the model's discriminative ability.ConclusionUsing unsupervised cluster analysis based on proteomic phenotypes, we identified two clusters of RA patients with distinct biomarkers profiles, clinical characteristics, and different outcomes that could reflect different pathophysiological backgrounds. TNF receptor superfamily-related proteins may be used to distinguish subgroups.

Keywords

• Arthritis, Rheumatoid; Biomarkers; Cluster Analysis; Cohort Studies; Humans; Proteomics; angiotensin receptor antagonist; beta adrenergic receptor blocking agent; biological marker; C reactive protein; corticosteroid; dipeptidyl carboxypeptidase inhibitor; disease modifying antirheumatic drug; hydroxymethylglutaryl coenzyme A reductase inhibitor; loop diuretic agent; methotrexate; nonsteroid antiinflammatory agent; receptor activator of nuclear factor kappa B; rituximab; tocilizumab; troponin T; tumor necrosis factor receptor; biological marker; adult; aged; Article; cardiovascular risk factor; cluster analysis; clustering algorithm; cohort analysis; comorbidity; confidence interval; controlled study; death; diastolic dysfunction; discriminant analysis; dyspnea; echocardiography; fatigue; female; follow up; heart ejection fraction; hospitalization; human; hypertension; k means clustering; Kaplan Meier method; laboratory test; major clinical study; male; medical society; middle aged; pa