2018
DOI: 10.1002/art.40428
|View full text |Cite
|
Sign up to set email alerts
|

Identification of Three Rheumatoid Arthritis Disease Subtypes by Machine Learning Integration of Synovial Histologic Features and RNA Sequencing Data

Abstract: Objective In this study, we sought to refine histologic scoring of rheumatoid arthritis (RA) synovial tissue by training with gene expression data and machine learning. Methods Twenty histologic features were assessed in 129 synovial tissue samples (n = 123 RA patients and n = 6 osteoarthritis [OA] patients). Consensus clustering was performed on gene expression data from a subset of 45 synovial samples. Support vector machine learning was used to predict gene expression subtypes, using histologic data as the … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

7
169
0
3

Year Published

2018
2018
2024
2024

Publication Types

Select...
7
1

Relationship

5
3

Authors

Journals

citations
Cited by 171 publications
(179 citation statements)
references
References 45 publications
7
169
0
3
Order By: Relevance
“…Tissue samples were stained with Harris’ modified hematoxylin solution and eosin Y (both from Sigma‐Aldrich). Ten features (synovial lining hyperplasia, lymphocytes, plasma cells, Russell bodies, binucleate plasma cells, fibrin, synovial giant cells, detritus, neutrophils, and mucin) were scored as previously described (http://www.hss.edu/pathology-synovitis.asp).…”
Section: Methodsmentioning
confidence: 99%
“…Tissue samples were stained with Harris’ modified hematoxylin solution and eosin Y (both from Sigma‐Aldrich). Ten features (synovial lining hyperplasia, lymphocytes, plasma cells, Russell bodies, binucleate plasma cells, fibrin, synovial giant cells, detritus, neutrophils, and mucin) were scored as previously described (http://www.hss.edu/pathology-synovitis.asp).…”
Section: Methodsmentioning
confidence: 99%
“…To gain insight into the underlying cellular and transcriptional mechanisms of RA, we recently performed histologic and RNA‐Seq analyses on RA synovium . Clustering of synovial gene expression data identified 3 synovial subtypes of RA: “low inflammatory,” “high inflammatory,” and “mixed” .…”
Section: Introductionmentioning
confidence: 99%
“…To gain insight into the underlying cellular and transcriptional mechanisms of RA, we recently performed histologic and RNA‐Seq analyses on RA synovium . Clustering of synovial gene expression data identified 3 synovial subtypes of RA: “low inflammatory,” “high inflammatory,” and “mixed” . Though these synovial subsets were significantly associated with autoantibodies such as cyclic citrullinated peptide (CCP) and rheumatoid factor (RF) and systemic markers of inflammation such as C‐reactive protein (CRP) level and erythrocyte sedimentation rate (ESR), they were not associated with clinical features (i. e., swollen and tender joint counts or pain scores).…”
Section: Introductionmentioning
confidence: 99%
“…To examine the impact of therapeutically targeting HBEGF + macrophages in RA joints, we directly assayed synovial tissue from RA patients with definitive RA diagnoses ( 40, 41 ) and extensive joint inflammation confirmed by histologic scoring ( 42, 43 ) (Table S1, n=8). Specifically, in an ex vivo tissue assay, synovium was dissociated into cell suspensions ( 44 ) and cultured with FDA-approved RA medications (Fig.…”
Section: Resultsmentioning
confidence: 99%