Vasculitis & polymyalgia rheumatica
Identification of the immune-related biomarkers in Behcet’s disease by plasma proteomic analysis
Authors' conclusion
Our study not only revealed a distinctive immune response-related protein profile for BD but also showed that IL10, FCRL3, MASP1, NF2, FAM3B, and MGMT could serve as potential immune biomarkers for this disease.
Study context
- Population
- Behcet's disease (BD) patients and healthy controls (plasma)
- Comparison
- BD patients vs healthy controls
- Outcome
- Immune response-related protein profile and prediction of BD
Methodological detailsplasma proteomics (Olink Immune Response Panel), machine learning prediction models, consensus clustering
- Plasma proteomics (Olink Immune Response Panel)
- Machine learning prediction models
- Consensus clustering
Performance
As reported in the abstract
- Differentially expressed proteins (DEPs) between BD patients and healthy controls (HC) (P < 0.05)
- 43
- Neural network model (best of five; DEPs IL10, FCRL3, MASP1, NF2, FAM3B, MGMT): AUC
- 0.856
- Neural network model: recall
- 0.692
- Neural network model: specificity
- 0.857
- Neural network model: precision
- 0.900
- Neural network model: accuracy
- 0.750
- Neural network model: F1 score
- 0.783
Further findings
BD subtypes by consensus clustering
- Two subtypes: high disease activity with higher TRIM5, SH2D1A, PIK3AP1, HCLS1 and DFFA expression; low disease activity with higher CCL11 expression
Original publication
Identification of the immune-related biomarkers in Behcet’s disease by plasma proteomic analysis. Arthritis Res Ther. Published 1 June 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →