Systemic sclerosis & Raynaud's
Cytokine Profiling of Systemic Sclerosis–Related Pulmonary Hypertension
Authors' conclusion
Using a single-center SSc cohort that reflects real-world heterogeneity, we generated a highly specific cytokine profile for SSc-PH through a random forest approach.
Study context
- Population
- Patients with SSc, 24 with SSc-PH by right heart catheterization; single centre24 with SSc-PH
- Participants
- 106 patients
- Comparison
- 48-cytokine random forest model vs collapsed six-cytokine model for identifying SSc-PH
- Outcome
- Discrimination of SSc-PH by cytokine profile (AUC, sensitivity, specificity, accuracy)
Methodological detailsobservational, single-center, random forest model, internal validation by train-test split
- Observational
- Single-center
- Random forest model
- Internal validation by train-test split
Performance
As reported in the abstract
Identification of SSc-PH
| Test or model | AUC | Sensitivity | Specificity | Accuracy |
|---|---|---|---|---|
| 48-cytokine model | 0.82 (95% CI 0.62-1.00) | — not stated in the abstract | — not stated in the abstract | — not stated in the abstract |
| Collapsed six-cytokine model | 0.83 (95% CI 0.72-1.00) | 0.14 (95% CI 0.00-0.58) | 0.96 (95% CI 0.80-1.00) | 0.78 (95% CI 0.60-0.91) |
AUC
48-cytokine model0.82 (95% CI 0.62-1.00)
Collapsed six-cytokine model0.83 (95% CI 0.72-1.00)
Sensitivity
48-cytokine model— not stated in the abstract
Collapsed six-cytokine model0.14 (95% CI 0.00-0.58)
Specificity
48-cytokine model— not stated in the abstract
Collapsed six-cytokine model0.96 (95% CI 0.80-1.00)
Accuracy
48-cytokine model— not stated in the abstract
Collapsed six-cytokine model0.78 (95% CI 0.60-0.91)
— not stated in the abstract
Original publication
Cytokine Profiling of Systemic Sclerosis–Related Pulmonary Hypertension. Arthritis Rheumatol. Published 11 May 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →