Systemic sclerosis & Raynaud's
A Multimodal Prediction Model for Diagnosing Pulmonary Hypertension in Systemic Sclerosis
Authors' conclusion
In patients with SSc, a random forest model can aid in the detection of PH with high sensitivity and specificity and may allow for better patient selection for RHC, thereby minimizing patient risk.
Study context
- Population
- Patients with systemic sclerosis (SSc) evaluated for pulmonary hypertension (PH) by right heart catheterization; models using pulmonary function testing, ECG, echocardiography and CT data66 (50.8%) with PH
- Participants
- 130 patients
- Comparison
- Random forest vs classification and regression tree vs logistic regression for predicting PH
- Outcome
- Presence of PH diagnosed by right heart catheterization
Methodological detailsinternal validation (train-test split)
- Internal validation (train-test split)
Performance
As reported in the abstract
Diagnostic performance for PH (best model)
| Test or model | AUC | Sensitivity | Specificity |
|---|---|---|---|
| Random forest | 0.92 (95% CI 0.83-1.00) | 0.95 (95% CI 0.75-1.00) | 0.80 (95% CI 0.56-0.94) |
Random forest
AUC0.92 (95% CI 0.83-1.00)
Sensitivity0.95 (95% CI 0.75-1.00)
Specificity0.80 (95% CI 0.56-0.94)
Original publication
A Multimodal Prediction Model for Diagnosing Pulmonary Hypertension in Systemic Sclerosis. Arthritis Care Res (Hoboken). Published 18 January 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →