A clinical-radiomics integrated nomogram for predicting 5-year survival in RA-associated interstitial lung disease
Authors' conclusion
The integrated nomogram (age, lymphocyte count, Rad-score) enables precise, user-friendly prediction of RA-ILD 5-year survival.
Study context
- Population
- Patients with RA-associated interstitial lung disease (RA-ILD) from two centres
- Participants
- 230 patients2 centres
- Comparison
- Clinical, radiomics and integrated clinical-radiomics models for predicting overall survival (OS)
- Trainingn = 144
- Internal validationn = 37
- External validationn = 49
- Outcome
- OS (5-year survival) prediction
- Follow-up
- 5 years
Methodological detailstwo-centre, internal and external validation, LASSO-Cox regression, nomogram, Radiomics features (n = 1688) selected via variance thresholding, univariate selection and LASSO-Cox; 24 optimal features retained
- Two-centre
- Internal and external validation
- LASSO-Cox regression
- Nomogram
- Radiomics features (n = 1688) selected via variance thresholding, univariate selection and LASSO-Cox; 24 optimal features retained
Performance
As reported in the abstract
Integrated model performance (C-index)
| Test or model | Concordance index (C-index) |
|---|---|
| Training | 0.832 |
| Internal validation | 0.816 |
| External validation | 0.812 |
Concordance index (C-index)
Training0.832
Internal validation0.816
External validation0.812
Further findings
Independent OS predictors (multivariate Cox)
| HR (95% CI) | P value | ||
|---|---|---|---|
| Age | 1.046 (1.013–1.080) | P = 0.006 | |
| Lymphocyte count | 1.385 (1.059–1.812) | P = 0.018 | |
| 0.512Hazard ratio (log scale) |
| Outcome | P value |
|---|---|
| OS by Rad-score (threshold 0.15)High-risk (Rad-score ≥ 0.15) vs Low-risk · significantly shorter OS in high-risk | all P < 0.01 |
Original publication
A clinical-radiomics integrated nomogram for predicting 5-year survival in RA-associated interstitial lung disease. Rheumatology (Oxford). Published 13 April 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →