Pretreatment mortality risk prediction model in patients with polymyositis/dermatomyositis-associated interstitial lung disease
Authors' conclusion
We developed and validated an evidence-based mortality risk prediction model with simple, readily accessible clinical variables in patients with PM/DM-ILD, which may inform clinical decision-making.
Study context
- Population
- Patients with PM/DM-ILD admitted to Nanjing Drum Hospital, 2016–2021
- Participants
- 418 patients
- Comparison
- Development vs Validation
- Developmentn = 282
- Validationn = 136
- Outcome
- Mortality within 1 year
- Follow-up
- 1 year
Methodological detailssingle-centre, least absolute shrinkage and selection operator (LASSO) logistic regression, random split into development and validation cohorts, internal validation
- Single-centre
- LASSO logistic regression
- Random split into development and validation cohorts
- Internal validation
Performance
As reported in the abstract
Discrimination of the mortality risk prediction model (age, arthralgia, anti-MDA5 antibody status, high-resolution CT pattern, laboratory risk score [CRP, lactate dehydrogenase, CD3+CD4+ T cell counts, PO2/FiO2])
AUC
0.869
95% CI 0.811 to 0.910
Further findings
Internal validation, sensitivity analyses and comparison against previous models
- Further confirmed the robustness of the prediction model
Original publication
Pretreatment mortality risk prediction model in patients with polymyositis/dermatomyositis-associated interstitial lung disease. RMD Open. Published 24 April 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →