Lupus & antiphospholipid syndrome
Development of a predictive model for systemic lupus erythematosus incidence risk based on environmental exposure factors
Authors' conclusion
We created a user-friendly dynamic nomogram for predicting the relative risk of SLE onset based on occupational and living environmental exposures.
Study context
- Population
- Individuals diagnosed with systemic lupus erythematosus (SLE) and healthy volunteers; basic information, occupational exposure history and environmental exposure data
- Participants
- 316 vs 851
- Comparison
- SLE vs healthy volunteers
- SLEn = 316
- Healthy volunteersn = 851reference
- Outcome
- Predictive performance of the ForestMDG model for SLE onset
Methodological detailsprediction model development, 70/30 random split into training and validation sets, multivariate logistic regression, leave-one-out cross-validation, Dynamic nomogram developed from the best model, accessible online
- Prediction model development
- 70/30 random split into training and validation sets
- Multivariate logistic regression
- Leave-one-out cross-validation
- Dynamic nomogram developed from the best model, accessible online
Main finding
As reported in the abstract
AUC, training set
0.903
95% CI 0.880 to 0.925
AUC, validation set
0.851
95% CI 0.809 to 0.894
Leave-one-out cross-validation accuracy (best of the models)
0.8338
Observational data: associations, not effects.
Original publication
Development of a predictive model for systemic lupus erythematosus incidence risk based on environmental exposure factors. Lupus Sci Med. Published 20 November 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →