Sjögren's disease & overlap diseases
Predicting autoimmune thyroiditis in primary Sjogren’s syndrome patients using a random forest classifier: a retrospective study
Authors' conclusion
Analyzing clinical and laboratory data from 96 pSS patients, the Random Forest model demonstrated superior performance (AUC = 0.755), identifying age, IgG levels, complement component 4 (C4), and absence of dry mouth as primary predictors.
Study context
- Population
- Patients with Primary Sjogren's syndrome (pSS), divided into positive and negative thyroid autoantibody (TPOAb and TgAb) groups
- Participants
- 96 patients
- Exposure
- Random Forest Classifier vs three other machine learning algorithms for predicting positive thyroid autoantibodies
- Outcome
- Prediction of positive thyroid autoantibodies (TPOAb and TgAb) in pSS patients
Methodological detailsmachine learning, random forest classifier
- Machine learning
- Random forest classifier
Main finding
As reported in the abstract
Prediction of positive thyroid autoantibodies
| Group | AUC |
|---|---|
| Random Forest Classifier | 0.755 |
Random Forest Classifier
AUC0.755
Observational data: associations, not effects.
Original publication
Predicting autoimmune thyroiditis in primary Sjogren’s syndrome patients using a random forest classifier: a retrospective study. Arthritis Res Ther. Published 2 January 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →