Age Deconfounding
Cross-source consensus on Age Deconfounding from 1 sources and 4 claims.
1 sources · 4 claims
How it works
Benefits
Evidence quality
Highlighted claims
- Clinical annotation used partial Spearman correlations that controlled for age. — GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
- Age deconfounding was necessary because raw age correlations dominated diagnosis correlations in the reported analysis. — GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
- Alive features were assigned clinical categories based on the strongest significant non-age age-partial correlation after FDR correction. — GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
- Partial Spearman correlations let feature labels reflect diagnosis, sex, APOE4, and comorbidities after removing age-related variance. — GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models