MCI-to-AD Prediction
Cross-source consensus on MCI-to-AD Prediction from 1 sources and 4 claims.
1 sources · 4 claims
Benefits
Comparisons
Evidence quality
Highlighted claims
- The 16-feature GeoSAE representation achieved the highest AUC among the tested single-scan MCI-to-AD prediction methods. — GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
- GeoSAE outperformed raw foundation model embeddings and several dimensionality-reduction or autoencoder baselines. — GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
- Randomly selected alive GeoSAE features performed near chance, so prediction gains were not caused by arbitrary sparse subsampling. — GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
- Removing non-specific features improved AUC, suggesting they added noise rather than useful conversion signal. — GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models