Filtering out high-uncertainty predictions from a transformer-random forest ensemble improves Alzheimer's disease classification accuracy on the remaining quarter of test samples, but overall performance stays modest.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
q-bio.GN 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Uncertainty-Aware Genomic Classification of Alzheimer's Disease: A Transformer-Based Ensemble Approach with Monte Carlo Dropout
Filtering out high-uncertainty predictions from a transformer-random forest ensemble improves Alzheimer's disease classification accuracy on the remaining quarter of test samples, but overall performance stays modest.