Replacing the CNN fusion layer in a TabNet+BERT triage model with a Vision Transformer encoder yields ~2% higher accuracy, F1, and ROC AUC on 11,102 emergency-department records, though the evaluation has unresolved inconsistencies.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multimodal Attention-based Deep Learning for Emergency Triage with Electronic Health Records
Replacing the CNN fusion layer in a TabNet+BERT triage model with a Vision Transformer encoder yields ~2% higher accuracy, F1, and ROC AUC on 11,102 emergency-department records, though the evaluation has unresolved inconsistencies.