An unsupervised approach using BioClinicalBERT embeddings and DEC clustering classifies surgical transcripts into immediate, urgent, and elective levels, validated by experts and followed by a BiLSTM classifier with robust performance on unseen data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unsupervised Neural Network for Automated Classification of Surgical Urgency Levels in Medical Transcriptions
An unsupervised approach using BioClinicalBERT embeddings and DEC clustering classifies surgical transcripts into immediate, urgent, and elective levels, validated by experts and followed by a BiLSTM classifier with robust performance on unseen data.