Lexical and feature-importance differences in self-harm triage notes between two hospitals are linked to reduced cross-site model performance despite shared core themes.
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
-
Why Do Self-Harm Prediction Models Struggle to Generalise? Lexical and Semantic Variations in Emergency Department Triage Notes
Lexical and feature-importance differences in self-harm triage notes between two hospitals are linked to reduced cross-site model performance despite shared core themes.