@inproceedings{chen-etal-2026-self,
    title = "Why Do Self-Harm Prediction Models Struggle to Generalise? {--} Lexical and Semantic Variations in Emergency Department Triage Notes",
    author = "Chen, Liuliu  and
      Conway, Mike  and
      Robinson, Jo  and
      Rozova, Vlada",
    editor = "Zirikly, Aya  and
      Bar, Kfir  and
      MacAvaney, Sean  and
      Ireland, Molly  and
      Ophir, Yaakov  and
      Atzil-Slonim, Dana  and
      Varadarajan, Vasudha  and
      Bedrick, Steven  and
      Desmet, Bart",
    booktitle = "Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology ({CLP}sych 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.clpsych-1.31/",
    pages = "383--388",
    ISBN = "979-8-89176-421-7",
    abstract = "Self-harm presentations to emergency departments (EDs) are strongly associated with higher suicide risk. NLP models have shown strong performance in detecting self-harm from triage notes within single hospitals, yet performance often declines across institutions. To examine potential causes, we compare ED triage notes from two hospitals by analyzing lexical characteristics, highly associated predictive features, and salient topics. Our results reveal variation in lexical expression and feature importance related to self-harm across hospitals, despite consistent core themes such as self-poisoning and self-injury. These documentation differences are associated with reduced cross-site performance. These findings provide insight into how institutional variation affects the identification of self-harm in clinical text and highlight potential methods to improve model generalisability."
}