Australian Emergency Department triage notes

Evidence-Augmented ML for Self-Harm Surveillance in Emergency Department Triage Notes

Researchers developed a three-stage pipeline combining traditional machine learning with LLM-based screening and evidence extraction to detect self-harm in Australian emergency department triage notes. The system achieved AUPRCs around 0.88 in both internal and external validation, and transferred to two external hospital sites without site-specific retraining. A notable capability is identifying the primary self-harm method with 95% accuracy, enabling more granular public health surveillance beyond binary classification.