Transferable Self-Harm Surveillance from Emergency Department Triage Notes Using an Evidence-Augmented Machine Learning Approach
2026-06-01 • Computation and Language
Computation and Language
AI summaryⓘ
The authors created a new method to find cases of self-harm by analyzing notes taken when people first arrive at the Emergency Department (ED). They used a combination of traditional machine learning and advanced language models to read these short notes and detect self-harm accurately. Their method worked well not only where it was developed but also at other hospitals without extra training. Additionally, the approach can identify details about how the self-harm happened, which helps provide better information than just saying yes or no to self-harm.
self-harmemergency departmenttriage notesmachine learninglarge language modelsAUPRCexternal validationtransferabilitybinary classificationsurveillance
Authors
Liuliu Chen, Gowri Rajaram, Eleanor Bailey, Katrina Witt, Michelle Lamblin, Jo Robinson, Mike Conway, Vlada Rozova
Abstract
Self-harm is a major public health concern, but current surveillance relying on hospital presentations is inadequate due to the low sensitivity of diagnostic codes. Emergency Department (ED) triage notes, recorded at the initial point of contact, provide a succinct summary of presentations and an opportunity to identify self-harm. We developed a three-stage approach, augmenting traditional machine learning with large language model-based screening and evidence extraction to detect self-harm in ED triage notes. We assessed model transferability across three Australian hospitals. Our approach showed AUPRCs of 0.887 +/- 0.016 and 0.884 +/- 0.012 during internal and external validation. Prospectively, it achieved AUPRC of 0.881 +/- 0.008 at the development site, and 0.879 +/- 0.012 and 0.816 +/- 0.015 at two external sites without site-specific retraining. A key advantage of the approach is that it enables identification of the primary self-harm method with an accuracy of 95%, supporting more granular surveillance beyond binary classification.