TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records
This work addresses data scarcity for emergency triage simulation, though it is incremental as it builds on existing methods for generating synthetic data from structured records.
The authors tackled the problem of limited data for emergency triage research by introducing TriageSim, a framework that generates synthetic nurse-patient conversations from structured EHRs, producing a corpus of ~800 transcripts and audio with modest agreement in acuity classification across modalities.
Research in emergency triage is restricted to structured electronic health records (EHR) due to regulatory constraints on nurse-patient interactions. We introduce TriageSim, a simulation framework for generating persona-conditioned triage conversations from structured records. TriageSim enables multi-turn nurse-patient interactions with explicit control over disfluency and decision behaviour, producing a corpus of ~800 synthetic transcripts and corresponding audio. We use a combination of automated analysis for linguistic, behavioural and acoustic fidelity alongside manual evaluation for medical fidelity using a random subset of 50 conversations. The utility of the generated corpus is examined via conversational triage classification. We observe modest agreement for acuity levels across three modalities: generated synthetic text, ASR transcripts, and direct audio inputs. The code, persona schemata and triage policy prompts for TriageSim will be available upon acceptance.