ELICITED: EHR-grounded Longitudinal Interactive Conversations for Information-seeking Triage Evaluation and Decision-making
2026-08-10 • Computation and Language
Computation and Language
AI summaryⓘ
The authors point out that in emergency rooms, doctors need to quickly decide who needs urgent care but often start with very little information. They highlight that important details are gathered through conversations, which current evaluation methods don’t fully capture since they only look at fixed moments of patient data. To address this, the authors created EHR2Dial-Triage, a tool that simulates and links triage conversations to real patient records over time. This helps study how information is gathered and used during triage, improving understanding of the process as a back-and-forth dialogue rather than a one-time snapshot.
Emergency Department (ED)TriageElectronic Health Record (EHR)Clinical CommunicationMIMIC-IV-EDInformation ElicitationEmergency Severity IndexClinical Decision MakingPatient Dialogue
Authors
Haohao Zhu, Xiaolin Shi, Jiayu Zhou
Abstract
Emergency-department (ED) triage requires clinicians to rapidly identify patients who need immediate attention, determine who can safely wait, and prioritize limited clinical resources. At presentation, however, information may be limited to a chief complaint and initial vital signs. Clinically important details, including symptom onset and progression, associated symptoms, medical history, and medication use, are often obtained through focused conversation. Effective triage therefore requires clinicians to identify information gaps, ask appropriate follow-up questions, and update their assessment as new evidence becomes available. Most existing ED benchmarks evaluate acuity prediction from a fixed clinical snapshot. Although this formulation measures predictive performance after patient information has been assembled, it does not capture the interactive process through which triage-relevant evidence is elicited and interpreted. Existing medical dialogue datasets support the study of clinical communication, but dialogue statements are not always linked to temporally ordered events in the electronic health record (EHR). We introduce EHR2Dial-Triage, an agentic conversation-generation framework and benchmark grounded in MIMIC-IV-ED. The framework constructs triage conversations under explicit role-based and temporal information boundaries. Each accepted patient disclosure is linked to its supporting EHR event and the first dialogue turn at which it becomes available. EHR2Dial-Triage enables controlled evaluation of information elicitation, evidence use, five-level Emergency Severity Index prediction, and patient-facing communication across models and patient personas. It provides a structured setting for studying conversational triage as a dynamic process of clinical information acquisition, reasoning, and communication.