Prospective Evaluation of AI Generated History of Present Illness Drafts in the Emergency Department

NCT07804407 — Recruiting, 100 participants, Yonsei University

ClinicalTrials Daily · Areas · Conditions · Drugs · Sponsors ·

Prospective Evaluation of Artificial Intelligence-generated History of Present Illness Drafts in the Emergency Department

Registry	NCT07804407
Status	Recruiting
Study type	Observational
Enrollment	100 (Estimated)
Sponsor	Yonsei University (Other)
Conditions	All Emergency Department Visits Meeting Eligibility Criteria
Interventions	EDnote HPI (AI-generated HPI draft), Conventional physician HPI (Other)
Dates	start 2026-09-01 (estimated), primary completion 2026-12-31 (estimated), completion 2026-12-31 (estimated), first posted 2026-09-04, last updated 2026-09-22
Locations	1 site in South Korea

-Summary

This single-center prospective observational study evaluates whether an on-premise, large language model-based tool (EDnote) that generates a draft history of present illness (HPI) from real-time transcription of the patient-physician encounter produces documentation of higher quality than conventional physician-written HPI in the emergency department. The treating physician writes the conventional HPI blinded to the AI draft. Unedited AI-generated HPI drafts and conventional HPI are compared through blinded review by independent emergency physicians.

Expand all sections · Collapse all

+Arms and interventions

Arm	Type	Interventions	Description
ED patients with EDnote-assisted initial encounter		Other: EDnote HPI (AI-generated HPI draft); Other: Conventional physician HPI	Adult emergency department patients whose initial encounter was recorded by EDnote. While the treating physician conducts usual care and writes the conventional HPI, EDnote generates an AI HPI draft in the background; the physician remains blinded to the draft. Both HPIs are evaluated by independent raters blinded to document source.

EDnote HPI (AI-generated HPI draft) (Other): On-premise large language model-based tool that transcribes the patient-physician encounter in real time and generates an unedited HPI draft. The treating physician is blinded to the AI HPI draft.
Conventional physician HPI (Other): HPI written by the treating emergency physician according to usual practice, blinded to the EDnote-generated HPI draft.

+Outcome measures

Primary outcomes

Encounter-level clinical fact capture rate [At blinded review, within 6 months after each index ED visit]

Secondary outcomes

Modified PDQI-9 score [At blinded review, within 6 months after each index ED visit]: Modified Physician Documentation Quality Instrument-9 (Modified PDQI-9) score. The modified instrument consists of 10 items, each rated from 1 to 5, yielding a total score ranging from 10 to 50. Higher scores indicate better documentation quality.
AI HPI draft generation time [At index ED visit]
Rater identification of document authorship (AI vs. physician-written) [At blinded review, within 6 months after each index ED visit]

+Eligibility

Sex: All, ages: 19 Years to any

Inclusion Criteria:

* Age ≥19 years; presenting to the emergency department; initial encounter documented with EDnote; verbal consent to study participation.

Exclusion Criteria:

* Cardiac arrest; limited ability of both patient and guardian to communicate verbally; refusal of participation.

+Locations (1)

Facility	City	Country	Status
Yonsei University Severance Hospital	Seoul, Seoul City	South Korea	Recruiting