Development and Evaluation of a Custom GPT-Based Artificial Intelligence Clinical Decision Support System for Emergency Department Interdepartmental Consultation Automation

초록

Objectives: This study aimed to develop a custom GPT-based, knowledge-guided documentation support system that draftsemergency department (ED) interdepartmental consultation requests from minimal free-text input and evaluate its feasibility,usability, and workflow integration. Methods: The system generates a patient summary, recommended consulting department,structured consultation draft, and clinical reference notes from brief natural language input, including age, chiefconcern, and key findings. Two public AI Hub datasets, the Essential Medical Knowledge Dataset (Dataset No. 71875) andthe Specialized Medical Knowledge Dataset (Dataset No. 71874), were used to guide prompt construction and constrain outputstructure rather than for model training. Department recommendation concordance was assessed using 22 de-identifiedED consultation scenarios purposively selected across multiple specialties. The documented department was removed fromthe input and compared with the system’s recommendation. A post-use survey of 10 emergency physicians and residents assessedworkflow utility, clinical appropriateness, usability, reflection of relevant information, perceived patient safety, adoptionintention, and editing requirements using 5-point Likert scales. Results: In the 22-case pilot set, the system’s recommendeddepartment aligned with the historically documented department in all cases under controlled conditions. Given thesmall sample size and study design, this finding represents preliminary evidence of workflow alignment rather than definitivevalidation of clinical performance. Conclusions: The proposed system demonstrates the feasibility of large language modelenableddocumentation support for generating standardized ED consultation requests, potentially reducing documentationburden. The system is intended to support, not replace, clinical decision-making, and clinician review remains essential. With further validation, this approach may be adaptable to other clinical referral contexts.

키워드