Patient Triage and Guidance in Emergency Departments Using Large Language Models: Multimetric Study
ChatGPT demonstrated promising capability for supporting patient triage and outpatient guidance in EDs. GPT-4-Turbo showed greater adaptability to prompt engineering, whereas GPT-4o exhibited superior responsiveness and emotional interaction, which are essential for patient-facing tasks. Future studies should explore real-world implementation and address the identified limitations to enhance ChatGPT's clinical integration.
Authors
- Xiaomei Tan (ORCID: https://orcid.org/0000-0002-5347-7115)
- Guangwu Qian (ORCID: https://orcid.org/0000-0001-9241-1699)
- Chenxu Wang (ORCID: https://orcid.org/0009-0009-0751-0242)
- Yaoyu Fu (ORCID: https://orcid.org/0000-0002-5890-4745)
- Shuhan Li (ORCID: https://orcid.org/0009-0005-8225-944X)
- Q W Ren (ORCID: https://orcid.org/0000-0003-0712-9299)
- Rong Yin (ORCID: https://orcid.org/0000-0003-4596-5407)
- Di Liu (ORCID: https://orcid.org/0009-0005-6433-5904)
- Fei Wang (ORCID: https://orcid.org/0009-0005-5211-7926)
- Kang Li (ORCID: https://orcid.org/0000-0002-8136-9816)
- Yu Cao (ORCID: https://orcid.org/0000-0003-4715-7331)
Institutions
- Sichuan University (CN)
- West China Medical Center of Sichuan University (CN)
- Queen Mary Hospital (CN)
- West China Hospital of Sichuan University (CN)
- Chengdu University (CN)
- University of Hong Kong (HK)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-05-15
- DOI
- https://doi.org/10.2196/71613
- Citations
- 10
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 6.54