TY - JOUR
T1 - Integration and Assessment of ChatGPT in Medical Case Reporting
T2 - A Multifaceted Approach
AU - Lin, Kuan Chen
AU - Chen, Tsung An
AU - Lin, Ming Hwai
AU - Chen, Yu Chun
AU - Chen, Tzeng-Ji
N1 - Publisher Copyright:
© 2024 by the authors.
PY - 2024/4
Y1 - 2024/4
N2 - ChatGPT, a large language model, has gained significance in medical writing, particularly in case reports that document the course of an illness. This article explores the integration of ChatGPT and how ChatGPT shapes the process, product, and politics of medical writing in the real world. We conducted a bibliometric analysis on case reports utilizing ChatGPT and indexed in PubMed, encompassing publication information. Furthermore, an in-depth analysis was conducted to categorize the applications and limitations of ChatGPT and the publication trend of application categories. A total of 66 case reports utilizing ChatGPT were identified, with a predominant preference for the online version and English input by the authors. The prevalent application categories were information retrieval and content generation. Notably, this trend remained consistent across different months. Within the subset of 32 articles addressing ChatGPT limitations in case report writing, concerns related to inaccuracies and a lack of clinical context were prominently emphasized. This pointed out the important role of clinical thinking and professional expertise, representing the foundational tenets of medical education, while also accentuating the distinction between physicians and generative artificial intelligence.
AB - ChatGPT, a large language model, has gained significance in medical writing, particularly in case reports that document the course of an illness. This article explores the integration of ChatGPT and how ChatGPT shapes the process, product, and politics of medical writing in the real world. We conducted a bibliometric analysis on case reports utilizing ChatGPT and indexed in PubMed, encompassing publication information. Furthermore, an in-depth analysis was conducted to categorize the applications and limitations of ChatGPT and the publication trend of application categories. A total of 66 case reports utilizing ChatGPT were identified, with a predominant preference for the online version and English input by the authors. The prevalent application categories were information retrieval and content generation. Notably, this trend remained consistent across different months. Within the subset of 32 articles addressing ChatGPT limitations in case report writing, concerns related to inaccuracies and a lack of clinical context were prominently emphasized. This pointed out the important role of clinical thinking and professional expertise, representing the foundational tenets of medical education, while also accentuating the distinction between physicians and generative artificial intelligence.
KW - artificial intelligence
KW - case reports
KW - clinical thinking
KW - health science
KW - LLM
KW - medical writing
UR - http://www.scopus.com/inward/record.url?scp=85191535252&partnerID=8YFLogxK
U2 - 10.3390/ejihpe14040057
DO - 10.3390/ejihpe14040057
M3 - Article
AN - SCOPUS:85191535252
SN - 2174-8144
VL - 14
SP - 888
EP - 901
JO - European Journal of Investigation in Health, Psychology and Education
JF - European Journal of Investigation in Health, Psychology and Education
IS - 4
ER -