eISSN 2097-6054 ISSN 1672-9234 CN 11-5289/R
Responsible Institution:China Association for Science and Technology
Publishing:Chinese Nursing Journals Publishing House Co.,Ltd.
Sponsor:Chinese Nursing Association
Source journal for Chinese Science Citation Database
China Academic Journals Full-text Database
China Core Journal Alternative Database
Scopus

Chinese Journal of Nursing Education ›› 2025, Vol. 22 ›› Issue (4): 398-402.doi: 10.3761/j.issn.1672-9234.2025.04.003

• AI-powered Nursing Education • Previous Articles     Next Articles

Application of ChatGPT in self-directed answers to nursing problems and measures for surgical patients

LI Peng(),ZHANG Yuanhui(),TANG Long,LIU Shan,ZHENG Xiaoni,Jianchun Ji,LIU Jian,LONG Teng   

  • Received:2025-01-02 Online:2025-04-15 Published:2025-04-16

Abstract:

Objective To evaluate the accuracy of ChatGPT-4 in autonomously answering nursing questions and measures for surgical patients,and to provide a reference for the intelligent reform of nursing education.Methods Thirty inpatient cases from a tertiary first-class hospital in 2024 were selected as analytical data. Nursing problems and measures were generated following steps of pre-training input,writing instructional prompts,and inputting instructions. Five nursing experts evaluated the accuracy based on a unified scoring standard,and consistency was tested using Fleiss’s Kappa test and Cronbach’s α coefficient.Results The accuracy of nursing questions and measures for the 30 cases was rated as “excellent” at 85.3% and 80.0%,respectively. The Fleiss’s Kappa test values for pairwise comparison of expert scores for each case ranged from 0.433 to 0.763,and the overall Cronbach’s α coefficients for nursing questions and measures across all cases were 0.908 and 0.943,respectively.Conclusion The overall accuracy of autonomously generated nursing questions and measures by ChatGPT-4 is acceptable,reflecting the potential of large language models to serve as teaching aids. However,further judgment of the generated information is necessary,which can provide a reference for the further application and development of artificial intelligence in the field of nursing education.

Key words: ChatGPT-4, Artificial Intelligence, Nursing problems, Nursing measures, Accuracy