loading page

Evaluating the performance of ChatGPT in clinical pharmacy
  • +3
  • Xiaoru Huang,
  • Dannya Estau,
  • Xuening Liu,
  • Yang Yu,
  • Jiguang Qin,
  • Zijian Li
Xiaoru Huang
Author Profile
Dannya Estau
Author Profile
Xuening Liu
Author Profile
Jiguang Qin
Author Profile
Zijian Li

Corresponding Author:lizijian@bjmu.edu.cn

Author Profile

Abstract

Aim To evaluate the performance of ChatGPT in key areas of clinical pharmacy practice, including prescription review, patient medication education, adverse drug reaction (ADR) recognition, ADR causality assessment, and drug counseling. Methods Quantitative and qualitative analyses were conducted to assess the accuracy and quality of ChatGPT in comparison to those of the clinical pharmacist. Results The results indicate that ChatGPT is excellent in drug counseling and weak in prescription review, patient medication education, ADR recognition, and ADR causality. Conclusions While ChatGPT holds promise in clinical pharmacy practice as a supplementary tool, the ability of ChatGPT to handle complex problems needs further improvement and refinement.
26 Apr 2023Submitted to British Journal of Clinical Pharmacology
26 Apr 2023Submission Checks Completed
26 Apr 2023Assigned to Editor
26 Apr 2023Review(s) Completed, Editorial Evaluation Pending
29 Apr 2023Reviewer(s) Assigned
16 May 2023Editorial Decision: Revise Major
15 Jun 20231st Revision Received
15 Jun 2023Submission Checks Completed
15 Jun 2023Assigned to Editor
15 Jun 2023Review(s) Completed, Editorial Evaluation Pending
16 Jun 2023Reviewer(s) Assigned
10 Jul 2023Editorial Decision: Revise Minor
01 Aug 20232nd Revision Received
02 Aug 2023Submission Checks Completed
02 Aug 2023Assigned to Editor
02 Aug 2023Review(s) Completed, Editorial Evaluation Pending
14 Aug 2023Editorial Decision: Accept