Evaluating the performance of ChatGPT in clinical pharmacy: A comparative study of ChatGPT and clinical pharmacists

Abstract

AimsTo evaluate the performance of chat generative pretrained transformer (ChatGPT) in key domains of clinical pharmacy practice, including prescription review, patient medication education, adverse drug reaction (ADR) recognition, ADR causality assessment and drug counselling.MethodsQuestions and clinical pharmacist's answers were collected from real clinical cases and clinical pharmacist competency assessment. ChatGPT's responses were generated by inputting the same question into the ‘New Chat’ box of ChatGPT Mar 23 Version. Five licensed clinical pharmacists independently rated these answers on a scale of 0 (Completely incorrect) to 10 (Completely correct). The mean scores of ChatGPT and clinical pharmacists were compared using a paired 2‐tailed Student's t‐test. The text content of the answers was also descriptively summarized together.ResultsThe quantitative results indicated that ChatGPT was excellent in drug counselling (ChatGPT: 8.77 vs. clinical pharmacist: 9.50, P = .0791) and weak in prescription review (5.23 vs. 9.90, P = .0089), patient medication education (6.20 vs. 9.07, P = .0032), ADR recognition (5.07 vs. 9.70, P = .0483) and ADR causality assessment (4.03 vs. 9.73, P = .023). The capabilities and limitations of ChatGPT in clinical pharmacy practice were summarized based on the completeness and accuracy of the answers. ChatGPT revealed robust retrieval, information integration and dialogue capabilities. It lacked medicine‐specific datasets as well as the ability for handling advanced reasoning and complex instructions.ConclusionsWhile ChatGPT holds promise in clinical pharmacy practice as a supplementary tool, the ability of ChatGPT to handle complex problems needs further improvement and refinement.