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

AIMS: To 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. METHODS: Questions 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. RESULTS: The 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. 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.

Therapeutic drug monitoring guidelines in oncology: what do we know and how to move forward? Insights from a systematic review.

Background: Compared with anti-infective drugs, immunosuppressants and other fields, the application of therapeutic drug monitoring (TDM) in oncology is somewhat limited. Objective: We aimed to provide a comprehensive understanding of TDM guidelines for antineoplastic drugs and to promote the development of individualized drug therapy in oncology. Design: This study type is a systematic review. Data sources and methods: This study was performed and reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 statement. Databases including PubMed, Embase, the official websites of TDM-related associations and Chinese databases were comprehensively searched up to March 2023. Two investigators independently screened the literature and extracted data. The methodological and reporting quality was evaluated using the Appraisal of Guidelines for Research and Evaluation II (AGREE II) and the Reporting Items for Practice Guidelines in Healthcare (RIGHT), respectively. Recommendations and quality evaluation results were presented by visual plots. This study was registered in PROSPERO (No. CRD42022325661). Results: A total of eight studies were included, with publication years ranging from 2014 to 2022. From the perspective of guideline development, two guidelines were developed using evidence-based methods. Among the included guidelines, four guidelines were for cytotoxic antineoplastic drugs, three for small molecule kinase inhibitors, and one for antineoplastic biosimilars. Currently available guidelines and clinical practice provided recommendations of individualized medication in oncology based on TDM, as well as influencing factors. With regard to methodological quality based on AGREE II, the average overall quality score was 55.21%. As for the reporting quality by RIGHT evaluation, the average reporting rate was 53.57%. Conclusion: From the perspective of current guidelines, TDM in oncology is now being expanded from cytotoxic antineoplastic drugs to newer targeted treatments. Whereas, the types of antineoplastic drugs involved are still small, and there is still room for quality improvement. Furthermore, the reflected gaps warrant future studies into the exposure-response relationships and population pharmacokinetics models.

Status and Quality of Guidelines for Therapeutic Drug Monitoring Based on AGREE II Instrument.

BACKGROUND: With the progress of therapeutic drug monitoring (TDM) technology and the development of evidence-based medicine, many guidelines were developed and implemented in recent decades. OBJECTIVE: The aim was to evaluate the current status of TDM guidelines and provide suggestions for their development and updates based on Appraisal of Guidelines for Research and Evaluation (AGREE) II. METHODS: The TDM guidelines were systematically searched for among databases including PubMed, Embase, China National Knowledge Infrastructure, Wanfang Data, and the Chinese biomedical literature service system and the official websites of TDM-related associations. The search period was from inception to 6 April 2023. Four researchers independently screened the literature and extracted data. Any disagreement was discussed and reconciled by another researcher. The quality of guidelines was assessed using the AGREE II instrument. RESULTS: A total of 92 guidelines were included, including 57 technical guidelines, three management guidelines, and 32 comprehensive guidelines. The number of TDM guidelines has gradually increased since 1979. The United States published the most guidelines (20 guidelines), followed by China (15 guidelines) and the United Kingdom (ten guidelines), and 23 guidelines were developed by international organizations. Most guidelines are aimed at adult patients only, while 28 guidelines include special populations. With respect to formulation methods, there are 23 evidence-based guidelines. As for quality evaluation results based on AGREE II, comprehensive guidelines scored higher (58.16%) than technical guidelines (51.36%) and administrative guidelines (50.00%). CONCLUSION: The number of TDM guidelines, especially technical and comprehensive ones, has significantly increased in recent years. Most guidelines are confronted with the problems of unclear methodology and low quality of evidence according to AGREE II. More evidence-based research on TDM and high-quality guideline development is recommended to promote individualized therapy.