Assessing the applicability and appropriateness of ChatGPT in answering clinical pharmacy questions

OBJECTIVES

Clinical pharmacists rely on different scientific references to ensure appropriate, safe, and cost-effective drug use. Tools based on artificial intelligence (AI) such as ChatGPT (Generative Pre-trained Transformer) could offer valuable support. The objective of this study was to assess ChatGPT's capacity to correctly respond to clinical pharmacy questions asked by healthcare professionals in our university hospital.

MATERIAL AND METHODS

ChatGPT's capacity to respond correctly to the last 100 consecutive questions recorded in our clinical pharmacy database was assessed. Questions were copied from our FileMaker Pro database and pasted into ChatGPT March 14 version online platform. The generated answers were then copied verbatim into an Excel file. Two blinded clinical pharmacists reviewed all the questions and the answers given by the software. In case of disagreements, a third blinded pharmacist intervened to decide.

RESULTS

Documentation-related issues (n=36) and drug administration mode (n=30) were preponderantly recorded. Among 69 applicable questions, the rate of correct answers varied from 30 to 57.1% depending on questions type with a global rate of 44.9%. Regarding inappropriate answers (n=38), 20 were incorrect, 18 gave no answers and 8 were incomplete with 8 answers belonging to 2 different categories. No better answers than the pharmacists were observed.

CONCLUSIONS

ChatGPT demonstrated a mitigated performance in answering clinical pharmacy questions. It should not replace human expertise as a high rate of inappropriate answers was highlighted. Future studies should focus on the optimization of ChatGPT for specific clinical pharmacy questions and explore the potential benefits and limitations of integrating this technology into clinical practice.

[Clinical pharmacy in four French-speaking university hospitals, integration and supervision of clinical pharmacists: An exploratory study]

BACKGROUND

Pharmacy practice continues to evolve worldwide. The clinical role of the pharmacists is increasingly recognized and their integration into the health care team is irreversible. Despite this progress, there are still a wide disparity in the scope of practice provided by hospital pharmacists around the world. This disparity can be attributed to a variety of factors.

OBJECTIVES

The primary objective is to describe the organization of clinical pharmacy in four university hospitals in four French-speaking countries. The secondary objective is to identify similarities and differences and to identify perspectives for the future.

METHODS

This is an exploratory cross-sectional descriptive study. The study targeted a university hospital (CHU) in France, Belgium, Switzerland and Canada (Quebec). A volunteer expert pharmacist involved in the management of clinical pharmacy at each hospital was approached at the initiative of a team member. A working group of five pharmacists was set up.

RESULTS

During the year 2021, the group met virtually on ten occasions. Although all institutions have an academic mission, they have very different numbers of beds and volumes of activity. The number of pharmacists is also very different (0.83 FTE pharmacist/1000 admissions in Belgium, 0.22 in France, 0.59 in Switzerland and 2.39 in Quebec). In all countries, pharmacists provide clinical pharmacy services to patients in a centralised or decentralised manner, including, to various extent, prescription analysis, medication reconciliation, pharmaceutical interviews and discharge plans.

CONCLUSIONS

Clinical pharmacy practice is very heterogeneous in a selection of four French-speaking teaching hospitals. Identification of similarities and differences may inspire improvements in the organization of clinical pharmacy activity. This work has contributed to the establishment of a community of practice on clinical pharmacy in the French-speaking world.

Determination of aciclovir and ganciclovir in human plasma by liquid chromatography–spectrofluorimetric detection and stability studies in blood samples

A sensitive HPLC method has been developed for the assay of aciclovir and ganciclovir in human plasma, by HPLC coupled with spectrofluorimetric detection. Plasma (1000 microl), with 9-ethyl-guanine added as internal standard, is submitted to protein precipitation with trichloroacetic acid solution 20%. The supernatant, evaporated to dryness at 37 degrees C, is reconstituted in 100 microl of a solution of sodium heptanosulfonate 0.4% adjusted with acetic acid to pH 2.60 and a 30 microl volume is then injected onto a Nucleosil 100-5 microm C18 column. Aciclovir and ganciclovir are analysed by spectrofluorimetric detection set at 260 nm (excitation) and 380 nm (emission) using a gradient elution program with solvents constituted of acetonitrile and a solution of sodium heptanosulfonate 0.4% adjusted to pH 2.60. The calibration curves are linear between 0.1 and 10 microg/ml. The mean absolute recovery of aciclovir and ganciclovir are 99.2+/-2.5 and 100.3+/-2.5%, respectively. The method is precise (with mean inter-day C.V.s within 1.0-1.6% for aciclovir and 1.2-3.5% for ganciclovir), and accurate (range of inter-day deviations -1.6 to +1.6% for aciclovir and -0.4 to -1.4% for ganciclovir). The method has been applied in stability studies of ganciclovir in patients' blood samples, demonstrating its good stability in plasma at -20 degrees C and at room temperature. The distribution of ganciclovir and aciclovir in plasma and red blood cells was also investigated in vitro in spiking experiments with whole blood, which showed an initial drop of ganciclovir and aciclovir levels in plasma (about -25%) due to the cellular uptake of aciclovir and ganciclovir by red blood cells. The method has been validated and is currently applied in a clinical study assessing the ganciclovir plasma concentration variability after administration of valganciclovir in a population of solid organ transplant patients.