European Journal of Hospital Pharmacy

To investigate the performance and risk associated with the usage of Chat Generative Pre-trained Transformer (ChatGPT) to answer drug-related questions.A sample of 50 drug-related questions were consecutively collected and entered in the artificial intelligence software application ChatGPT. Answers were documented and rated in a standardised consensus process by six senior hospital pharmacists in the domains content (correct, incomplete, false), patient management (possible, insufficient, not possible) and risk (no risk, low risk, high risk). As reference, answers were researched in adherence to the German guideline of drug information and stratified in four categories according to the sources used. In addition, the reproducibility of ChatGPT's answers was analysed by entering three questions at different timepoints repeatedly (day 1, day 2, week 2, week 3).Overall, only 13 of 50 answers provided correct content and had enough information to initiate management with no risk of patient harm. The majority of answers were either false (38%, n=19) or had partly correct content (36%, n=18) and no references were provided. A high risk of patient harm was likely in 26% (n=13) of the cases and risk was judged low for 28% (n=14) of the cases. In all high-risk cases, actions could have been initiated based on the provided information. The answers of ChatGPT varied over time when entered repeatedly and only three out of 12 answers were identical, showing no reproducibility to low reproducibility.In a real-world sample of 50 drug-related questions, ChatGPT answered the majority of questions wrong or partly wrong. The use of artificial intelligence applications in drug information is not possible as long as barriers like wrong content, missing references and reproducibility remain.

Benedict Morath

Ute Chiriac

Elena Jaszkowski

Carolin Deiß

Hannah Nürnberg

Katrin Hörth

Torsten Hoppe-Tichy

Kim Green

Eur J Hosp Pharm

Performance and risks of ChatGPT used in drug information: an exploratory real-world analysis

ChatGPT在药物信息中的表现与风险：一项探索性真实世界分析

We read with interest the article on ‘Performance and risks of ChatGPT used in drug information: an exploratory realworld analysis’. Morath et al consider the performance and risks of using Chat Generative Pretrained Transformer (ChatGPT) to answer drugrelated questions. In a realworld sample of 50 drugrelated questions, Morath et al found that ChatGPT answered the majority of the questions wrongly or that answers were partially inaccurate. According to Morath et al, it is impossible to use artificial intelligence systems for drug knowledge as long as there are obstacles like inaccurate content, missing references, and repeatability. Artificial intelligence (AI) is a phrase used to describe computational software that draws conclusions from freely available data that may have come from reliable or suspect sources. AI cannot study, approve, or create confidential scientific or medical data. Without human supervision, AI should not be used to generate, update, or approve sensitive content. The reliability of data in AI is a significant and contentious issue. It is vital to think about how AI should be used responsibly and what responsible uses for AI should be. The ChatGPT may provide pertinent information right away even without user participation. Indeed, effective intake management techniques may help prevent misuse. Nonetheless in our opinion, it is crucial to keep in mind that whether or not AI is used ethically and practically is a decision to be made by people, not AI.

Amnuay Kleebayoon

Viroj Wiwanitkit

Performance and risks of ChatGPT used in drug information: comment

ChatGPT在药物信息中的表现与风险：评论

To analyse the economic impact of the use of immune checkpoint inhibitors in fixed-dose regimens and to determine the potential economic savings of using weight-adjusted dosing, as well as to describe the current situation in Spanish hospitals.

Marca Diaz-Rangel

Francisca Sanchez-Rubio

Andrea Drozdz-Vergara

Juan Manuel Collado-Sanz

Sonia Ruiz-Sanchez

Ana Valladolid-Walsh

Ana Cristina Cercos-Lleti

Fixed or weight-adjusted dose in immunotherapy?

免疫疗法中固定剂量还是体重调整剂量？

Tommy Thai

Lisa Hong

Christopher Hauschild

Tomona Iso

Comparison of sodium zirconium cyclosilicate and sodium polystyrene sulfonate in the treatment of acute hyperkalaemia

环硅酸锆钠与聚苯乙烯磺酸钠在治疗急性高钾血症中的比较

David Sapsford

Helen Dufton

Monica Trivedi

Joanne McPeake

Andrew Conway Morris

Retrospective service evaluation of clinical pharmacist involvement in a critical care COVID-19 rehabilitation clinic

重症监护COVID-19康复诊所中临床药师参与的回顾性服务评估

<h3>Background</h3> The use of complementary and alternative medications (CAM) is popular among cancer patients. CAM includes vitamins, minerals, phytotherapy, homeopathy, nutritional supplements and probiotics. CAM use may lead to unwanted risks by interacting with anticancer drugs; therefore, it is important for healthcare providers to be aware of CAM use by their patients. This article describes the prevalence and potential risk of CAM use in an adult Dutch cancer population. This is the first study in which CAM use was investigated using medication reconciliation. <h3>Methods</h3> A descriptive, observational study was conducted at Amsterdam UMC between August 2021 and July 2022. Data regarding the use of CAM was obtained by medication reconciliation reviews with inpatients and outpatients with cancer who received systemic anticancer treatment. Acquired data were evaluated by the research team, and the risks of interactions were classified into relevant, potential, unknown or no interaction. Ultimately, patient-specific recommendations on the use of CAM were provided. <h3>Results</h3> Of the 100 included patients, 73% used CAM during the past year and 41% used CAM actively while receiving anticancer treatment. The most common CAM were vitamins and multivitamins (both 28%). Some 10% of CAM were classified as having a relevant interaction with one or more concurrently used anticancer drugs. No association between age or gender and CAM use was found, while outpatients used significantly more CAM than inpatients (72.7% vs 32.1%; p=0.001). Patients received personalised advice from the hospital pharmacy about their CAM use. <h3>Conclusions</h3> More than 40% of oncology patients investigated in this study used CAM while receiving anticancer treatment, leading to unwanted risks. This prevalence is higher than reported in other studies, possibly due to the use of medication reconciliation interviews. To guarantee safety and efficacy of anticancer treatment, communication between healthcare professionals and patients about CAM is essential.

Maurien D Rombouts

Rowan M Y Karg

Shiewanie S P Raddjoe

Mirjam Crul

Over 40% of cancer patients use complementary and alternative medications while receiving anticancer treatment

超过40%的癌症患者在抗癌治疗期间使用补充和替代药物

Jinming Cao

Zhicong Chen

Feng Xu

Correspondence on: ‘Patient reported medication-related problems, adherence and waste of oral anticancer medication over time’ by van den Bemt<i>et al</i>

关于van den Bemt等人《患者报告的药物相关问题、依从性及口服抗癌药物浪费随时间变化》的通信

Abbreviation	Eur J Hosp Pharm
Journal Impact	1.41
Quartiles(Global)	PHARMACOLOGY & PHARMACY(Q3)

ISSN	2047-9956, 2047-9964
h-index	24

Publication Information	Publisher: European Association of Hospital Pharmacists (EAHP)，Publishing cycle: ，Journal Type: journal，Open Access Journals: No
Basic data	Year of publication: 2012，Proportion of original research papers: 97.22%，Self Citation Rate:N.A.， Gold OA Rate: 0.00%
Average review cycle	网友分享经验：较慢,6-12周
Average recruitment ratio	网友分享经验：容易

European Journal of Hospital Pharmacy

Journal Citation Format

A journal article with 1 author

A journal article with 2 authors

A journal article with 3 authors

A journal article with 5 or more authors

Books Citation Format

Thesis Citation Format

Web sites Citation Format

Patent Citation Format

Staying up late manually editing references? ivySCI automatically matches journals and helps you generate references with a single click.

Share Submission Experience

Performance and risks of ChatGPT used in drug information: an exploratory real-world analysis

Performance and risks of ChatGPT used in drug information: comment

Fixed or weight-adjusted dose in immunotherapy?

Comparison of sodium zirconium cyclosilicate and sodium polystyrene sulfonate in the treatment of acute hyperkalaemia

Retrospective service evaluation of clinical pharmacist involvement in a critical care COVID-19 rehabilitation clinic

Over 40% of cancer patients use complementary and alternative medications while receiving anticancer treatment

Comparison of sodium zirconium cyclosilicate and sodium polystyrene sulfonate in the treatment of acute hyperkalaemia

Retrospective service evaluation of clinical pharmacist involvement in a critical care COVID-19 rehabilitation clinic

Fixed or weight-adjusted dose in immunotherapy?

Correspondence on: ‘Patient reported medication-related problems, adherence and waste of oral anticancer medication over time’ by van den Bemtet al