International Journal of Clinical Pharmacy最新文献

{"title":"Students' acceptance and use of generative AI in pharmacy education: international cross-sectional survey based on the extended unified theory of acceptance and use of technology.","authors":"Mohamed Hassan Elnaem, Betul Okuyan, Naeem Mubarak, Abrar K Thabit, Merna Mahmoud AbouKhatwa, Diana Laila Ramatillah, AbdulMuminu Isah, Ali Azeez Al-Jumaili, Nor Ilyani Mohamed Nazar","doi":"10.1007/s11096-025-01936-w","DOIUrl":"10.1007/s11096-025-01936-w","url":null,"abstract":"<p><strong>Background: </strong>Generative artificial intelligence (GenAI) has significant potential implications for pharmacy education, but its ethical, practical, and pedagogical implications have not been fully explored.</p><p><strong>Aim: </strong>This international study evaluated pharmacy students' acceptance and use of GenAI tools using the Extended Unified Theory of Acceptance and Use of Technology (UTAUT).</p><p><strong>Method: </strong>A cross-sectional survey of pharmacy students from nine countries during the first half of 2024 assessed GenAI usage patterns, curricular integration, and acceptance via the Extended UTAUT framework. After appropriate translation and cultural adaptation, exploratory factor analysis (EFA) identified key adoption factors.</p><p><strong>Results: </strong>A total of 2009 responses were received. ChatGPT and Quillbot were the tools most frequently utilised. EFA identified three key dimensions: Utility-Driven Adoption, Affordability and Habitual Integration, and Social Influence. Students rated performance and effort expectancy highly, highlighting their perceived usefulness and ease of use of GenAI tools. In contrast, habit and price value received lower ratings, indicating barriers to habitual use and affordability concerns. Gender disparities were noted, with males demonstrating significantly higher acceptance (p < 0.001). Additionally, country-specific differences were evident, as Malaysia reported a high performance expectancy, while Egypt exhibited low facilitating conditions. Over 20% indicated an over-reliance on GenAI for assignments, raising ethical concerns. Significant gaps were observed, such as limited ethical awareness-only 10% prioritised legal and ethical training-and uneven curricular integration, with 60% reporting no formal exposure to Generative AI.</p><p><strong>Conclusion: </strong>Findings reveal critical gaps in ethical guidance, equitable access, and structured GenAI integration in pharmacy education. A proactive, context-specific strategy is essential to align technological innovation with pedagogical integrity.</p>","PeriodicalId":13828,"journal":{"name":"International Journal of Clinical Pharmacy","volume":" ","pages":"1097-1108"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12335392/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144215749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learnings from research on artificial intelligence enabled solutions in clinical pharmacy practice and education.","authors":"Kreshnik Hoti, Anita E Weidmann, Derek Stewart","doi":"10.1007/s11096-025-01982-4","DOIUrl":"10.1007/s11096-025-01982-4","url":null,"abstract":"","PeriodicalId":13828,"journal":{"name":"International Journal of Clinical Pharmacy","volume":" ","pages":"917-920"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144730305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Conversational agents for pharmaceutical use: insights from the eCCo database.","authors":"Mara Pereira Guerreiro, Helga Rafael Henriques, Elena Mugellini, Leonardo Angelini","doi":"10.1007/s11096-025-01948-6","DOIUrl":"10.1007/s11096-025-01948-6","url":null,"abstract":"<p><p>Conversational agents are computer programmes designed to replicate bidirectional human conversation through spoken or written language, potentially supplemented with nonverbal features. The eCCo database is a searchable repository of primary studies on conversational agents in health and well-being. It catalogs 657 papers currently, published between 1991 and 2022; 51 address the use of medicines. Most of these papers focus on usability rather than rigorous effectiveness or implementation research, underscoring a need for more robust evaluation. The largest category of conversational agents for pharmaceutical use consists of non-embodied agents (n = 24), followed by virtual embodiment only (n = 19), most using virtual humans (n = 16). This database facilitates the comparison and appraisal of existing research in this field, while contributing to a more nuanced understanding of this technology through multidimensional attributes. We aim to enhance the database accuracy and expand its completeness beyond 2022 with the support of the global research community.</p>","PeriodicalId":13828,"journal":{"name":"International Journal of Clinical Pharmacy","volume":" ","pages":"1114-1119"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144674705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of the bedside check of medication appropriateness (BED-CMA) at the hematology ward: a mixed-methods study.","authors":"Greet Van De Sijpe, Lien Cosemans, Jens Neefs, Hannah De Schutter, Tine Van Nieuwenhuyse, Mariëlle Beckers, Johan Maertens, Hélène Schoemans, Peter Vandenberghe, Minne Casteels, Veerle Foulon, Isabel Spriet","doi":"10.1007/s11096-025-01926-y","DOIUrl":"10.1007/s11096-025-01926-y","url":null,"abstract":"<p><strong>Background: </strong>Hematology patients have complex medication regimens and rapidly changing organ function, rendering them susceptible to medication errors. Health information technology can facilitate the detection of inappropriate prescriptions and assist healthcare professionals in enhancing patient safety.</p><p><strong>Aim: </strong>To evaluate the impact of a pharmacist-oriented clinical decision support system, called Bedside Check of Medication Appropriateness (BED-CMA), on inappropriate prescribing at the hematology ward, and to qualitatively assess its impact on the organization of bedside clinical pharmacy practice.</p><p><strong>Method: </strong>A mixed-methods study was conducted at the semi-critical 15-bed hematology ward of UZ Leuven between 2020 and 2023. A pre-post study was performed to evaluate the impact of BED-CMA on residual potentially inappropriate prescriptions (PIPs), defined as those that persisted for at least 24 h after their initial identification. A time trend analysis was performed to identify any potential pre-existing patterns. The BED-CMA intervention consisted of embedding 19 clinical rules into the hospital information system. The pre-intervention cohort received usual clinical pharmacy services. Post-intervention, clinical pharmacists used BED-CMA alerts in addition to standard practices. A focus group discussion with clinical pharmacists assessed the impact on the organization of bedside clinical pharmacy practice.</p><p><strong>Results: </strong>Pre-intervention, 70% (48/69) of initial PIPs remained residual PIPs, which decreased to 20% (13/66) post-intervention (odds ratio 0.11 (95% confidence interval 0.05-0.22, P < .0.0001)). There was no evidence for a pre-existing time trend (P = .0.52). Pharmacists reported improved workflow efficiency through enhanced patient prioritization and prompt identification of PIPs.</p><p><strong>Conclusion: </strong>BED-CMA significantly reduced residual PIPs by streamlining clinical pharmacy practice at a hematology ward.</p>","PeriodicalId":13828,"journal":{"name":"International Journal of Clinical Pharmacy","volume":" ","pages":"1064-1074"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144110548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Developing a machine learning-based predictive model for the analgesic effectiveness of transdermal fentanyl in cancer patients: an interpretable approach.","authors":"Xiaogang Hu, Ya Chen, Yuelu Tang, Xiaoxiao Wang, Lixian Li, Chao Li, Wanyi Chen","doi":"10.1007/s11096-025-01921-3","DOIUrl":"10.1007/s11096-025-01921-3","url":null,"abstract":"","PeriodicalId":13828,"journal":{"name":"International Journal of Clinical Pharmacy","volume":" ","pages":"1120"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144026532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intentions of hospital pharmacists to use digital technology in their daily practice: a cross-sectional survey using the Theory of Planned Behaviour.","authors":"Kamer Tecen-Yucel, Nesligül Ozdemir-Ayduran, Emre Kara, Kutay Demirkan, Betul Okuyan","doi":"10.1007/s11096-025-01868-5","DOIUrl":"10.1007/s11096-025-01868-5","url":null,"abstract":"<p><strong>Background: </strong>Digital technology has been widely integrated into healthcare. This encompasses knowledge, skills, and practices related to the development and use of health technologies. The behavior of health professionals is critical to the adoption of these technologies.</p><p><strong>Aim: </strong>This study aimed to investigate factors associated with hospital pharmacists' intention to use digital technology in their daily practice using the Theory of Planned Behaviour (TPB).</p><p><strong>Method: </strong>In this cross-sectional study, a paper-based survey was conducted among hospital pharmacists who attended the National Hospital Pharmacy Congress in Türkiye in March 2022. A valid and reliable Turkish scale based on the TBP was used to identify factors associated with the intention score by a multiple linear regression model.</p><p><strong>Results: </strong>One hundred ten participants completed the survey (response rate: 44.0%). Seventy percent of pharmacists reported that they had not received prior training in digital technologies. More than eighty percent of the participants said they intend to use digital technology in daily practice. The higher scores of attitudes (p = 0.005), self-efficacy (p < 0.001), and working place (p = 0.017) were associated with increased intention scores.</p><p><strong>Conclusion: </strong>Positive attitudes, higher self-efficacy, and working in tertiary hospitals were associated with hospital pharmacists' intentions to use digital technology in daily practice. These factors should be considered in developing interventions to promote digital technology use of hospital pharmacists.</p>","PeriodicalId":13828,"journal":{"name":"International Journal of Clinical Pharmacy","volume":" ","pages":"1024-1033"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12335391/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143381945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting survival benefits of immune checkpoint inhibitor therapy in lung cancer patients: a machine learning approach using real-world data.","authors":"Lingyun Pan, Li Mu, Haike Lei, Siwei Miao, Xiaogang Hu, Zongwei Tang, Wanyi Chen, Xiaoxiao Wang","doi":"10.1007/s11096-024-01818-7","DOIUrl":"10.1007/s11096-024-01818-7","url":null,"abstract":"<p><strong>Background: </strong>Due to the heterogeneity in the effectiveness of immunotherapy for lung cancer, identifying predictors is crucial.</p><p><strong>Aim: </strong>This study aimed to develop a machine learning model to identify predictors of overall survival in lung cancer patients treated with immune checkpoint inhibitors (ICIs).</p><p><strong>Method: </strong>A retrospective analysis was performed on data from 1314 lung cancer patients at the Chongqing University Cancer Hospital from September 2018 to September 2022. We used the random survival forest (RSF) model to identify survival-influencing factors, using backward elimination for variable selection. A Cox proportional hazards (CPH) model was constructed using the most significant predictors. We assessed model performance and generalizability using time-dependent receiver operating characteristics (ROC) and predictive error curves.</p><p><strong>Results: </strong>The RSF model demonstrated better predictive accuracy than the CPH (IBS 0.17 vs. 0.17; C-index 0.91 vs. 0.68), with better discrimination and prediction performance. The influential variables identified included D-dimer, Karnofsky performance status, albumin, surgery, TNM stage, platelet count, and age. The RSF model, which incorporated these variables, achieved area under the curve (AUC) scores of 0.95, 0.94, and 0.98 for 1-, 3-, and 5-year survival predictions, respectively, in the training set. The validation set showed AUCs of 0.94, 0.90, and 0.95, respectively, exceeding the performance of the CPH model.</p><p><strong>Conclusion: </strong>The study successfully developed a machine learning model that accurately predicted the survival benefits of ICI therapy in lung cancer patients, supporting clinical decision-making in lung cancer treatment.</p>","PeriodicalId":13828,"journal":{"name":"International Journal of Clinical Pharmacy","volume":" ","pages":"981-989"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142545315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Defining histamine H2 receptor antagonist response in critically ill patients with heart failure: a machine learning cluster analysis.","authors":"Li-Juan Yang, Fang Yu, Yu Chen, Xin Zhang, Sun-Jun Yin, Ping Wang, Meng-Han Jiang, Hai-Ying Yang, Jia-De Zhu, Ran Xu, Wen-Ke Cai, Gong-Hao He","doi":"10.1007/s11096-025-01892-5","DOIUrl":"10.1007/s11096-025-01892-5","url":null,"abstract":"<p><strong>Background: </strong>Recent studies showed histamine H2 receptor antagonists (H2RAs) exposure was associated with reduced mortality in heart failure (HF) patients. However, specific HF patients who are sensitive to H2RAs exposure or not are yet to be further defined.</p><p><strong>Aim: </strong>This study aimed to identify HF patient characteristics that may benefit from H2RAs exposure.</p><p><strong>Method: </strong>Neural network-based variational autoencoders and Gaussian Mixture Model (GMM) clustering methods were employed to classify the critically ill patients with HF exposed to H2RAs based on Medical Information Mart for Intensive Care III and IV databases. Binary logistic and multivariable Cox regression analysis based on propensity score matching (PSM) were employed to estimate the association between H2RAs exposure of each cluster and all-cause mortality of included patients.</p><p><strong>Results: </strong>A total of 9,585 H2RAs users among 23,855 included HF patients were identified into four clusters according to GMM clustering: cluster 1 (combined with acute kidney failure, septic shock, and pneumonia), cluster 2 (combined with atrial fibrillation), cluster 3 (combined with coronary artery disease (CAD) and/or had higher urine output), and cluster 4 (co-administered with calcium-antagonists). The cluster 3 patients were significantly associated with reduced all-cause mortality compared with non-H2RAs users after PSM, which were further validated in 14,280 HF patients from the large multi-center electronic intensive care unit Collaborative Research Database (eICU-CRD).</p><p><strong>Conclusion: </strong>Histamine H2 receptor antagonist exposure was more sensitive in HF patients who were combined with CAD. Furthermore, male HF patients or those with higher urine output were also sensitive to H2RAs exposure.</p>","PeriodicalId":13828,"journal":{"name":"International Journal of Clinical Pharmacy","volume":" ","pages":"1087-1096"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143582241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating a customised large language model (DELSTAR) and its ability to address medication-related questions associated with delirium: a quantitative exploratory study.","authors":"Katharina Teresa Spagl, Edward William Watson, Adam Jatowt, Anita Elaine Weidmann","doi":"10.1007/s11096-025-01900-8","DOIUrl":"10.1007/s11096-025-01900-8","url":null,"abstract":"<p><strong>Background: </strong>A customised large language model (LLM) could serve as a next-generation clinical pharmacy research assistant to prevent medication-associated delirium. Comprehensive evaluation strategies are still missing.</p><p><strong>Aim: </strong>This quantitative exploratory study aimed to develop an approach to comprehensively assess the domain-specific customised delirium LLM (DELSTAR) ability, quality and performance to accurately address complex clinical and practice research questions on delirium that typically require extensive literature searches and meta-analyses.</p><p><strong>Method: </strong>DELSTAR, focused on delirium-associated medications, was implemented as a 'Custom GPT' for quality assessment and as a Python-based software pipeline for performance testing on closed and leading open models. Quality metrics included statement accuracy and data credibility; performance metrics covered F1-Score, sensitivity/specificity, precision, AUC, and AUC-ROC curves.</p><p><strong>Results: </strong>DELSTAR demonstrated more accurate and comprehensive information compared to information retrieved by traditional systematic literature reviews (SLRs) (p < 0.05) and accessed Application Programmer Interfaces (API), private databases, and high-quality sources despite mainly relying on less reliable internet sources. GPT-3.5 and GPT-4o emerged as the most reliable foundation models. In Dataset 2, GPT-4o (F1-Score: 0.687) and Llama3-70b (F1-Score: 0.655) performed best, while in Dataset 3, GPT-3.5 (F1-Score: 0.708) and GPT-4o (F1-Score: 0.665) led. None consistently met desired threshold values across all metrics.</p><p><strong>Conclusion: </strong>DELSTAR demonstrated potential as a clinical pharmacy research assistant, surpassing traditional SLRs in quality. Improvements are needed in high-quality data use, citation, and performance optimisation. GPT-4o, GPT-3.5, and Llama3-70b were the most suitable foundation models, but fine-tuning DELSTAR is essential to enhance sensitivity, especially critical in pharmaceutical contexts.</p>","PeriodicalId":13828,"journal":{"name":"International Journal of Clinical Pharmacy","volume":" ","pages":"1053-1063"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12335389/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143993224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing a machine learning-based predictive model for the analgesic effectiveness of transdermal fentanyl in cancer patients: an interpretable approach.","authors":"Xiaogang Hu, Ya Chen, Yuelu Tang, Xiaoxiao Wang, Lixian Li, Chao Li, Wanyi Chen","doi":"10.1007/s11096-024-01860-5","DOIUrl":"10.1007/s11096-024-01860-5","url":null,"abstract":"<p><strong>Background: </strong>Cancer-related pain is a common and distressing symptom in patients with malignant tumors, significantly affecting quality of life. Transdermal fentanyl is a convenient opioid option for patients with intestinal obstruction or difficulty swallowing; however, some patients do not experience adequate pain relief. Predicting transdermal fentanyl analgesic effectiveness is crucial to optimize pain management.</p><p><strong>Aim: </strong>This study aimed to develop a predictive model for transdermal fentanyl effectiveness in cancer patients.</p><p><strong>Method: </strong>Clinical data from adult cancer pain patients at Chongqing University Cancer Hospital were analyzed (January 2020-December 2022). Logistic regression and feature selection were applied, followed by developing nine predictive models using Logistic Regression, Random Forest (RF), and Extreme Gradient Boosting. The receiver operating characteristic (ROC) curves, the Youden index, and the Brier score were used to evaluate the performance of the model. Cross-validation and SHapley Additive exPlanations (SHAP) analysis were used for validation and feature interpretation.</p><p><strong>Results: </strong>Among 151 patients, 27.2% reported ineffectiveness of transdermal fentanyl. Logistic regression identified key factors of NRS, transdermal fentanyl dosage, BMI, and ALT. Among the nine models, RF Model 8 exhibited the best performance, achieving a ROC-AUC of 0.984 (95% CI: [0.968, 0.999]). This performance was further validated by the confusion matrix metrics and visualization results. The SHAP analysis highlighted BMI, lower doses, NRS, and ALT as predictors of transdermal fentanyl ineffectiveness.</p><p><strong>Conclusion: </strong>The Random Forest model offers a valuable tool for predicting the effectiveness of transdermal fentanyl in cancer pain patients, supporting the refined assessment and management of pain.</p>","PeriodicalId":13828,"journal":{"name":"International Journal of Clinical Pharmacy","volume":" ","pages":"1011-1023"},"PeriodicalIF":3.2,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143648655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}