The role of artificial intelligence in emergency medicine pharmacy practice

被引:1
作者
Edwards, Christopher J. [1 ,2 ]
Erstad, Brian L. [1 ]
Ng, Vivienne [2 ]
机构
[1] Univ Arizona, R Ken Coit Coll Pharm, Dept Pharm Practice & Sci, Tucson, AZ 85721 USA
[2] Univ Arizona, Coll Med, Dept Emergency Med, Tucson, AZ 85721 USA
关键词
artificial intelligence; emergency medicine; pharmacy practice; MODEL;
D O I
10.1093/ajhp/zxaf038
中图分类号
R9 [药学];
学科分类号
1007 ;
摘要
Purpose This primer aims to serve as a foundational resource on artificial intelligence (AI) for pharmacists practicing in the emergency department (ED).Summary Artificial intelligence (AI) is increasingly recognized for its potential to transform healthcare, including emergency medicine (EM) and pharmacy practice. AI applications in EM include diagnostic evaluation, risk stratification, resource optimization, and therapeutic decision-making. AI's role in improving triage, diagnostics, and resource utilization in the emergency setting is discussed along with its application in the medication-use process, from prescribing to monitoring. Despite the promise of AI, significant barriers such as factual inaccuracies, ethical concerns, and data transparency prevent the widespread clinical adoption of AI tools. Challenges such as racial bias, data privacy, model transparency, and the phenomenon of hallucinations in large language model outputs are highlighted as critical considerations. AI's future success in EM will depend on responsible integration, guided by clinicians including pharmacists, and a careful consideration of ethical issues and patient-specific values.Conclusion Pharmacists practicing in the ED should be familiar with AI tools and should understand the importance of their role in the development, implementation, and oversight of these tools to ensure safe, effective, and equitable patient care.
引用
收藏
页数:8
相关论文
共 47 条
[1]   Snakebite Advice and Counseling From Artificial Intelligence: An Acute Venomous Snakebite Consultation With ChatGPT [J].
Altamimi, Ibraheem ;
Altamimi, Abdullah ;
Alhumimidi, Abdullah S. ;
Altamimi, Abdulaziz ;
Temsah, Mohamad Hani .
CUREUS JOURNAL OF MEDICAL SCIENCE, 2023, 15 (06)
[2]  
American College of Emergency Physicians, 2008, Ann Emerg Med, V52, P189, DOI [10.1016/j.annemergmed.2008.05.028, 10.1016/j.annemergmed.2008.05.029]
[4]   Predicting inpatient pharmacy order interventions using provider action data [J].
Balestra, Martina ;
Chen, Ji ;
Iturrate, Eduardo ;
Aphinyanaphongs, Yindalon ;
Nov, Oded .
JAMIA OPEN, 2021, 4 (03)
[5]   A scoping review of machine learning for sepsis prediction- feature engineering strategies and model performance: a step towards explainability [J].
Bomrah, Sherali ;
Uddin, Mohy ;
Upadhyay, Umashankar ;
Komorowski, Matthieu ;
Priya, Jyoti ;
Dhar, Eshita ;
Hsu, Shih-Chang ;
Syed-Abdul, Shabbir .
CRITICAL CARE, 2024, 28 (01)
[6]  
Boussina A, 2024, NPJ DIGIT MED, V7, DOI 10.1038/s41746-023-00986-6
[7]   Using natural language processing to identify problem usage of prescription opioids [J].
Carrell, David S. ;
Cronkite, David ;
Palmer, Roy E. ;
Saunders, Kathleen ;
Gross, David E. ;
Masters, Elizabeth T. ;
Hylan, Timothy R. ;
Von Korff, Michael .
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, 2015, 84 (12) :1057-1064
[8]  
Casper S, 2023, Arxiv, DOI [arXiv:2307.15217, 10.48550/arXiv.2307.15217, DOI 10.48550/ARXIV.2307.15217]
[9]   Accuracy of a chatbot in answering questions that patients should ask before taking a new medication [J].
Cornelison, Bernadette R. ;
Erstad, Brian L. ;
Edwards, Christopher .
JOURNAL OF THE AMERICAN PHARMACISTS ASSOCIATION, 2024, 64 (04)
[10]   A machine learning-based clinical decision support system to identify prescriptions with a high risk of medication error [J].
Corny, Jennifer ;
Rajkumar, Asok ;
Martin, Olivier ;
Dode, Xavier ;
Lajonchere, Jean-Patrick ;
Billuart, Olivier ;
Bezie, Yvonnick ;
Buronfosse, Anne .
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2020, 27 (11) :1688-1694