Exploring the impact of artificial intelligence integration on medication error reduction: A nursing perspective

IF 3.3 3区医学 Q1 NURSING

Nurse Education in Practice Pub Date : 2025-06-21 DOI:10.1016/j.nepr.2025.104438

Muhyeeddin Alqaraleh , Wesam Taher Almagharbeh , Muhammad Waleed Ahmad

{"title":"Exploring the impact of artificial intelligence integration on medication error reduction: A nursing perspective","authors":"Muhyeeddin Alqaraleh , Wesam Taher Almagharbeh , Muhammad Waleed Ahmad","doi":"10.1016/j.nepr.2025.104438","DOIUrl":null,"url":null,"abstract":"<div><h3>Aim</h3><div>To systematically evaluate the impact of artificial intelligence (AI) technologies on reducing medication errors in nursing practice, focusing on tools such as clinical decision support systems (CDSS), smart infusion pumps, barcode scanning and automated prescription validation.</div></div><div><h3>Background</h3><div>Medication errors are a persistent threat to patient safety and a major burden on healthcare systems. Nurses, who are central to the medication administration process, remain vulnerable to human error. AI offers new opportunities to enhance safety through real-time decision support and predictive analytics.</div></div><div><h3>Design</h3><div>A systematic review following PRISMA 2020 guidelines and using a mixed-methods approach to integrate quantitative outcomes with qualitative insights from nursing practice.</div></div><div><h3>Methods</h3><div>Studies published in English between January 2013 and March 2024 were retrieved from PubMed, ScienceDirect and CINAHL. Eligibility was guided by the PICO framework. Quality appraisal tools appropriate to study designs were applied.</div></div><div><h3>Results</h3><div>Twelve studies were included. CDSS reduced operating room errors by up to 95 %, while smart infusion pumps reduced IV medication errors by approximately 80 %. Prescription validation tools led to a 55 % reduction in prescribing errors. AI-driven alert filtering decreased non-actionable alerts by 45 %. Qualitative data revealed both appreciation of AI’s utility and concerns about algorithmic bias, system usability and trust.</div></div><div><h3>Conclusions</h3><div>AI technologies significantly improve medication safety in nursing. However, successful implementation depends on nurse training, system integration, ethical safeguards and workflow alignment. Further experimental studies are needed to validate efficacy and address barriers such as alert fatigue, algorithm transparency and adoption resistance.</div></div>","PeriodicalId":48715,"journal":{"name":"Nurse Education in Practice","volume":"86 ","pages":"Article 104438"},"PeriodicalIF":3.3000,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nurse Education in Practice","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1471595325001945","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NURSING","Score":null,"Total":0}

引用次数: 0

Abstract

Aim

To systematically evaluate the impact of artificial intelligence (AI) technologies on reducing medication errors in nursing practice, focusing on tools such as clinical decision support systems (CDSS), smart infusion pumps, barcode scanning and automated prescription validation.

Background

Medication errors are a persistent threat to patient safety and a major burden on healthcare systems. Nurses, who are central to the medication administration process, remain vulnerable to human error. AI offers new opportunities to enhance safety through real-time decision support and predictive analytics.

Design

A systematic review following PRISMA 2020 guidelines and using a mixed-methods approach to integrate quantitative outcomes with qualitative insights from nursing practice.

Methods

Studies published in English between January 2013 and March 2024 were retrieved from PubMed, ScienceDirect and CINAHL. Eligibility was guided by the PICO framework. Quality appraisal tools appropriate to study designs were applied.

Results

Twelve studies were included. CDSS reduced operating room errors by up to 95 %, while smart infusion pumps reduced IV medication errors by approximately 80 %. Prescription validation tools led to a 55 % reduction in prescribing errors. AI-driven alert filtering decreased non-actionable alerts by 45 %. Qualitative data revealed both appreciation of AI’s utility and concerns about algorithmic bias, system usability and trust.

Conclusions

AI technologies significantly improve medication safety in nursing. However, successful implementation depends on nurse training, system integration, ethical safeguards and workflow alignment. Further experimental studies are needed to validate efficacy and address barriers such as alert fatigue, algorithm transparency and adoption resistance.

查看原文本刊更多论文

从护理角度探讨人工智能集成对减少用药错误的影响

目的系统评估人工智能（AI）技术对减少护理实践中用药错误的影响，重点关注临床决策支持系统（CDSS）、智能输液泵、条形码扫描和自动处方验证等工具。用药错误是对患者安全的持续威胁，也是医疗保健系统的主要负担。护士是药物管理过程的核心，仍然容易受到人为错误的影响。人工智能通过实时决策支持和预测分析为提高安全性提供了新的机会。根据PRISMA 2020指南设计一项系统评价，并使用混合方法将定量结果与护理实践的定性见解相结合。方法检索2013年1月至2024年3月在PubMed、ScienceDirect和CINAHL网站发表的英文论文。资格以PICO框架为指导。应用了适合研究设计的质量评价工具。结果共纳入12项研究。CDSS将手术室错误率降低了95% %，而智能输液泵将静脉用药错误率降低了约80% %。处方验证工具使处方错误率降低了55% %。人工智能驱动的警报过滤减少了45% %的不可操作警报。定性数据显示了对人工智能效用的赞赏，以及对算法偏见、系统可用性和信任的担忧。结论ai技术显著提高护理用药安全性。然而，成功实施取决于护士培训、系统整合、道德保障和工作流程一致性。需要进一步的实验研究来验证有效性，并解决警报疲劳、算法透明度和采用阻力等障碍。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Nurse Education in Practice NURSING-

CiteScore

5.40

自引率

9.40%

发文量

180

审稿时长

51 days

期刊介绍： Nurse Education in Practice enables lecturers and practitioners to both share and disseminate evidence that demonstrates the actual practice of education as it is experienced in the realities of their respective work environments. It is supportive of new authors and will be at the forefront in publishing individual and collaborative papers that demonstrate the link between education and practice.