Clinical Practice Guideline: Safe Medication Use in the ICU

Kane‐Gill, Sandra L.; Dasta, Joseph F.; Buckley, Mitchell S.; Devabhakthuni, Sandeep; Liu, Mengmeng; Cohen, Henry; George, Elisabeth; Pohlman, Anne S.; Agarwal, Swati; Henneman, Elizabeth A.; Bejian, Sharon; Berenholtz, Sean M.; Pepin, Jodie L.; Scanlon, Matthew C.; Smith, Brian S.

doi:10.1097/ccm.0000000000002533

Cited by 85 publications

(52 citation statements)

References 314 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Apart from some clinical decision support systems, commonly used systems such as computerized prescriber order entry and bar-coded medication administration lack personalized recommendations to optimize medication effectiveness and minimize side effects [ 51 ]. Wang et al [ 47 ] applied a deep learning network based on RL to exploit medication recommendations with a data-driven strategy.…”

Section: Resultsmentioning

confidence: 99%

Reinforcement Learning for Clinical Decision Support in Critical Care: Comprehensive Review

Liu¹,

See²,

Ngiam³

et al. 2020

J Med Internet Res

136

View full text Add to dashboard Cite

Background Decision support systems based on reinforcement learning (RL) have been implemented to facilitate the delivery of personalized care. This paper aimed to provide a comprehensive review of RL applications in the critical care setting. Objective This review aimed to survey the literature on RL applications for clinical decision support in critical care and to provide insight into the challenges of applying various RL models. Methods We performed an extensive search of the following databases: PubMed, Google Scholar, Institute of Electrical and Electronics Engineers (IEEE), ScienceDirect, Web of Science, Medical Literature Analysis and Retrieval System Online (MEDLINE), and Excerpta Medica Database (EMBASE). Studies published over the past 10 years (2010-2019) that have applied RL for critical care were included. Results We included 21 papers and found that RL has been used to optimize the choice of medications, drug dosing, and timing of interventions and to target personalized laboratory values. We further compared and contrasted the design of the RL models and the evaluation metrics for each application. Conclusions RL has great potential for enhancing decision making in critical care. Challenges regarding RL system design, evaluation metrics, and model choice exist. More importantly, further work is required to validate RL in authentic clinical environments.

show abstract

Section: Resultsmentioning

confidence: 99%

Reinforcement Learning for Clinical Decision Support in Critical Care: Comprehensive Review

Liu¹,

See²,

Ngiam³

et al. 2020

J Med Internet Res

136

View full text Add to dashboard Cite

show abstract

“…A literatura registra que os pacientes internados em UTI estão mais vulneráveis a danos, pois existe a utilização de maior número de fármacos. 16,17 Apurou-se também que houve prescrições que chegaram a ter mais de três MPPs. Esses dados chamam a atenção para a necessidade de se instituírem práticas seguras que funcionem como barreiras para proteger os pacientes.…”

Section: Discussionunclassified

Identificação de riscos e práticas na utilização de medicamentos potencialmente perigosos em hospital universitário

Maia

Batista

Rosa³

et al. 2020

REME Rev Min Enferm.

View full text Add to dashboard Cite

Objetivo: analisar as prescrições de medicamentos potencialmente perigosos e identificar as práticas adotadas na dispensação em hospital universitário público de alta complexidade, propondo estratégias para prevenção de eventos adversos. Métodos: estudo transversal realizado com 566 prescrições, em três turnos, no período de abril a dezembro de 2016. A identificação de práticas para dispensação foi por observação direta com aplicação de checklist baseado no protocolo do Ministério da Saúde (MS) /Agência Nacional de Vigilância Sanitária (ANVISA). Utilizou-se teste não paramétrico do qui-quadrado de independência para avaliar a associação entre prescrições com e sem medicamentos potencialmente perigosos e unidades de internação. Resultados: mais da metade das prescrições (56,6%) continha dois ou mais medicamentos potencialmente perigosos e quase todos injetáveis (95,4%), principalmente analgésicos opioides (31,2%), glicose 50% (24,7%) e insulina NPH e regular (24,3%). A taxa dos prescritos correspondeu a 18,2%. As principais práticas que representaram riscos foram: distribuição coletiva de cloreto de potássio e insulina; falta de etiquetas de alerta; dupla conferência inexistente; uso de fontes de interrupção/distração em 43,9% das prescrições atendidas. Conclusão: apesar de serem frequentes em mais da metade das prescrições, as práticas adotadas na dispensação de medicamentos potencialmente perigosos foram insuficientes para uma dispensação segura, podendo comprometer a administração desses medicamentos e causar danos aos pacientes. É importante a implementação do protocolo do MS/ANVISA para prevenção de erros de medicação, em consonância com o terceiro desafio global da Organização Mundial da Saúde (OMS).

show abstract

“…Indeed, in many cases, we identified a lack of knowledge in this field leading to errors. Education is recommended as part of any program intending to reduce AEs and MEs 25. Poor communication within the health care team and failures in organization were the second type of frequent issue.…”

Section: Discussionmentioning

confidence: 99%

“…As recommended recently in a large review, prevention strategies for medication-related events have to be applied for each phase within the medication-use process. Active surveillance systems that include reporting, identification, and evaluation were highlighted 25. The same review indicated that there was no evidence on the impact of benchmarking for patient safety–surveillance strategies on the rates of MEs, ADEs, or mortality in critically ill patients 25.…”

Section: Discussionmentioning

confidence: 99%

<p>Interprofessional safety reporting and review of adverse events and medication errors in critical care</p>

Chapuis

Chanoine

Colombet

et al. 2019

TCRM

View full text Add to dashboard Cite

Background The intensive care unit (ICU) environment is prone to the risk of adverse events (AEs) and medication errors (MEs). The objective of this work was to describe a multidisciplinary safety program focused on AE and ME reporting and review in an ICU over a 7-year period. Methods The program was implemented in an 18-bed medical ICU of a 2,200-bed university hospital. A multidisciplinary steering committee (intensivist, clinical pharmacist, nurses, and research assistants) met monthly. The first part of the meeting was dedicated to the review of events targeted through an internal voluntary reporting system, and the second part concerned the analysis of the previous month’s events, according to a standardized method called Orion, inspired by the aeronautic industry. Results A total of 808 AEs were reported, mostly related to medication processes (30.3% and 33.4% for prescription and administration, respectively). Among these, 526 AEs were related to medications (65.1%), of which 464 were MEs (88.2%). These MEs concerned mostly anti-infective drugs (23.5%) and related to wrong doses (35.8%). Among all AEs reported, 58 (43 MEs [74.1%]) were analyzed further and found to be associated with anti-infective (16.1%) and vasoactive drugs (16.1%). According to National Coordinating Council for Medication Error Reporting and Prevention classification, most AEs caused no harm to patients (category A–D: 38 events, 65.5%). Nurses were most often involved in the analysis (50.7%), along with pharmacists (37.5%). Training was identified as the most frequent corrective action (45.1%). Conclusion This program dedicated to AE and ME reporting, review, and analysis in ICU showed long-term engagement of the health care team in AE surveillance and helped in targeting measures for education, organization, and promoting teamwork and safety.

show abstract

Clinical Practice Guideline: Safe Medication Use in the ICU

Cited by 85 publications

References 314 publications

Reinforcement Learning for Clinical Decision Support in Critical Care: Comprehensive Review

Reinforcement Learning for Clinical Decision Support in Critical Care: Comprehensive Review

Identificação de riscos e práticas na utilização de medicamentos potencialmente perigosos em hospital universitário

<p>Interprofessional safety reporting and review of adverse events and medication errors in critical care</p>

Contact Info

Product

Resources

About