OBJECTIVE: The emergence of artificial intelligence (AI) is catching the interest of hospital pharmacists. A massive collection of health data is now available to train AI models and hold the promise of disrupting codes and practices. The objective of this systematic review was to examine the state of the art of machine learning or deep learning models that detect inappropriate hospital medication orders.
METHODS: A systematic review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. MEDLINE and Embase databases were searched from inception to May 2023. Studies were included if they reported and described an AI model intended for use by clinical pharmacists in hospitals. Risk of bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST).
RESULTS: 13 articles were selected after review: 12 studies were judged to have high risk of bias; 11 studies were published between 2020 and 2023; 8 were conducted in North America and Asia; 6 analysed orders and detected inappropriate prescriptions according to patient profiles and medication orders; and 7 detected specific inappropriate prescriptions, such as detecting antibiotic resistance, dosage abnormality in prescriptions, high alert drugs errors from prescriptions or predicting the risk of adverse drug events. Various AI models were used, mainly supervised learning techniques. The training datasets used were very heterogeneous; the length of study varied from 2 weeks to 7 years and the number of prescription orders analysed went from 31 to 5 804 192.
CONCLUSIONS: This systematic review points out that, to date, few original research studies report AI tools based on machine or deep learning in the field of hospital clinical pharmacy. However, these original articles, while preliminary, highlighted the potential value of integrating AI into clinical hospital pharmacy practice.

Cholesterol-lowering statins are frequently prescribed for primary and secondary prevention of ischaemic vascular events. Whereas most patients tolerate statins without problems, statin-associated myopathy is well documented, as are several risk factors. We present a case report of an 80-90-year-old man with coronary artery disease who rapidly developed severe rhabdomyolysis during treatment with rosuvastatin while in intensive care. He had several concomitant risk factors for statin-induced myopathy including high dosage, old age, renal and hepatic impairment, and a pharmacogenetic SLCO1B1*1 a/*5 variant. Single known risk factors have a low predictive value for statin-induced myopathy and may therefore be underestimated in clinical practice. However, adverse drug reactions frequently involve the joint action of a multitude of environmental and genetic component causes, and statin-induced myopathy should be regarded as a multicausal event. We therefore advocate a proactive multifactorial risk assessment to guide and individualise statin therapy in high-risk patients.

Medication administration errors (MAEs) are a major cause of morbidity and mortality. An updated barcode medication administration (BCMA) technology on infusion pumps is implemented in the operating rooms to automate double check at a syringe exchange.
The aim of this mixed-methods before-and-after study is to understand the medication administrating process and assess the compliance with double check before and after implementation.
Reported MAEs from 2019 to October 2021 were analysed and categorised to the three moments of medication administration: (1) bolus induction, (2) infusion pump start-up and (3) changing an empty syringe. Interviews were conducted to understand the medication administration process with functional resonance analysis method (FRAM). Double check was observed in the operating rooms before and after implementation. MAEs up to December 2022 were used for a run chart.
Analysis of MAEs showed that 70.9% occurred when changing an empty syringe. 90.0% of MAEs were deemed to be preventable with the use of the new BCMA technology. The FRAM model showed the extent of variation to double check by coworker or BCMA.Observations showed that the double check for pump start-up changed from 70.2% to 78.7% postimplementation (p=0.41). The BCMA double check contribution for pump start-up increased from 15.3% to 45.8% (p=0.0013). The double check for changing an empty syringe increased from 14.3% to 85.0% (p<0.0001) postimplementation. BCMA technology was new for changing an empty syringe and was used in 63.5% of administrations. MAEs for moments 2 and 3 were significantly reduced (p=0.0075) after implementation in the operating rooms and ICU.
An updated BCMA technology contributes to a higher double check compliance and MAE reduction, especially when changing an empty syringe. BCMA technology has the potential to decrease MAEs if adherence is high enough.

Medication errors can have severe consequences and threaten patient safety. The patient safety-related benefits of automated dispensing cabinets (ADCs) have been reported by several previous studies, including a reduction in medication errors in intensive care units (ICUs) and emergency departments. However, the benefits of ADCs need to be assessed, given the different healthcare practice models. This study aimed to compare the rates of medication errors, including prescription, dispensing, and administrative, before and after using ADCs in intensive care units. The prescription, dispensing, and administrative error data before and after the adoption of ADCs were retrospectively collected from the medication error report system. The severity of medication errors was classified according to the National Coordinating Council for Medication Error Reporting and Prevention guidelines. The study outcome was the rate of medication errors. After the adoption of ADCs in the intensive care units, the rates of prescription and dispensing errors reduced from 3.03 to 1.75 per 100,000 prescriptions and 3.87 to 0 per 100,000 dispensations, respectively. The administrative error rate decreased from 0.046 to 0.026%. The ADCs decreased National Coordinating Council for Medication Error Reporting and Prevention category B and D errors by 75% and category C errors by 43%. To improve medication safety, multidisciplinary collaboration and strategies, such as the use of automated dispensing cabinets, education, and training programs from a systems perspective, are warranted.

Although electronic medication administration records (eMARs) and bar-coded medication administration (BCMA) have improved medication safety, poor usability of these technologies can increase patient safety risks.
The objective of our systematic review was to identify the impact of eMAR and BCMA design on usability, operationalized as efficiency, effectiveness, and satisfaction.
We retrieved peer-reviewed journal articles on BCMA and eMAR quantitative usability measures from PsycInfo and MEDLINE (1946-August 20, 2019), and EMBASE (1976-October 23, 2019). Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we screened articles, extracted and categorized data into the usability categories of effectiveness, efficiency, and satisfaction, and evaluated article quality.
We identified 1,922 articles and extracted data from 41 articles. Twenty-four articles (58.5%) investigated BCMA only, 10 (24.4%) eMAR only, and seven (17.1%) both BCMA and eMAR. Twenty-four articles (58.5%) measured effectiveness, 8 (19.5%) efficiency, and 17 (41.5%) satisfaction. Study designs included randomized controlled trial (n = 1; 2.4%), interrupted time series (n = 1; 2.4%), pretest/posttest (n = 21; 51.2%), posttest only (n = 14; 34.1%), and pretest/posttest and posttest only for different dependent variables (n = 4; 9.8%). Data collection occurred through observations (n = 19, 46.3%), surveys (n = 17, 41.5%), patient safety event reports (n = 9, 22.0%), surveillance (n = 6, 14.6%), and audits (n = 3, 7.3%).
Of the 100 measures across the 41 articles, implementing BCMA and/or eMAR broadly resulted in an increase in measures of effectiveness (n = 23, 52.3%) and satisfaction (n = 28, 62.2%) compared to measures of efficiency (n = 3, 27.3%). Future research should focus on eMAR efficiency measures, utilize rigorous study designs, and generate specific design requirements.

(1) Characterize persistent hazards and inefficiencies in inpatient medication administration; (2) Explore cognitive attributes of medication administration tasks; and (3) Discuss strategies to reduce medication administration technology-related hazards.
Interviews were conducted with 32 nurses practicing at 2 urban, eastern and western US health systems. Qualitative analysis using inductive and deductive coding included consensus discussion, iterative review, and coding structure revision. We abstracted hazards and inefficiencies through the lens of risks to patient safety and the cognitive perception-action cycle (PAC).
Persistent safety hazards and inefficiencies related to MAT organized around the PAC cycle included: (1) Compatibility constraints create information silos; (2) Missing action cues; (3) Intermittent communication flow between safety monitoring systems and nurses; (4) Occlusion of important alerts by other, less helpful alerts; (5) Dispersed information: Information required for tasks is not collocated; (6) Inconsistent data organization: Mismatch of the display and the user\'s mental model; (7) Hidden medication administration technologies (MAT) limitations: Inaccurate beliefs about MAT functionality contribute to overreliance on the technology; (8) Software rigidity causes workarounds; (9) Cumbersome dependencies between technology and the physical environment; and (10) Technology breakdowns require adaptive actions.
Errors might persist in medication administration despite successful Bar Code Medication Administration and Electronic Medication Administration Record deployment for reducing errors. Opportunities to improve MAT require a deeper understanding of high-level reasoning in medication administration, including control over the information space, collaboration tools, and decision support.
Future medication administration technology should consider a deeper understanding of nursing knowledge work for medication administration.

OBJECTIVE: To describe the frequency of the different types of medication-related incidents that caused patient harm, or adverse consequences, in a major teaching hospital and investigate whether the likelihood of these incidents occurring would have been reduced by electronic prescribing and medicines administration (EPMA).
METHODS: A retrospective review of harmful incidents (n=387) was completed for medication-related reports at the hospital between 1 September 2020 and 31 August 2021. Frequencies of different types of incidents were collated. The potential for EPMA to have prevented these incidents was assessed by reviewing DATIX reports and additional information, including results of any investigations.
RESULTS: The largest proportion of harmful medication incidents were administration related (n=215, 55.6%), followed by incidents classified as \'other\' and \'prescribing\'. Most incidents were classified as low harm (n=321, 83.0%). EPMA could have reduced the likelihood of all incidents which caused harm by 18.6% (n=72) without configuration, and a further 7.5% (n=29) with configuration where configuration refers to adapting the software\'s functionality without supplier input or development. For 18.4% of the low-harm incidents (n=59) and 20.3% (n=13) of the moderate-harm incidents, EPMA could reduce the likelihood of the incident occurring without configuration. Medication errors most likely to be reduced by EPMA were due to illegibility, multiple drug charts or missing drug charts.
CONCLUSIONS: This study found that administration incidents were the most common type of medication-related incidents. Most of the incidents (n=243, 62.8%) could not be mitigated by EPMA in any circumstance, even with connectivity between technologies. EPMA has the potential to prevent certain types of harmful medication-related incidents, and further improvements could be achieved with configuration and development.

Knowledge of the prevalence and characteristics of medication errors in pediatric and neonatal patients is limited. This study aimed to evaluate the incidence and medication error characteristics in a pediatric hospital over 5 years and to determine whether serial error prevention programs to optimize a computerized physician order entry (CPOE) system reduce error incidence.
We retrospectively reviewed medication errors documented between January 2015 and December 2019.
A total of 2,591,596 prescriptions were checked, and 255 errors were identified. Wrong dose prescriptions constituted the most common errors (56.9%). Medications with the highest rate of errors were antibiotics/antiviral drugs (36.9%). Oral route medications comprised the highest portion (60.8%), followed by intravenous ones (28.6%). The most common stage for medication errors was physician ordering (93.3%). Junior residents were responsible for most errors (45.9%). Most errors occurred in the pediatric ward (53.7%). In total, 221 (86.7%) errors were near misses. Only 4 errors (1.6%) were considered significant and required active monitoring or intervention. Type of error, stage of error, staff composition, and severity level of errors were significantly related to the number of errors in different years. There was a statistically significant decrease in errors per 100,000 prescriptions across different years after optimizing the CPOE system.
The incidence of medication errors decreased with extensive use of the CPOE system. Continuous application of the CPOE optimization program can effectively reduce medication errors. Further incorporation of pediatric-specific decision-making and support tools and error prevention measures into CPOE systems is needed.

The state of digitalisation in the healthcare sector in Switzerland is lagging, even as the national electronic health record (EHR) is being gradually implemented. Little is known about the implementation of electronic prescribing systems, their auxiliary features or drug datasets in Swiss hospitals.The aim of this study was to understand which electronic systems are implemented to support doctors in Swiss hospitals during the medication prescribing process.
The survey was sent in spring 2021 to the chief pharmacists of the main Swiss hospitals. The survey focused on the introduction of the EHR, the clinical information system (CIS) and its prescribing module, as well as drug information data and clinical decision support systems (CDSS).
The response rate was 98% (58/59 hospitals). Almost half of the hospitals (47%) were connected to the national EHR, almost all hospitals (86%) used a CIS and a vast majority of the hospitals (84%) had implemented electronic prescribing systems in their CIS. 10 years ago, around 63% of hospitals used a CIS and 40% were equipped with an electronic prescribing system. Today, CDSS of any kind were implemented in 50% of the hospitals, predominantly for drug-drug interactions. Drug master data were maintained in most hospitals (76%) via an automated interface, but mostly supplemented manually. Clinical drug information data were maintained in 74% of hospitals. In 67% of hospitals, datasets were imported via an automated interface.
The digitalisation of the medical prescribing process in Swiss hospitals has progressed over the last decade. Drug prescriptions via electronic prescribing systems were introduced in most hospitals. However, this survey suggests that the current use of CDSS is far from exhausted, and that clinical drug information data could be maintained more efficiently. Optimising electronic support for healthcare professionals during the prescribing process still has considerable potential.

Pharmacy and therapeutics committees (PTCs) are multidisciplinary hospital teams responsible for rational medication use. We aimed at developing and piloting an assessment tool for their operating quality.We conducted a scoping literature review in PubMed and Embase to identify potential assessment items. Their relevance was systematically rated and consolidated into the final tool.60 relevant items were included, grouped into eight focus topics: the committee\'s institutional integration, member characteristics, performance indicators, meeting structure, formulary decision-making and characteristics, strategies to guide medication use and medication use evaluations.In combination with a SWOT (strengths, weaknesses, opportunities and threats) analysis, the tool helped the identification of improvement opportunities for a pilot hospital: adapting the committee\'s structure, improving the formulary decision-making, implementing strategies to guide formulary medication use and strengthening the committee\'s recognition within the institution.The tool successfully identified improvement opportunities for a PTC and could therefore be interesting for other hospitals.