Computerized pharmacy surveillance and alert system for drug-related problems

The Impact of Hospital Pharmacy Operation on the Quality of Patient Care

This paper presents the role, tasks, and place of a hospital pharmacy in the structure of the entire facility. The role of hospital drug management and pharmacy seems to be extremely important in providing patients with high-quality care. Particular emphasis was placed on the distribution systems of medicinal products and medical devices in the hospital. The advantages and disadvantages of the classical distribution system and modern systems such as unit-dose and multi-dose-and the most important differences between them-are presented. Difficulties related to implementing modern distribution systems in hospitals were also discussed. The information provided is presented in the context of the legal regulations in Poland.

Classification of Musculoskeletal Radiograph Requisition Appropriateness Using Machine Learning

Objective: Poor quality imaging requisitions lower report quality and impede good patient care. Manual control of such requisitions is time consuming and can be a source of friction with referring physicians. The purpose of this study was to determine if poor quality requisitions could be identified automatically using machine learning and natural language processing techniques in order to allow for more efficient workflow. Methods: Exam indications from 50 000 musculoskeletal radiograph requisitions were manually classified, reviewed and deemed 'appropriate' or 'inappropriate' by two staff radiologists based on ACR appropriateness criteria. The requisitions were divided into training and test groups (80/20 split). The training set was pre-processed, converted to a bag-of-words model and used to train a Multinomial Naïve Bayes classifier which was then applied to the test set. Results: Out of 50 000 requisitions, 12 253 (24.5%) were deemed to contain an inappropriate indication. A Naive Bayes model correctly classified requisitions with an accuracy of 98%. In the test set, 107 of 7561 (1.4%) appropriate requisitions were incorrectly flagged and 92 of 2439 (3.8%) inappropriate requisitions were not flagged. Conclusions: Accurate automated identification of inappropriate indications on musculoskeletal requisitions is feasible using machine learning and natural language processing.

Drug-related problems in patients admitted for SARS-CoV-2 infection during the COVID-19 pandemic

Introduction: Drug-related problems (DRP) are events or circumstances in which drug therapy does or could interfere with desired health outcomes. In December 2019, a new coronavirus, SARS-CoV-2, appeared. Little knowledge about this type of infection resulted in the administration of various drugs with limited use in other pathologies. Evidence about DRP in patients with COVID-19 is lacking. Objective: The aim of the present study is to describe identified cases of DRP and those drugs involved in the first wave of patients with COVID-19, and evaluate associated risk factors. Material and methods: Observational, retrospective study performed in a tertiary university hospital between 14th March 2020 and 31 May 2020 (corresponding to the first COVID-19 wave). We recruited patients admitted during the study period. Exclusion criteria included age < 18 years; admission to critically ill units; and care received either in the emergency room, at-home hospitalization or a healthcare center. Results: A total of 817 patients were included. The mean age was 62.5 years (SD 16.4) (range 18-97), and 453 (55.4%) were male. A total of 516 DRP were detected. Among the patients, 271 (33.2%) presented at least one DRP. The mean DRP per patient with an identified case was 1.9. The prevailing DRPs among those observed were: incorrect dosage (over or underdosage) in 145 patients (28.2%); wrong drug combination in 131 (25.5%); prescriptions not in adherence to the then COVID-19 treatment protocol in 73 (14.1%); prescription errors due to the wrong use of the computerized physician order entry in 47 (9.2%); and incorrect dosage due to renal function in 36 (7%). The logistic regression analysis showed that patients who received only prescriptions of antibacterials for systemic use (J01 ATC group) faced a higher likelihood of experiencing a DRP (OR 2.408 (1.071-5.411), p = 0.033). Conclusion: We identified several factors associated with an increased risk of DRPs, similar to those reported in other pre-pandemic studies, including a prolonged length of stay, higher number of prescribed drugs and antimicrobial administration. The relevance of pharmacists and tools like pharmacy warning systems can help prevent, identify and resolve DRP efficiently.

Clinical validation of clinical decision support systems for medication review: A scoping review

The aim of this scoping review is to summarize approaches and outcomes of clinical validation studies of clinical decision support systems (CDSSs) to support (part of) a medication review. A literature search was conducted in Embase and Medline. In total, 30 articles validating a CDSS were ultimately included. Most of the studies focused on detection of adverse drug events, potentially inappropriate medications and drug‐related problems. We categorized the included articles in three groups: studies subjectively reviewing the clinical relevance of CDSS's output (21/30 studies) resulting in a positive predictive value (PPV) for clinical relevance of 4–80%; studies determining the relationship between alerts and actual events (10/30 studies) resulting in a PPV for actual events of 5–80%; and studies comparing output of CDSSs to chart/medication reviews in the whole study population (10/30 studies) resulting in a sensitivity of 28–85% and specificity of 42–75%. We found heterogeneity in the methods used and in the outcome measures. The validation studies did not report the use of a published CDSS validation strategy. To improve the effectiveness and uptake of CDSSs supporting a medication review, future research would benefit from a more systematic and comprehensive validation strategy.

Identification and Prioritization of Clinical Decision Support Functionalities Built Within A Computerized Provider Order Entry System

Background: Clinical decision support (CDS) functionalities in Computerized Provider Order Entry system (CPOE) need to be identified by the institutional healthcare providers in developing countries. In this regard, CDS functionalities should be a priority for the execution in CPOE. Objectives: Thus, our study was done to identify and prioritize the CDS functionalities in CPOE. Methods: A Two-round Modified Delphi process was used. Firstly, a systematic search was conducted in electronic databases from the date of database inception to February 2019 for identifying CDS functionalities integrated into CPOE. Studies were retrieved from databases, including PubMed, Embase, ProQuest, Scopus, Web of Science, Cochrane, Science Direct, ACM digital library, and IEEE Xplore Digital Library. Secondly, the Modified Delphi method was carried out in 2019 to provide contextual priorities regarding CDS functionalities in CPOE in two iterative rounds. A total of 12 experts working in the three Intensive Care Units (ICUs) with more than three years of experience with homegrown CPOE in Shiraz Nemazee Teaching Hospital, including two clinical pharmacists, two health information management faculty member, four cases with critical care fellowship, and four critical care experts participated in the study. The ≥ 66.6% agreement was considered as the consensus level. SPSS software version 24 was used for statistical analysis. Results: Totally, 327 studies, which met eligibility criteria were found. A number of 60 potential CDS functionalities in CPOE were identified from eligible studies. Also, 13 out of 60 CDS functionalities reached high priority consensus after 2 iterative Delphi rounds, including drug-allergy checking (83.3%), basic dosing guidance (75%), single dosing checking (66.7%), duplicate therapy checking (66.7%), drug-pregnancy alerts (75%), time-based alerts (66.7%), alert for deep vein thrombosis prophylaxis (66.7%), alerts for duplicate medication order checking (66.7%), drug-drug interaction checking (75%), intelligent dosing guidance based on the patients’ characteristics (66.7%), renal-drug problems checking (83.3%), drug-disease interaction checking (66.7%), and displaying medication/test cost (75%). Conclusions: Our study identified high-priority CDS functionalities to be considered in the CPOE system from the viewpoint of multidisciplinary experts, especially in Iran. Results of this study may be beneficial to plan, design, and implement CDS functionalities in CPOE in the ICU.

Assessing the International Transferability of a Machine Learning Model for Detecting Medication Error in the General Internal Medicine Clinic: Multicenter Preliminary Validation Study

Background

Although most current medication error prevention systems are rule-based, these systems may result in alert fatigue because of poor accuracy. Previously, we had developed a machine learning (ML) model based on Taiwan’s local databases (TLD) to address this issue. However, the international transferability of this model is unclear.

Objective

This study examines the international transferability of a machine learning model for detecting medication errors and whether the federated learning approach could further improve the accuracy of the model.

Methods

The study cohort included 667,572 outpatient prescriptions from 2 large US academic medical centers. Our ML model was applied to build the original model (O model), the local model (L model), and the hybrid model (H model). The O model was built using the data of 1.34 billion outpatient prescriptions from TLD. A validation set with 8.98% (60,000/667,572) of the prescriptions was first randomly sampled, and the remaining 91.02% (607,572/667,572) of the prescriptions served as the local training set for the L model. With a federated learning approach, the H model used the association values with a higher frequency of co-occurrence among the O and L models. A testing set with 600 prescriptions was classified as substantiated and unsubstantiated by 2 independent physician reviewers and was then used to assess model performance.

Results

The interrater agreement was significant in terms of classifying prescriptions as substantiated and unsubstantiated (κ=0.91; 95% CI 0.88 to 0.95). With thresholds ranging from 0.5 to 1.5, the alert accuracy ranged from 75%-78% for the O model, 76%-78% for the L model, and 79%-85% for the H model.

Conclusions

Our ML model has good international transferability among US hospital data. Using the federated learning approach with local hospital data could further improve the accuracy of the model.

Vancomycin is commonly under-dosed in critically ill children and neonates

Aims

Vancomycin is frequently used in critically ill children in whom the drug pharmacokinetics are significantly altered as a result of changes in renal clearance and volume of distribution. Therapeutic drug monitoring (TDM) is recommended to achieve vancomycin trough concentrations between 10 and 20 mg/L. In this study we reviewed vancomycin dosing, TDM and treatment outcomes in paediatric and neonatal intensive care unit patients.

Methods

We reviewed the medical records of all patients receiving intravenous vancomycin in a tertiary paediatric and neonatal intensive care unit over a 10‐month period. Demographic, vancomycin dosing, TDM and drug‐related adverse effects data were collected.

Results

In total, 115 children received 126 courses of vancomycin and had at least 1 TDM blood sample taken at steady state. In only 38/126 (30%) courses was the target concentration (10–20 mg/L) achieved at the initial steady state trough sample. Of the 88 courses that had initial trough concentrations outside the target range, the dose was adjusted in only 49 (56%). Overall, minimum doses of 30 mg/kg/day in neonates with a corrected gestational age of <35 weeks, and 50 mg/kg/day in older children, were required to achieve target vancomycin concentrations. Vancomycin‐attributable nephrotoxicity occurred in 10/126 (8%) courses and there were no episodes of red man syndrome.

Conclusion

In critically ill children, individualised dosing is needed. In the absence of Bayesian model‐based dosing, in children with normal renal function, empiric vancomycin doses of at least 30 mg/kg/day in neonates of <35 weeks corrected gestational age, and 50 mg/kg/day in older children, should be considered. Optimisation of TDM practices through the development of protocols, ideally built into electronic medical records, should be considered.

Role and impact of pharmacists in Spain: a scoping review

Background The role of the pharmacist has evolved greatly over the last decades, expanding to patient-oriented activities, administrative tasks and public health functions. However, considerable differences emerge across regions. Aim of the review To gather evidence in order to describe and highlight the different characteristics of the pharmacists' role and the impact of their activities in Spain. Method A review of the existing literature was conducted. The literature search was undertaken in PubMed between 01/01/2006 and 15/08/2017. Results were screened and reviewed to extract previously established criteria such as author(s), publication year, language, study design, setting, pharmaceutical activity, patient care programs, targeted diseases and intervention description using DEPICT2 tool. Pharmaceutical intervention were classified into eight outcome measures and categorized by types of outcomes reported: descriptive or impact evaluation regarding the effect of the service (positive, neutral or negative). Results The search strategy resulted in 473 articles and 108 articles met the inclusion criteria. The most common design was observational (n = 76, 70%). Most articles were published after 2011 (75%), in English (69%). Studies were conducted in hospitals (60%) and community pharmacies (30%). Of the 24 pharmaceutical activities identified, medication review was the activity most frequently studied (n = 42), followed by patient education (n = 29), risk and prevention (n = 27) and medication reconciliation (n = 19). Only 39 articles (36%) had outcome measures with impact evaluation. Of the 223 impact outcome measures, 48% (107/223) had a positive effect. Conclusion This review shows the substantial scientific production focusing on pharmacy practice in Spain over the last years. The evidence reviewed reflects the pharmacist role at various professional settings, providing a wide variety of activities on diverse targeted diseases and patient care programs, in line with the increasing specialization of clinical pharmacists over the last years.

Evaluation of computerized provider order entry systems: assessing the usability of systems for electronic prescription

BACKGROUND

The field of medicine has been influenced by the growth and development of information systems such as the Computerized Provider Order Entry (CPOE) System.

OBJECTIVE

This study aimed to evaluate the usability of CPOE systems for electronic prescription in Tehran, Iran.

METHODS

This was an evaluation study conducted in 2017. The research population consisted of the CPOE systems used in hospitals of Tehran (Iran) and nurses who had access to, and used, the CPOE systems. Five hospitals with CPOE systems were included in the research sample. The data were collected using a questionnaire, and included a total of 50 questions. The questionnaires were distributed among 254 nurses who were the users of the systems. Data analysis was performed by IBM-SPSS version 21, using independent-samples t-test. A p-value of ≤0.05 was considered statistically significant.

RESULTS

Among the four aspects assessed, the "user-friendliness" (3.87±0.59) had the highest mean score. The lowest mean score (2.01±0.58) was related to the "decision support" feature of the systems. The highest and lowest mean scores for "prescription support" criterion belonged to system E (3.26±0.23) and system C (1.90±0.16), respectively. There was a statistically significant difference between the usability of the systems used in the private and the public hospitals (p<0.001). It was found that the CPOE systems in private hospitals had a higher level of usability (3.42+0.10) compared to those in public hospitals (2.91+0.25).

CONCLUSION

Two main functions of the studied CPOE systems i.e., decision support and prescription support should be developed to make electronic prescription safer and more intuitive. Addressing usability aspects of CPOE systems in practice could improve the usability of these systems for prescription.

[Analysis of drug-related problems in a tertiary university hospital in Barcelona (Spain)]

OBJECTIVE

To describe drug-related problems identified in hospitalized patients and to assess physicians' acceptance rate of pharmacists' recommendations.

METHODS

Retrospective observational study that included all drug-related problems detected in hospitalized patients during 2014-2015. Statistical analysis included a descriptive analysis of the data and a multivariate logistic regression to evaluate the association between pharmacists' recommendation acceptance rate and the variable of interest.

RESULTS

During the study period 4587 drug-related problems were identified in 44,870 hospitalized patients. Main drug-related problems were prescription errors due to incorrect use of the computerized physician order entry (18.1%), inappropriate drug-drug combination (13.3%) and dose adjustment by renal and/or hepatic function (11.5%). Acceptance rate of pharmacist therapy advice in evaluable cases was 81.0%. Medical versus surgical admitting department, specific types of intervention (addition of a new drug, drug discontinuation and correction of a prescription error) and oral communication of the recommendation were associated with a higher acceptance rate.

CONCLUSIONS

The results of this study allow areas to be identified on which to implement optimization strategies. These include training courses for physicians on the computerized physician order entry, on drugs that need dose adjustment with renal impairment, and on relevant drug interactions.