Concordance analysis of two databases to search for potential drug interactions in onco-hematologic patients.

INTRODUCTION: Potential drug interactions exert a significant impact on patient safety, especially within intricate onco-hematological treatments, potentially resulting in toxicity or treatment failures. Despite the availability of databases for potential drug interaction investigation, persistent heterogeneity in concordance rates and classifications exists. The additional variability in database agreement poses further complexity, notably in critical contexts like onco-hematology. AIM: To analyze the concordance of two databases for researching potential drug interaction in prescriptions for hematological patients at a University Hospital in the Midwest region of Brazil. METHOD: Cross-sectional study developed in a Brazilian hospital. The search for potential drug interaction was conducted in Micromedex® and UpToDate®. The variables were: the presence of potential drug interaction, severity, mechanism, management, and documentation. Data was analyzed in terms of frequency (absolute and relative), Cohen's kappa, and Fleiss kappa. RESULTS: The presence of potential drug interaction, showed a lack of concordance between the databases (k = -0.115 [95% CI: 0.361-0.532], p = 0.003). Regarding the mechanism, a strong agreement was observed (k = 0.805, p < 0.001 [95% CI: 0.550-0.941]). The management concordance showed a fair agreement, 46.8% (k = 0.22, p < 0.001 [95% CI: 0.099-0.341]). Stratifying the categories, significant concordance was observed in "Adjustment of dose + Monitoring" (k = 0.302, p = 0.018) and "Monitoring" (k = 0.417, p = 0.001), while other categories did not reach statistical significance. CONCLUSION: Our study emphasizes the variability in potential drug interaction research, revealing disparities in severity classification, management recommendations, and documentation practices across databases.

Validation of a computerized decision support system to review pharmacotherapy treatment: scheduling guidelines.

BACKGROUND: The review of pharmacotherapy can be conceptualized as a service in which the drugs used by the patient are reviewed to control the risks as well as to improve the results of the drug therapy, detecting, solving, and preventing issues associated with the drug, readjusting the doses and times (schedule) so that the treatment is not incompatible or in duplicity. METHODS: The aim of the study was to validate an intelligent information system, which was developed to assist the scheduling activity in the pharmacotherapy review. The system used the concept of Genetic Algorithms. To validate the system, hypothetical cases were elaborated considering various aspects of pharmacotherapy such as underdose, overdose, drug interactions and contraindications. These cases were tested in the system and were also analyzed by pharmaceutical experts with clinical and research experience in the pharmacotherapy review process. The degree of agreement between the assessments of the appointments carried out by the pharmaceutical specialists and by the system were measured using the Kappa index with a 95% confidence interval. RESULTS: In detecting errors and make propositions, the system was able to identify 80% of errors, with pharmaceutical experts identifying between 20 and 70% of errors. In relation the results of kappa between the cases, the system had 87,3% of concordance, whereas the best pharmaceutical expert had 75,5% of concordance, considering the correct answer. CONCLUSION: It can be concluded that with the methodology used, the investigation met the objectives and confirmed the system is effective for pharmaceutical review process. There are indications that the system can help in the Pharmacotherapy review process, being able to find prescription errors as well as to establish times for the use of medications according to the patient's routine.

Evaluation of adverse drug reaction formatting in drug information mobile phone applications.

OBJECTIVE: To evaluate the differences in presentation (formatting) of adverse drug reaction (ADR) information within drug monographs in commonly used drug information (DI) mobile device applications. METHODS: A cross-sectional analysis of ADR formatting of twenty commonly prescribed oral medications within seven DI mobile applications was performed. Databases were assessed for ADR information, including presence of placebo comparisons, severity of ADR, onset of ADR, formatting of ADRs in percentile (quantitative) format or qualitative format, whether references were used to cite information, and whether ADRs are grouped by organ system. Data was collected by two study investigators and discrepancies were resolved via consensus. RESULTS: The seven DI mobile applications varied significantly on every analyzed ADR variable with the exception of ADR onset, which was absent in all databases. Significant differences were found for variables known to impact clinical judgment such as placebo comparisons and qualitative versus quantitative formatting. Placebo comparisons were most common among monographs in Lexicomp (30%) but were absent among monographs within other applications. Quantitative information was commonly used in most databases but was absent in Epocrates. Qualitative formatting was present in all Epocrates and Micromedex applications but absent in the majority of other applications. Substantial variations were also found in severity and grouping information. CONCLUSION: Substantial variation in ADR formatting exists among the most common DI mobile applications. These differences may translate into alternative interpretations of medical information and thus impact clinical judgment. Health care librarians and clinicians should consider ADR formatting when choosing between DI applications.

Utilization of a Pharmacy Clinical Surveillance System for Pharmacist Alerting and Communication at a Tertiary Academic Medical Center.

The objective of this analysis is to describe the utilization metrics of a pharmacy clinical surveillance system (PCSS) at a tertiary, academic medical center.We performed a retrospective database analysis assessing rule-based alerts (RBA), interventions and pharmacist communication notes documented in the PCSS from January 1, 2014 to December 31, 2014. Reports were generated on 92 unique RBAs sent to clinicians for evaluation. Metrics assessed included the number of RBAs that were triggered, clinically evaluated, intervened on by pharmacists, and therapeutic category of interventions. Pharmacy communication notes were also evaluated.A total of 399,979 RBAs were triggered through the PCSS. During that time, pharmacists documented a total of 17,733 interventions. The most common RBAs were related to lab abnormalities (132,487; 33 %) and anticoagulation/antiplatelet therapy (126,425; 32.1 %). Interventions were most frequently related to RBAs regarding anticoagulation/antiplatelet therapy (6412; 36 %) and antimicrobial therapy (3320; 19 %). Pharmacist communication was most commonly related to clarification of medication and lab orders, and therapeutic drug monitoring.Based on utilization metrics presented, the implementation of a PCSS has successfully generated RBAs to aid pharmacists in clinical practice and improved departmental documentation and communication. Further analysis is warranted to assess the impact of the RBAs, interventions, and communication notes on outcomes such as hospital cost and adverse drug events.

Novel opportunities for clinical pharmacy research: development of a machine learning model to identify medication related causes of delirium in different patient groups.

The advent of artificial intelligence (AI) technologies has taken the world of science by storm in 2023. The opportunities of this easy to access technology for clinical pharmacy research are yet to be fully understood. The development of a custom-made large language model (LLM) (DELSTAR) trained on a wide range of internationally recognised scientific publication databases, pharmacovigilance sites and international product characteristics to help identify and summarise medication related information on delirium, as a proof-of-concept model, identified new facilitators and barriers for robust clinical pharmacy practice research. This technology holds great promise for the development of much more comprehensive prescribing guidelines, practice support applications for clinical pharmacy, increased patient and prescribing safety and resultant implications for healthcare costs. The challenge will be to ensure its methodologically robust use and the detailed and transparent verification of its information accuracy.

Med rec double check: Inpatient psychiatry medication errors identified on admission using Medicaid Web portals and electronic pharmaceutical claims data.

Introduction: The role of pharmacists during medication reconciliation (MR) is well established, with a number of reports describing this in the context of psychiatric hospitalizations. However, medication errors (MEs) are common during transitions of care, with no exception during psychiatric hospitalizations. Our institution uses pharmacy-performed MR processes using patient interviews and reviewing objective sources, such as electronic pharmaceutical claims data (EPCD), which includes Medicaid Web portals. The inpatient psychiatric pharmacist reviews EPCD sources against previously pharmacy-completed MRs for new admissions, where if discrepancies are found, the patient is reinterviewed to identify and correct MEs. Methods: We performed a prospective quality improvement project during 28 days to evaluate the quantity and classification of MEs upon admission to a 22-bed inpatient psychiatry unit. Results: Of 52 included patients, where a cumulative 426 medications were reviewed, a total of 29 MEs in 16 patients were identified. Eight patients had discrepancies on their home medication lists when compared to EPCD, where 7 of these had at least 1 ME due to inaccurate MR. Discussion: Of all the MEs identified, the greatest quantity was found secondary to the EPCD "double-check" method. The most common MEs in all patients were the omission of home medications (34%), wrong frequency (28%), and ordering medication the patient is not taking (10%). All patients admitted on long-acting injection antipsychotics had errors in last dose received. No MEs resulted in patient harm, and they were identified and corrected by the psychiatric pharmacist 97% of the time.

Enhancing the clinical pharmacy service of a large teaching hospital: Development of a new clinical prioritisation tool.

Background: The number and complexity of patients being admitted to hospitals is rising and some patients may not receive a full clinical pharmacy review or be reviewed as regularly as needed during their inpatient stay. This is a risk factor for medication errors. Clinical prioritisation identifies patients who are high-risk and most in need of a pharmacist review, targeting finite pharmacy resources to patients who will benefit the most. Objectives: Assess and enhance clinical prioritisation within a hospital pharmacy department. Methods: The study was conducted in a large urban academic teaching hospital. A cross-sectional survey of clinical pharmacists in the hospital was conducted to establish the patient clinical criteria they prioritise in their work. A clinical prioritisation tool was developed based on survey findings and was integrated into an existing electronic pharmacy care interface. A pre- and post-intervention study was conducted, consisting of data collection for five days pre- and five days post-implementation of the tool. Quantitative data were analysed using descriptive and inferential statistics. Qualitative data were analysed by thematic analysis. Results: Of 39 eligible pharmacists, 37 (95%) responded to the survey. The top-rated prioritisation criteria, including medicines reconciliation tasks and high-risk medicines, helped to inform the content of the clinical prioritisation tool. Post-intervention, there were more Level 1 complex patients reviewed by pharmacists and fewer Level 3 stable patients compared to pre-intervention. Tool sensitivity ranged from 51 to 88%, depending on the experience of the pharmacist using the tool. High levels of satisfaction with clinical prioritisation were reported by those using the tool. Conclusion: This newly developed clinical prioritisation tool has the potential to support pharmacists in identifying and reviewing patients in a more targeted manner than practice prior to tool development. Continued development and validation of the tool is essential, with a focus on developing a fully automated tool.

Improving medication safety in a paediatric hospital: a mixed-methods evaluation of a newly implemented computerised provider order entry system.

OBJECTIVES: Computerised provider order entry (CPOE) systems have been implemented around the world as a solution to reduce ordering and transcription errors. However, previous literature documented many challenges to attain this goal, especially in paediatric settings. The objectives of this study were to (1) analyse the impact of a paediatric CPOE system on medication safety and (2) suggest potential error prevention strategies. METHODS: A pre-post observational study was conducted at the pilot ward (n=60 beds) of a paediatric academic health centre through mixed methods. The implementation project and medication management workflows were described through active participation to the project management team, observation, discussions and analysis of related documents. Furthermore, using incident reports, the nature of each error and error rate was compared between the preperiod and postperiod. RESULTS: The global error rate was lower, but non-statistically significant, in the post implementation phase, which was mostly driven by a significant reduction in errors during order acknowledgement, transmission and transcription. Few errors occurred at the prescription step, and most errors occurred during medication administration. Furthermore, some errors could have been prevented using a CPOE in the pre-implementation period, and the CPOE led to few technology-related errors. DISCUSSION AND CONCLUSION: This study identified both intended and unintended effects of CPOE adoption through the entire medication management workflow. This study revealed the importance of simplifying the acknowledgement, transmission and transcribing steps through the implementation of a CPOE to reduce medication errors. Improving the usability of the electronic medication administration record could help further improve medication safety.

An EHR-based method to structure, standardize, and automate clinical documentation tasks for pharmacists to generate extractable outcomes.

As the recognition of team-based care grows and pharmacists increase in patient care interventions, it is important that tools to track clinical services are easily accessible and well-integrated into workflow for all providers. We describe and discuss feasibility and implementation of data tools in an electronic health record to evaluate a pragmatic clinical pharmacy intervention focused on deprescribing in aged adults delivered at multiple clinical sites in a large academic health system. Of the data tools utilized, we were able to demonstrate clear documentation frequency of certain phrases during the intervention period for 574 patients receiving opioids and 537 patients receiving benzodiazepines. Although clinical decision support and documentation tools exist, they are underutilized or cumbersome to integrate into primary health care and strategies, such as employed, are a solution. This communication incorporates the importance of clinical pharmacy information systems in research design.

Clicks away from reduced healthcare expenditures: leveraging the electronic health record to reinforce education efforts.

OBJECTIVES: Lupron 11.25 mg has both a narrow indication and a high cost compared to other Lupron presentations. Prior to our study initiation there was no clear distinction between presentations when ordering within the health-system's Electronic Health Record (EHR). This resulted in inappropriate product selection, payment and billing errors that negatively impact our healthcare system. To reinforce prior education efforts, a new approach was considered leveraging the EHR with information to steer prescribers to the proper Lupron presentation based on indication. This study aimed to reduce off-label prescribing for Lupron 11.25 mg (NDC 00074-3663-03) by 25% by 02/28/2022 without negatively impacting the insurance collection rate. METHODS: Baseline Lupron 11.25 mg adult kit administrations one year prior to intervention and off-label prescribing was found to account for 22.7% of administrations. In December 2021 intervention order questions were added to Lupron 11.25 mg in the EHR. One and two-month data was obtained after implementing order questions within the EHR. Lupron 11.25 mg administrations were classified into one of four categories to determine impact on off-label prescribing. RESULTS: In the one- and two-month post-implementation periods off-label prescribing was 0% and 15.3% respectively, a reduction of 22.7% to and 7.4% respectively from the baseline assessment. There were no clinical denials found in either post-implementation reporting period. CONCLUSION: This report adds to the body of evidence that leveraging the EHR can lead to healthcare savings and illustrates how patient and healthcare system burden can be reduced by prompting thought and direction when a medication has indication specific dose requirements.

Utilising an automated medication inventory management system for emergency crash carts during the COVID-19 pandemic.

The high acuity of patients with COVID-19 during the pandemic in the city of New York correlated with an increased incidence of cardiac arrests and other emergent resuscitation scenarios requiring life-sustaining treatment. A spike in the utilisation of emergency crash cart medications was to be expected. The department of pharmacy at SUNY Downstate Health Sciences University optimised the use of an automated medication inventory management system with radio-frequency identification to assess usage and turnover of emergency crash carts; improve efficiency and turnaround times for crash cart dispatches; track drug consumption; and manage ongoing medication shortages during the peak of the COVID-19 pandemic. By capitalising on the utility and functionality of technology and automation, the institution was able to keep pace with acute patient care demands to prevent gaps in pharmaceutical care and medication management during emergency responses.

Implementation and safety evaluation of autoverification for select low-risk, high-volume medications in the emergency department.

PURPOSE: Use of autoverification has decreased in many emergency departments (EDs) with the expansion of emergency medicine (EM) pharmacists. Few studies have evaluated ways to prioritize verification of medications. Here we describe a process to design, implement, and measure the safety of autoverification of low-risk, high-volume medications. SUMMARY: A 3-month retrospective review of medications ordered and administered in the ED generated a list of medications to be considered for autoverification. Concurrently, a novel risk stratification tool was created to identify low-risk medications. Taking these together, medications that were high volume and low risk were considered potentially autoverified medications (PAMs). To evaluate the safety of PAMs, a retrospective review of the ED medication orders placed before implementation of autoverification was performed. A total of 7,433 medication orders were reviewed. Of these, 3,057 orders (41%) were identified as PAMs. EM pharmacists verified 2,982 (97.5%) of the orders without changes. Of the remaining 93 orders that were modified or discontinued and met autoverification criteria, only 2 (0.07%) were identified as potentially inappropriate for autoverification. CONCLUSION: Low-risk, high-volume medications can be safely autoverified in the ED by using a systematic approach to order selection. Using these methods can provide large decreases in verification volume, close to 41%, without compromising patient safety.

Assessment of a hybrid decision support system using machine learning with artificial intelligence to safely rule out prescriptions from medication review in daily practice.

Background Medication review is time-consuming and not exhaustive in most French hospitals. We routinely use an innovative hybrid decision support system using Artificial Intelligence to prioritize medication review by scoring prescriptions by their risk of containing at least one drug related problem (DRP). Aim Our aim was to attest that the prescriptions with low risk of DRPs ruled out by the tool in everyday practice were effectively free of any DRPs with potentially severe clinical impact. Methods We conducted a randomized single-blinded study to compare the rate of pharmaceutical interventions (PI) between low and high-risk prescriptions defined by the tool's calculated score. Prescriptions were reviewed daily by a clinical pharmacist. Proportion of prescriptions with at least one severe DRP was calculated in both groups. Severe DRPs were characterized through a multidisciplinary approach. Results Four hundred and twenty (107 low score and 313 high score) prescriptions were analyzed. The percentage of prescriptions with severe DRPs was dramatically decreased in low score prescriptions (2.8% vs. 15.3% for high-risk; p = 0.0248). A significant difference was found (94% vs. 20%; p < 0.001) in the percentage of severe DRPs detected by the hybrid approach compared to a CDSS. During the study period, the hybrid tool allowed to rule out 55% of all prescriptions in our hospital.Conclusion This hybrid decision support tool has shown to be accurate to detect DRPs in daily practice. Despite some limitations, it offers the best possible solution to prioritized medication review, considering the shortage of clinical pharmacists in France and considerably improves the safety of patients' care.

Interventions to Increase Leukocyte Testing during Treatment with Dimethyl Fumarate.

Dimethyl fumarate (DMF), a treatment for multiple sclerosis, may cause leukopenia and infection. Accordingly, periodic white blood cell (WBC) monitoring is recommended. We sought to evaluate the US Department of Veteran Affairs' safety program which provides facilities with a list of patients prescribed DMF therapy without a documented white blood cell count (WBC). We identified 118 sites with patients treated with DMF from 1 January 2016 through 30 September 2016. Each site was asked if any of seven interventions were used to improve WBC monitoring (academic detailing, provider education without academic detailing, electronic clinical reminders, request for provider action plan, draft orders for WBC monitoring, patient mailings, and patient calls). The survey response rate was 78%. For the 92 responding sites (78%) included sites (1115 patients) the mean rate of WBC monitoring was 54%. In multivariate analysis, academic detailing increased the rate by 17% (95% CI 4 to 30%, p = 0.011) and provider education increased the rate by 9% (95% CI 0.6 to 18%, p = 0.037). The WBC monitoring rate increased by 3.8% for each additional intervention used (95% CI 1.2-6.4%, p = 0.005). Interventions focused on the physician, including academic detailing, were associated with improved WBC monitoring for patients at risk for leukopenia from DMF treatment.

Pharmacists' perceptions of a machine learning model for the identification of atypical medication orders.

OBJECTIVES: The study sought to assess the clinical performance of a machine learning model aiming to identify unusual medication orders. MATERIALS AND METHODS: This prospective study was conducted at CHU Sainte-Justine, Canada, from April to August 2020. An unsupervised machine learning model based on GANomaly and 2 baselines were trained to learn medication order patterns from 10 years of data. Clinical pharmacists dichotomously (typical or atypical) labeled orders and pharmacological profiles (patients' medication lists). Confusion matrices, areas under the precision-recall curve (AUPRs), and F1 scores were calculated. RESULTS: A total of 12 471 medication orders and 1356 profiles were labeled by 25 pharmacists. Medication order predictions showed a precision of 35%, recall (sensitivity) of 26%, and specificity of 97% as compared with pharmacist labels, with an AUPR of 0.25 and an F1 score of 0.30. Profile predictions showed a precision of 49%, recall of 75%, and specificity of 82%, with an AUPR of 0.60, and an F1 score of 0.59. The model performed better than the baselines. According to the pharmacists, the model was a useful screening tool, and 9 of 15 participants preferred predictions by medication, rather than by profile. DISCUSSION: Predictions for profiles had higher F1 scores and recall compared with medication order predictions. Although the performance was much better for profile predictions, pharmacists generally preferred medication order predictions. CONCLUSIONS: Based on the AUPR, this model showed better performance for the identification of atypical pharmacological profiles than for medication orders. Pharmacists considered the model a useful screening tool. Improving these predictions should be prioritized in future research to maximize clinical impact.

A machine learning-based clinical decision support system to identify prescriptions with a high risk of medication error.

OBJECTIVE: To improve patient safety and clinical outcomes by reducing the risk of prescribing errors, we tested the accuracy of a hybrid clinical decision support system in prioritizing prescription checks. MATERIALS AND METHODS: Data from electronic health records were collated over a period of 18 months. Inferred scores at a patient level (probability of a patient's set of active orders to require a pharmacist review) were calculated using a hybrid approach (machine learning and a rule-based expert system). A clinical pharmacist analyzed randomly selected prescription orders over a 2-week period to corroborate our findings. Predicted scores were compared with the pharmacist's review using the area under the receiving-operating characteristic curve and area under the precision-recall curve. These metrics were compared with existing tools: computerized alerts generated by a clinical decision support (CDS) system and a literature-based multicriteria query prioritization technique. Data from 10 716 individual patients (133 179 prescription orders) were used to train the algorithm on the basis of 25 features in a development dataset. RESULTS: While the pharmacist analyzed 412 individual patients (3364 prescription orders) in an independent validation dataset, the areas under the receiving-operating characteristic and precision-recall curves of our digital system were 0.81 and 0.75, respectively, thus demonstrating greater accuracy than the CDS system (0.65 and 0.56, respectively) and multicriteria query techniques (0.68 and 0.56, respectively). DISCUSSION: Our innovative digital tool was notably more accurate than existing techniques (CDS system and multicriteria query) at intercepting potential prescription errors. CONCLUSIONS: By primarily targeting high-risk patients, this novel hybrid decision support system improved the accuracy and reliability of prescription checks in a hospital setting.

A Survey-based Study of Pharmacist Acceptance and Resistance to Health Information Technology.

Purpose: Because user acceptance and resistance to the use of health information technology (HIT) affects system utilization and previous studies in this area have typically excluded pharmacists, this study specifically addresses the response of institutional pharmacists to HIT. Methods: A survey investigating pharmacists' responses to electronic medical record (EMR) system use was developed using questions modified from previously validated research. The survey was distributed electronically to the mailing list for pharmacy preceptors for the University of Tennessee College of Pharmacy. Descriptive statistics and univariate and multivariate analyses were used to analyze the collected data based on a previously validated dual-factor model. Results: Of the 96 responses from institutional pharmacists, 64 responses (66.7 percent) were complete and usable. Of the acceptance and resistance constructs evaluated, only attitude and perceived behavior control were found to be significantly associated with acceptance of use (p = .036 and p = .025, respectively), and only transition cost was found to be significantly associated with resistance to use (p = .018). System vendor and interface integration were also significantly associated with acceptance of use. These findings suggest that attitude, perceived behavior control, and transition costs may have the most impact on pharmacists' responses to the use of EMR systems. Conclusion: It is reasonable for hospitals to focus efforts on specific factors influencing acceptance of and resistance to EMR use and, before a system is selected, to consider the effects of vendor selection and level of interface integration on acceptance of use.

Analysis of dosing-button compliance.

PURPOSE: A project was undertaken at an academic medical center to assess use of available dosing buttons within the computerized provider-order-entry (CPOE) system in order to identify opportunities for optimization of medication builds. METHODS: A retrospective observational study was conducted to identify medication records within a CPOE system meeting prespecified inclusion and exclusion criteria. A report capturing all inpatient adult medication orders associated with the identified medication records over a 6-month period was generated. The primary endpoint was percent dosing-button compliance, calculated as the number of orders with doses consistent with existing dosing-button options divided by the total number of orders during the study period. Secondary study objectives included a comparison of high- and low-performing medication record samples and identification of potential reasons for lack of dosing-button use. RESULTS: A total of 2,506 CPOE medication records associated with a total of 694,877 medication orders entered during the study period were analyzed. Median percent dosing-button compliance was 99.92% (interquartile range, 83.33-100%). High-performing records (n = 1243) were more likely to be associated with anti-infective medications (p = 0.041) and medications not on formulary at the study institution (p < 0.001). Medications in the sample of poor-performing CPOE records (n = 614) were more likely to be agents delivered via the i.v. route (p < 0.001). There were 45 records for which poor dosing-button compliance was attributed to lack of a clinically reasonable dosing option. CONCLUSION: A high level of dosing-button compliance was demonstrated despite the lack of routine revalidation of dosing buttons after initial medication builds. Some opportunity for optimization was identified during the project, which established a quality assurance method to facilitate future auditing of medication builds.

Initial study of clinical pharmacy work prioritization tools.

PURPOSE: The development, implementation, and validity of clinical pharmacy work prioritization tools (CPWPTs) were analyzed. METHODS: Informatics pharmacists were contacted and asked to participate in 30-minute teleconference interviews, as they have primary responsibility for the technical configuration of CPWPTs. A total of 19 respondents participated in the survey. The qualitative data collected encompassed the thoughts and ideas of practicing informatics pharmacists who are knowledgeable about the design, configuration, management, and use of CPWPTs. In addition to capturing their thoughts and ideas with open-ended questions, demographic data were collected, as was information about the sites where respondents worked and the CPWPTs they used. RESULTS: Most of the CPWPTs were built into existing electronic health record platforms. There was considerable variation among the prioritization factors used at each site. The most commonly identified categories of prioritization factors were patient-specific factors, therapeutic classes of medications, and potential pharmacist interventions. All respondents reported that the prioritized tasks generated by their CPWPTs were examined for face validity. Of the 19 respondents, only 4 reported that the priorities generated by their CPWPT had been empirically validated in some way. Qualitative data analysis revealed that informatics pharmacists have 5 general perceptions about CPWPT factors, validation, and use in practice: (1) mirroring practice, (2) pharmacist consensus-based design, (3) complexity of logic, (4) tension between task-oriented and patient-centric approaches to practice, and (5) comfort from tracking tasks to completion. CONCLUSION: Early CPWPTs vary significantly in their prioritization factors. These tools partially reflect the scope of clinical pharmacy practice at the sites where they are used.