Stewardship Prompts to Improve Antibiotic Selection for Urinary Tract Infection: The INSPIRE Randomized Clinical Trial.

Importance: Urinary tract infection (UTI) is the second most common infection leading to hospitalization and is often associated with gram-negative multidrug-resistant organisms (MDROs). Clinicians overuse extended-spectrum antibiotics although most patients are at low risk for MDRO infection. Safe strategies to limit overuse of empiric antibiotics are needed. Objective: To evaluate whether computerized provider order entry (CPOE) prompts providing patient- and pathogen-specific MDRO risk estimates could reduce use of empiric extended-spectrum antibiotics for treatment of UTI. Design, Setting, and Participants: Cluster-randomized trial in 59 US community hospitals comparing the effect of a CPOE stewardship bundle (education, feedback, and real-time and risk-based CPOE prompts; 29 hospitals) vs routine stewardship (n = 30 hospitals) on antibiotic selection during the first 3 hospital days (empiric period) in noncritically ill adults (≥18 years) hospitalized with UTI with an 18-month baseline (April 1, 2017-September 30, 2018) and 15-month intervention period (April 1, 2019-June 30, 2020). Interventions: CPOE prompts recommending empiric standard-spectrum antibiotics in patients ordered to receive extended-spectrum antibiotics who have low estimated absolute risk (<10%) of MDRO UTI, coupled with feedback and education. Main Outcomes and Measures: The primary outcome was empiric (first 3 days of hospitalization) extended-spectrum antibiotic days of therapy. Secondary outcomes included empiric vancomycin and antipseudomonal days of therapy. Safety outcomes included days to intensive care unit (ICU) transfer and hospital length of stay. Outcomes were assessed using generalized linear mixed-effect models to assess differences between the baseline and intervention periods. Results: Among 127 403 adult patients (71 991 baseline and 55 412 intervention period) admitted with UTI in 59 hospitals, the mean (SD) age was 69.4 (17.9) years, 30.5% were male, and the median Elixhauser Comorbidity Index count was 4 (IQR, 2-5). Compared with routine stewardship, the group using CPOE prompts had a 17.4% (95% CI, 11.2%-23.2%) reduction in empiric extended-spectrum days of therapy (rate ratio, 0.83 [95% CI, 0.77-0.89]; P < .001). The safety outcomes of mean days to ICU transfer (6.6 vs 7.0 days) and hospital length of stay (6.3 vs 6.5 days) did not differ significantly between the routine and intervention groups, respectively. Conclusions and Relevance: Compared with routine stewardship, CPOE prompts providing real-time recommendations for standard-spectrum antibiotics for patients with low MDRO risk coupled with feedback and education significantly reduced empiric extended-spectrum antibiotic use among noncritically ill adults admitted with UTI without changing hospital length of stay or days to ICU transfers. Trial Registration: ClinicalTrials.gov Identifier: NCT03697096.

Stewardship Prompts to Improve Antibiotic Selection for Pneumonia: The INSPIRE Randomized Clinical Trial.

Importance: Pneumonia is the most common infection requiring hospitalization and is a major reason for overuse of extended-spectrum antibiotics. Despite low risk of multidrug-resistant organism (MDRO) infection, clinical uncertainty often drives initial antibiotic selection. Strategies to limit empiric antibiotic overuse for patients with pneumonia are needed. Objective: To evaluate whether computerized provider order entry (CPOE) prompts providing patient- and pathogen-specific MDRO infection risk estimates could reduce empiric extended-spectrum antibiotics for non-critically ill patients admitted with pneumonia. Design, Setting, and Participants: Cluster-randomized trial in 59 US community hospitals comparing the effect of a CPOE stewardship bundle (education, feedback, and real-time MDRO risk-based CPOE prompts; n = 29 hospitals) vs routine stewardship (n = 30 hospitals) on antibiotic selection during the first 3 hospital days (empiric period) in non-critically ill adults (≥18 years) hospitalized with pneumonia. There was an 18-month baseline period from April 1, 2017, to September 30, 2018, and a 15-month intervention period from April 1, 2019, to June 30, 2020. Intervention: CPOE prompts recommending standard-spectrum antibiotics in patients ordered to receive extended-spectrum antibiotics during the empiric period who have low estimated absolute risk (<10%) of MDRO pneumonia, coupled with feedback and education. Main Outcomes and Measures: The primary outcome was empiric (first 3 days of hospitalization) extended-spectrum antibiotic days of therapy. Secondary outcomes included empiric vancomycin and antipseudomonal days of therapy and safety outcomes included days to intensive care unit (ICU) transfer and hospital length of stay. Outcomes compared differences between baseline and intervention periods across strategies. Results: Among 59 hospitals with 96 451 (51 671 in the baseline period and 44 780 in the intervention period) adult patients admitted with pneumonia, the mean (SD) age of patients was 68.1 (17.0) years, 48.1% were men, and the median (IQR) Elixhauser comorbidity count was 4 (2-6). Compared with routine stewardship, the group using CPOE prompts had a 28.4% reduction in empiric extended-spectrum days of therapy (rate ratio, 0.72 [95% CI, 0.66-0.78]; P < .001). Safety outcomes of mean days to ICU transfer (6.5 vs 7.1 days) and hospital length of stay (6.8 vs 7.1 days) did not differ significantly between the routine and CPOE intervention groups. Conclusions and Relevance: Empiric extended-spectrum antibiotic use was significantly lower among adults admitted with pneumonia to non-ICU settings in hospitals using education, feedback, and CPOE prompts recommending standard-spectrum antibiotics for patients at low risk of MDRO infection, compared with routine stewardship practices. Hospital length of stay and days to ICU transfer were unchanged. Trial Registration: ClinicalTrials.gov Identifier: NCT03697070.

Navigating the New Antimicrobial Stewardship Regulations.

Purpose: Many health care facilities are navigating their way through the new antimicrobial stewardship standards and guidelines. The purpose of this article is to provide information for health care facilities to improve patient care. Summary: New regulations and guidelines surrounding antimicrobial stewardship have prompted facilities to review their process related to antimicrobial stewardship. In setting up a program, there are many factors to consider including involving key personnel, obtaining leadership support, identifying an infectious disease physician to chair or cochair the committee, and meeting agenda, metrics, and educational needs. Conclusion: Antimicrobial stewardship plays a vital role in both our hospital and community setting. Pharmacists are uniquely positioned to improve optimal patient care through rounding, review of patients' chart, and contribute to the improvement of antimicrobial stewardship by working with a multidisciplinary team. These efforts may improve the utilization of antimicrobial agents.

Simulated Y-Site Compatibility of Vancomycin and Piperacillin-Tazobactam.

PURPOSE: To evaluate the physical compatibility of vancomycin with piperacillin-tazobactam during simulated Y-site administration. METHODS: Vancomycin and piperacillin-tazobactam were tested using 2 different diluents: 0.9% sodium chloride and 5% dextrose for injection. Vancomycin concentrations of 2, 5, and 10 mg/mL were tested using 0.9% sodium chloride and 4 and 8 mg/mL in 5% dextrose. Piperacillin-tazobactam was diluted to 16, 30, 40, 80, and 100 mg/mL, representing common concentrations used clinically in hospitals, and concentrations were tested in both 0.9% sodium chloride and 5% dextrose for injection. Medications were reconstituted under USP <797> aseptic technique. Combinations were tested in duplicate and reverse order with control solutions. Compatibility testing for Y-site included visual inspection, inspection with a high-intensity monodirectional light source (Tyndall beam), turbidimeter for turbidity evaluation, pH, and microscopic viewing. Testing occurred immediately after mixing, 15 minutes, 60 minutes, and 4 hours. If inconsistencies were observed between samples, testing was repeated to confirm results. Solutions were deemed incompatible if any one test failed and compatible if all tests were accepted. RESULTS: When dextrose 5% for injection was used as the diluent, vancomycin 4 mg/mL was Y-site compatible with piperacillin-tazobactam 16, 30, and 40 mg/mL and incompatible with 80 and 100 mg/mL. Vancomycin 8 mg/mL was incompatible with all tested concentrations of piperacillin-tazobactam. When 0.9% sodium chloride was used as the diluents, Y-site compatibility was found with vancomycin 2 and 5 mg/mL and all tested concentrations of piperacillin-tazobactam. Vancomycin 10 mg/mL was incompatible with piperacillin-tazobactam 40, 80, and 100 mg/mL. Incompatibilities formed a white precipitate immediately on mixing. CONCLUSION: Y-site incompatibility was greater for the tested concentrations of piperacillin-tazobactam and vancomycin when 5% dextrose was used as the diluent versus 0.9% sodium chloride. Y-site incompatibility was seen immediately in the form of a white precipitate on mixing.

Utilizing Pharmacists to Optimize Medication Management Strategies During the COVID-19 Pandemic.

As the COVID-19 pandemic swept through the United States, our heath-system mobilized clinical pharmacy services to address critical clinical medication management needs. Reinforcing recommended medication management strategies for clinical pharmacists was key to successful implementation. Best practice strategies include converting patients from intravenous (IV) to oral medication, transitioning to IV push medication administration, evaluating standard medication administration timing, reviewing metered dose inhaler (MDI) and nebulizer utilization, using alternatives for medications in short supply, reviewing coronavirus disease COVID-19 treatment recommendations, reviewing COVID-19 patient care on interdisciplinary rounds, de-prescribing and de-escalating to eliminate unnecessary medications, and assessing for appropriate venous thromboembolism prophylaxis. These strategies served to help protect medication supply, reduce number of staff entries into patient rooms to conserve personal protective equipment, limit nursing time in patient rooms to reduce COVID-19 exposure risk, and to conserve compounding supplies. Here we present example medication management guidance as used by a large healthcare system during the COVID-19 pandemic.

COVID-19: The Vaccine Race Continues.

Description Over a year has passed since the discovery of SARS-CoV-2 and the subsequent COVID-19 pandemic. As mitigation efforts continue, COVID-19 has claimed over half a million lives in the United States and 3.1 million lives globally. The development and availability of vaccines delivering immunity to prevent COVID-19 offers hope to end the pandemic. Emergency use authorizations from the Food and Drug Administration have been issued in the United States for three vaccines, one each from Pfizer-BioNTech, Moderna and Janssen/J&J. Pfizer-BioNTech and Moderna are both mRNA vaccines with efficacy of 95% and 94.1% respectively, while the vector-based vaccine from Janssen/J&J has an overall efficacy of 66.1%. The Janssen/J&J vaccine, having received the most recent authorization, is an attractive option due to high efficacy with a single dose. With a high immunity rate of 70-80% needed to prevent the continued spread of the virus and mutations, the majority of the population will require vaccination. The rise of mutations from selective pressure has further increased the urgency. Recent discoveries of variants have led to uncertainties regarding the impact of immunity and effectiveness of vaccines. In order to end the global pandemic, it is essential that the Centers for Disease Control and World Health Organization monitor the variant potential and educate the public appropriately to encourage appropriate vaccination and allocation of product. Achieving high vaccination rates in the U.S. has been challenged by supply, storage requirements and public hesitancy. In a recent Gallup poll, a random sample of 4,098 adults demonstrated that 71% of survey respondents were willing to receive a vaccine, which remains on the lower end of the 70-80% vaccination range required to end this pandemic. Despite these challenges, the United States has managed to surpass 225 million vaccinations.

Characteristics Contributing to a Pharmacy Services Excellence Model in a Large Health System.

Objective: To identify characteristics that contribute to and promote a pharmacy services center of excellence model in a large health system. Methods: In 2019, a survey was conducted of 161 acute care pharmacy departments of health system-affiliated hospitals. Information captured included pharmacy practice models, pharmacist resource allocation, training of pharmacy residents, postgraduate training and pharmacist certifications. Results were combined with clinical pharmacy metric performance and centralized electronic data to identify features of top performing pharmacy departments. Results: Survey results were received from 141 of 161 affiliated hospitals (88%). Hospitals with 100 to 299 beds comprised 54% (n = 16 of 30) of the hospitals "at goal" and 66% (n = 26 of 40) of hospitals with "opportunity". Hospitals with top performing pharmacy services had greater participation in interdisciplinary rounds, reporting "always" participating in Adult Critical Care (67% versus 43%) and Medical/Surgical (30% vs. 8%) rounds. Hospitals that trained pharmacy residents had a greater number of clinical pharmacy metrics at goal (5.89 ± 1.59 versus 4.16 ± 1.86, p < 0.001), employed more board-certified pharmacists (2.32 ± 1.49 versus 1.57 ± 1.62, p = 0.019), more postgraduate year 1 (PGY1) trained pharmacists (2.06 ± 1.33 versus 1.19 ± 1.19, p < 0.001) and more PGY2 trained pharmacists (0.58 ± 0.64 versus 0.19 ± 0.44, p = 0.002). When including several key hospital characteristics into a single model, hospitals that trained pharmacy residents were significantly associated with achieving "at goal" status (p = 0.011). Conclusion: Defining characteristics of a pharmacy services center of excellence model included "at goal" clinical pharmacy metrics performance, clinical pharmacist time dedicated to patient care activities, accredited pharmacy residency training programs, presence of pharmacists with advanced training or board certification and optimal operations and scheduling.

Process analysis of procalcitonin monitoring within community hospitals.

PURPOSE: Monitoring of procalcitonin (PCT) levels may support appropriate antibiotic discontinuation. The purpose of this study was to determine the current state of PCT monitoring at community hospitals across the United States. METHODS: Data from adult patients who were admitted to community hospitals affiliated with a large healthcare system between August 1, 2016, and July 31, 2017, and who received antibiotics were evaluated for the number of PCT levels drawn and the timing between multiple levels. Data from eligible patients were evaluated for the discontinuation of antibiotics after meeting prespecified PCT thresholds for discontinuation of therapy, namely, a PCT measurement of <0.5 µg/L or a decrease of ≥80% from a previous peak value. RESULTS: PCT levels were evaluated for 103,913 patient data sets collected from 136 hospitals. Of these, 70% of the data sets showed a single PCT level drawn, and approximately 30% (30,887) of the data sets showed multiple levels drawn. The first PCT measurement was drawn within 36 hours of antibiotic initiation in 96% of the patients. Of those with multiple levels, 23% (7,089) had levels drawn 24 to 72 hours apart. A small proportion (20% [6,127]) of the patients with multiple levels were eligible for evaluation of appropriate antibiotic discontinuation. Of these, 1,973 (32.2%) patients had antibiotics discontinued within 36 hours of meeting the prespecified PCT thresholds; these patients had a mean duration of antibiotic therapy of 6.1 days with a median of 4.7. CONCLUSION: Additional standardization of ongoing PCT monitoring and education regarding the appropriate discontinuation of antibiotics when thresholds are reached could aid in the use of this biomarker in support of antibiotic and laboratory stewardship.

Covid-19: Race For A Vaccine.

Description The world is in the midst of a pandemic from COVID-19, a disease caused by the virus SARS-CoV-2. Despite broad mitigation efforts, new cases continue with 74 million cases and 1.6 million deaths worldwide. Regardless of previous research efforts, there is no commercially available vaccine for any coronavirus. Novel vaccine development has historically taken at least 10 years from discovery to availability with only a 6% market entry probability. With the global impact, there is an urgency to expedite a vaccine to protect the population. The U.S. government launched Operation Warp Speed with the goal to produce and deliver 300 million doses of safe and effective vaccines by January 2021. Efforts toward this goal have included coordinated government agency support, parallel clinical trial deployment, de-risking manufacturing earlier in the development process and real-time U.S. Food & Drug Administration evaluation of the safety and efficacy data. Safety is a priority and key analysis has not been eliminated during the compressed timeframe. The two frontrunner candidates show promising efficacy rates for preventing COVID-19 with Moderna reporting 94.1% efficacy and Pfizer reporting 95.0% efficacy. Despite the herculean efforts by scientists to develop an effective vaccine in such a short timeframe, several national surveys suggest that public confidence in these vaccines is low with less than 50% of the survey respondents willing to be vaccinated. According to experts, the U.S. needs the vaccine to be at least 70-80% effective and a 70-80% vaccination rate in order to return to normal. Significant education and promotion is planned in coordination with the Centers for Disease Control.

Innovative Conservation of Inhaled Medication Devices During the COVID-19 Pandemic Through a Canister Reassignment Process.

Background: The ideal practice for patients requiring metered-dose inhalers (MDI) with coronavirus disease 2019 (COVID-19) is to use patient specific MDIs. However, this practice may not be possible during a time of increased usage throughout the country and limited availability of the medication. Nebulized medications are a concern due to the potential for aerosolized virus and increased exposure for health care workers. An alternative program of canister reassignment is proposed to address concerns for infection prevention, cross-contamination of MDI canisters and the shortage of MDI's due to the COVID-19 pandemic. Methods: A comprehensive MDI canister reassignment process was developed for facilities affiliated with a large health care system in response to the COVID-19 pandemic. The MDI canister reassignment process consisted of 4 components: preservation of supply, reassignment workflow, canister cleaning and operational integration. Albuterol MDI administration data was monitored from January 1st to August 31st, 2020. Results: Following development and rapid implementation of a comprehensive canister reassignment process, albuterol MDI administration data was reviewed from 162 hospitals affiliated with a large health care system. At baseline (prior to the COVID-19 pandemic), 98% of patients received a nebulizer vs. an MDI. After the implementation of the MDI reassignment process (during the COVID-19 pandemic), nebulizer usage decreased by 60% from March 6th to March 31st and was sustained with >50% reduction through August 31st. Conclusion: MDI canister reassignment was an instrumental process to allow the continued delivery of pharmacologic bronchodilator therapy for COVID-19 patients. It also represents an important infection prevention strategy needed to protect our health care providers from the potential aerosolized virus associated with nebulizers.

Pharmacy Services Reboot Roadmap: Resiliency During the COVID-19 Pandemic.

Description Planning for resumption of patient care services during and following the impact of novel coronavirus disease-2019 (COVID-19) while controlling costs are essential for pharmacy services resiliency. Implementation of a pharmacy services reboot roadmap across a 179 hospital health-system is described. The roadmap encompassed eight key areas: pharmacy leadership, staffing and scheduling, clinical pharmacy services, medication safety, medication supply, regulatory and compliance, team support opportunities, and financial stewardship. A supporting checklist and volume-based staffing plan are included as examples to assist pharmacy leaders in planning optimal pharmacy services support as patient volumes increase, particularly in the emergency department, surgical services and critical care areas. Resiliency strategies are provided as tangible planning considerations to assess the current status of, and prepare for, future operational and clinical pharmacy practice needs to support optimal patient care.

Effectiveness of a clinical decision support system to identify heparin induced thrombocytopenia.

BACKGROUND: Subtle decreases in platelet count may impede timely recognition of heparin-induced thrombocytopenia (HIT), placing the patient at increased risk of thrombotic events. OBJECTIVE: A clinical decision support system (CDSS) was developed to alert physicians using computerized provider order entry when a patient with an active order for heparin experienced platelet count decreases consistent with HIT. METHODS: Comparisons for timeliness of HIT identification and treatment were evaluated for the year preceding and year following implementation of the CDSS in patients with laboratory confirmation of HIT. RESULTS: During the intervention time period, the CDSS alert occurred 41,922 times identifying 2,036 patients who had 2,338 inpatient admissions. The CDSS had no significant impact on time from fall in platelet count to HIT laboratory testing (control 2.3 days vs intervention 3.0 days P = 0.30) and therapy (control 19.3 days vs intervention 15.0 days P = 0.45), and appeared to delay discontinuation of heparin products (control 1.3 days vs. intervention 2.9 days P = 0.04). However, discontinuation of heparin following shorter exposure duration and after smaller decrease in platelet count occurred during the intervention period. The HIT CDSS sensitivity and specificity were each 87% with a negative predictive value of 99.9% and positive predictive value of 2.3%. CONCLUSIONS: Implementation of a CDSS did not appear to improve the ability to detect and respond to potential HIT, but resulted in increased laboratory testing and changes in clinician reactions to decreasing platelet counts that deserve further study.

Phased implementation of an antimicrobial stewardship program for a large community hospital system.

BACKGROUND: Antimicrobial stewardship is recommended as a crucial mechanism to reduce the emergence of antimicrobial resistance. The purpose of this article was to describe implementation of antimicrobial management programs (AMPs) across a large health system of community hospitals. METHODS: The initiative was structured in 4 phases. Although each phase was implemented sequentially, facilities could progress at their own pace. Phase goals needed to be met before moving to the next phase. The 4 phases included preparatory, foundational, clinical care optimization, and refinement. A survey was administered prior to the initiative in 2010, and modified surveys were administered in 2015 and 2017. RESULTS: Stewardship activities improved in most areas of the AMP initiative in 2015, with substantial improvement by 2017. Important changes included an increase in established programs, from 82% in 2010 to 88% and 96% in 2015 and 2017, respectively. Physician Champions increased from 73% in 2010 to 94% in 2017. Advances were made in the use of evidence-based treatment recommendations, antibiogram development, prospective audit and feedback for antimicrobials, tracking of antibiotic usage metrics, and a cost reduction of 40% from baseline. CONCLUSION: A well-designed, phased approach to implementing AMP can help community hospitals and hospital systems recognize substantial clinical and financial benefits.

Analysis of antibiotic use in a large network of emergency departments.

PURPOSE: To assess antibiotic selection, administration, and prescribing practices in emergency departments across a large hospital system using evidence-based practices and susceptibility patterns. METHODS: This retrospective data review was conducted using health system-level electronic data compiled from 145 emergency departments (EDs) across the United States. Data were examined for national generalizability, most common diagnoses of infectious origin seen in nonadmitted patients in the ED, most commonly administered antibiotics in the ED, and geographically defined areas' unique patterns of antibiotic resistance and susceptibility. RESULTS: More than 627,000 unique patient encounters and 780,000 antibiotic administrations were assessed for trends in patient demographics, antibiotics administered for a diagnosis of infectious origin, and corresponding susceptibility patterns. Results indicated that practices in the EDs of this health system aligned with evidence-based practices for streptococcal pharyngitis, otitis media, cellulitis, and uncomplicated urinary tract infections. CONCLUSION: These results provide a representative sample of the current state of practices within many EDs across the United States for nonadmitted patients. A similar data reconstruction can be completed by other health systems to assess their prescribing practices in the ED to improve and elevate care for patients visiting the emergency room and treated as outpatients.

Interaction between levodopa and enteral nutrition.

OBJECTIVE: To report and discuss a drug-nutrient interaction involving levodopa and protein in enteral nutrition. CASE SUMMARY: A 77-year-old male with Parkinson's disease was admitted to an intensive care unit for an intracerebral hemorrhage. To provide nutritional support, an oral gastric tube was placed and continuous enteral nutrition was initiated, with 1.4 g/kg of protein administered daily. The following medications were continued during hospitalization: immediate-release carbidopa/levodopa 25 mg/100 mg, with 1.5 tablets administered 4 times daily; pramipexole 1.5 mg 3 times daily; and entacapone 200 mg 4 times daily. Despite this drug therapy, the patient developed severe rigidity. A review of the literature revealed a potential interaction between levodopa and protein intake. To resolve this interaction, the amount of protein in the enteral nutrition was decreased to 0.9 g/kg/day and the nutritional administration was changed from continuous enteral feeding to bolus feeding, with levodopa given between boluses. After these adjustments, the patient showed marked improvement of parkinsonian symptoms. DISCUSSION: The drug-nutrient interaction between protein and levodopa in outpatient settings has been reported widely in the literature; however, this interaction has not been previously reported with continuous enteral nutrition. Decreased parkinsonian symptom control, despite adherence to an established medication regimen, together with dramatic improvement observed after manipulation of enteral nutrition delivery and content, strongly suggest interference with levodopa absorption. Use of the Naranjo probability scale supports a probable interaction between the protein content in tube feeds and levodopa, resulting in decreased levodopa efficacy. CONCLUSIONS: Clinicians should be cognizant of the potential drug-nutrient interaction between levodopa and enteral nutrition.

Use of clinical decision support to identify i.v.-to-oral conversion opportunities and cost savings.

PURPOSE: The use of a clinical decision support (CDS) tool to determine patients' eligibility for oral medication therapy and the opportunity cost of i.v.-to-oral conversion practices in a large health system was evaluated. METHODS: This multicenter, retrospective, process improvement study comprised CDS data generated by 149 hospitals from May 1 through October 31, 2015. Data related to i.v.-to-oral conversions were identified and compiled for evaluation. For each patient with an opportunity for i.v.-to-oral therapy conversion, corresponding barcode-assisted medication administration data were evaluated to determine the number of doses that were administered within prespecified time periods. RESULTS: A total of 121,685 i.v.-to-oral conversion opportunities, corresponding to 71,342 unique patients and encompassing 31 different medications, were evaluated. The top 13 medications representing 94% of the total number of alerts and over 1.4 million doses were included for analysis. Current i.v.-to-oral conversion practices saved the hospitals 9% on medication costs. Upon further evaluation, additional cost savings of 29-78% for those 13 medications could be achieved with more timely conversion from i.v. to oral therapy. CONCLUSION: Hospital pharmacists' i.v.-to-oral conversion practices with the CDS tool resulted in medication cost savings of 9%, or $1.48 million, for 13 medications evaluated over a 6-month period.