Leveraging artificial intelligence to advance implementation science: potential opportunities and cautions.

BACKGROUND: The field of implementation science was developed to address the significant time delay between establishing an evidence-based practice and its widespread use. Although implementation science has contributed much toward bridging this gap, the evidence-to-practice chasm remains a challenge. There are some key aspects of implementation science in which advances are needed, including speed and assessing causality and mechanisms. The increasing availability of artificial intelligence applications offers opportunities to help address specific issues faced by the field of implementation science and expand its methods. MAIN TEXT: This paper discusses the many ways artificial intelligence can address key challenges in applying implementation science methods while also considering potential pitfalls to the use of artificial intelligence. We answer the questions of "why" the field of implementation science should consider artificial intelligence, for "what" (the purpose and methods), and the "what" (consequences and challenges). We describe specific ways artificial intelligence can address implementation science challenges related to (1) speed, (2) sustainability, (3) equity, (4) generalizability, (5) assessing context and context-outcome relationships, and (6) assessing causality and mechanisms. Examples are provided from global health systems, public health, and precision health that illustrate both potential advantages and hazards of integrating artificial intelligence applications into implementation science methods. We conclude by providing recommendations and resources for implementation researchers and practitioners to leverage artificial intelligence in their work responsibly. CONCLUSIONS: Artificial intelligence holds promise to advance implementation science methods ("why") and accelerate its goals of closing the evidence-to-practice gap ("purpose"). However, evaluation of artificial intelligence's potential unintended consequences must be considered and proactively monitored. Given the technical nature of artificial intelligence applications as well as their potential impact on the field, transdisciplinary collaboration is needed and may suggest the need for a subset of implementation scientists cross-trained in both fields to ensure artificial intelligence is used optimally and ethically.

Implementation of clopidogrel pharmacogenetic clinical decision support for a preemptive return of results program.

DISCLAIMER: In an effort to expedite the publication of articles, AJHP is posting manuscripts online as soon as possible after acceptance. Accepted manuscripts have been peer-reviewed and copyedited, but are posted online before technical formatting and author proofing. These manuscripts are not the final version of record and will be replaced with the final article (formatted per AJHP style and proofed by the authors) at a later time. PURPOSE: To describe our experiences implementing and iterating CYP2C19 genotype-guided clopidogrel pharmacogenetic clinical decision support (CDS) tools over time in the setting of a large health system-wide, preemptive pharmacogenomics program. SUMMARY: Clopidogrel-treated patients who are genetically predicted cytochrome P450 isozyme 2C19 intermediate or poor metabolizers have an increased risk of atherothrombotic events, some of which can be life-threatening. The Clinical Pharmacogenetics Implementation Consortium provides guidance for the use of clopidogrel based on CYP2C19 genotype in patients with cardiovascular and cerebrovascular diseases. Our multidisciplinary team implemented an automated, interruptive alert that fires when clopidogrel is ordered or refilled for biobank participants with structured CYP2C19 intermediate or poor metabolizer genomic indicators in the electronic health record. The implementation began with a narrow cardiovascular indication and setting and was then scaled in 4 primary dimensions: (1) clinical indication; (2) availability across health-system locations; (3) care venue (e.g., inpatient vs outpatient); and (4) provider groups (eg, cardiology and neurology). We iterated our approach over time based on evolving clinical evidence and proactive strategies to optimize CDS maintenance and sustainability. A key facilitator of expansion was socialization of the broader pharmacogenomics initiative among our academic medical center community, accompanied by clinician acceptance of pharmacogenetic alerts in practice. CONCLUSION: A multidisciplinary collaboration is recommended to facilitate the use of CYP2C19 genotype-guided antiplatelet therapy in patients with cardiovascular and cerebrovascular diseases. Evolving clopidogrel pharmacogenetic evidence necessitates thoughtful iteration of implementation efforts and strategies to optimize long-term maintenance and sustainability.

Evaluating the prescribing and monitoring of medications associated with QTc-prolongation in the ambulatory care setting.

RATIONALE: Little is known about the prescribing of medications with potential to cause QTc-prolongation in the ambulatory care settings. Understanding real-world prescribing of QTc-prolonging medications and actions taken to mitigate this risk will help guide strategies to optimize safety and appropriate prescribing among ambulatory patients. OBJECTIVE: To evaluate the frequency of clinician action taken to monitor and mitigate modifiable risk factors for QTc-prolongation when indicated. METHODS: This retrospective, cross-sectional study evaluated clinician action at the time of prescribing prespecified medications with potential to prolong QTc in adult patients in primary care. The index date was defined as the date the medication was ordered. Electronic health record (EHR) data were evaluated to assess patient, clinician and visit characteristics. Clinician action was determined if baseline or follow-up monitoring was ordered or if action was taken to mitigate modifiable risk factors (laboratory abnormalities or electrocardiogram [ECG] monitoring) within 48 h of prescribing a medication with QTc-prolonging risk. Descriptive statistics were used to describe current practice. RESULTS: A total of 399 prescriptions were prescribed to 386 patients, with a mean age of 51 ± 18 years, during March 2021 from a single-centre, multisite health system. Of these, 17 (4%) patients had a known history of QTc-prolongation, 170 (44%) did not have a documented history of QTc-prolongation and 199 (52%) had an unknown history (no ECG documented). Thirty-nine patients (10%) had at least one laboratory-related risk factor at the time of prescribing, specifically hypokalemia (16 patients), hypomagnesemia (8 patients) or hypocalcemia (19 patients). Of these 39 patients with laboratory risk factors, only 6 patients (15%) had their risk acknowledged or addressed by a clinician. Additionally, eight patients' most recent QTc was ≥500 ms and none had an ECG checked at the time the prescription was ordered. CONCLUSION: Despite national recommendations, medication monitoring and risk mitigation is infrequent when prescribing QTc-prolonging medications in the ambulatory care setting. These findings call for additional research to better understand this gap, including reasons for the gap and consequences on patient outcomes.

Sustained Effect of Clinical Decision Support for Heart Failure: A Natural Experiment Using Implementation Science.

OBJECTIVES: In a randomized controlled trial, we found that applying implementation science (IS) methods and best practices in clinical decision support (CDS) design to create a locally customized, "enhanced" CDS significantly improved evidence-based prescribing of ß blockers (BB) for heart failure compared with an unmodified commercially available CDS. At trial conclusion, the enhanced CDS was expanded to all sites. The purpose of this study was to evaluate the real-world sustained effect of the enhanced CDS compared with the commercial CDS. METHODS: In this natural experiment of 28 primary care clinics, we compared clinics exposed to the commercial CDS (preperiod) to clinics exposed to the enhanced CDS (both periods). The primary effectiveness outcome was the proportion of alerts resulting in a BB prescription. Secondary outcomes included patient reach and clinician adoption (dismissals). RESULTS: There were 367 alerts for 183 unique patients and 171 unique clinicians (pre: March 2019-August 2019; post: October 2019-March 2020). The enhanced CDS increased prescribing by 26.1% compared with the commercial (95% confidence interval [CI]: 17.0-35.1%), which is consistent with the 24% increase in the previous study. The odds of adopting the enhanced CDS was 81% compared with 29% with the commercial (odds ratio: 4.17, 95% CI: 1.96-8.85). The enhanced CDS adoption and effectiveness rates were 62 and 14% in the preperiod and 92 and 10% in the postperiod. CONCLUSION: Applying IS methods with CDS best practices was associated with improved and sustained clinician adoption and effectiveness compared with a commercially available CDS tool.

The iPRISM webtool: an interactive tool to pragmatically guide the iterative use of the Practical, Robust Implementation and Sustainability Model in public health and clinical settings.

BACKGROUND: To increase uptake of implementation science (IS) methods by researchers and implementers, many have called for ways to make it more accessible and intuitive. The purpose of this paper is to describe the iPRISM webtool (Iterative, Practical, Robust Implementation and Sustainability Model) and how this interactive tool operationalizes PRISM to assess and guide a program's (a) alignment with context, (b) progress on pragmatic outcomes, (c) potential adaptations, and (d) future sustainability across the stages of the implementation lifecycle. METHODS: We used an iterative human-centered design process to develop the iPRISM webtool. RESULTS: We conducted user-testing with 28 potential individual and team-based users who were English and Spanish speaking from diverse settings in various stages of implementing different types of programs. Users provided input on all aspects of the webtool including its purpose, content, assessment items, visual feedback displays, navigation, and potential application. Participants generally expressed interest in using the webtool and high likelihood of recommending it to others. The iPRISM webtool guides English and Spanish-speaking users through the process of iteratively applying PRISM across the lifecycle of a program to facilitate systematic assessment and alignment with context. The webtool summarizes assessment responses in graphical and tabular displays and then guides users to develop feasible and impactful adaptations and corresponding action plans. Equity considerations are integrated throughout. CONCLUSIONS: The iPRISM webtool can intuitively guide individuals and teams from diverse settings through the process of using IS methods to iteratively assess and adapt different types of programs to align with the context across the implementation lifecycle. Future research and application will continue to develop and evaluate this IS resource.

A machine learning evaluation of patient characteristics associated with prescribing of guideline-directed medical therapy for heart failure.

Introduction/background: Patients with heart failure and reduced ejection fraction (HFrEF) are consistently underprescribed guideline-directed medications. Although many barriers to prescribing are known, identification of these barriers has relied on traditional a priori hypotheses or qualitative methods. Machine learning can overcome many limitations of traditional methods to capture complex relationships in data and lead to a more comprehensive understanding of the underpinnings driving underprescribing. Here, we used machine learning methods and routinely available electronic health record data to identify predictors of prescribing. Methods: We evaluated the predictive performance of machine learning algorithms to predict prescription of four types of medications for adults with HFrEF: angiotensin converting enzyme inhibitor/angiotensin receptor blocker (ACE/ARB), angiotensin receptor-neprilysin inhibitor (ARNI), evidence-based beta blocker (BB), or mineralocorticoid receptor antagonist (MRA). The models with the best predictive performance were used to identify the top 20 characteristics associated with prescribing each medication type. Shapley values were used to provide insight into the importance and direction of the predictor relationships with medication prescribing. Results: For 3,832 patients meeting the inclusion criteria, 70% were prescribed an ACE/ARB, 8% an ARNI, 75% a BB, and 40% an MRA. The best-predicting model for each medication type was a random forest (area under the curve: 0.788-0.821; Brier score: 0.063-0.185). Across all medications, top predictors of prescribing included prescription of other evidence-based medications and younger age. Unique to prescribing an ARNI, the top predictors included lack of diagnoses of chronic kidney disease, chronic obstructive pulmonary disease, or hypotension, as well as being in a relationship, nontobacco use, and alcohol use. Discussion/conclusions: We identified multiple predictors of prescribing for HFrEF medications that are being used to strategically design interventions to address barriers to prescribing and to inform further investigations. The machine learning approach used in this study to identify predictors of suboptimal prescribing can also be used by other health systems to identify and address locally relevant gaps and solutions to prescribing.

Clinician challenges to evidence-based prescribing for heart failure and reduced ejection fraction: A qualitative evaluation.

BACKGROUND: Reasons for suboptimal prescribing for heart failure with reduced ejection fraction (HFrEF) have been identified, but it is unclear if they remain relevant with recent advances in healthcare delivery and technologies. This study aimed to identify and understand current clinician-perceived challenges to prescribing guideline-directed HFrEF medications. METHODS: We conducted content analysis methodology, including interviews and member-checking focus groups with primary care and cardiology clinicians. Interview guides were informed by the Cabana Framework. RESULTS: We conducted interviews with 33 clinicians (13 cardiology specialists, 22 physicians) and member checking with 10 of these. We identified four levels of challenges from the clinician perspective. Clinician level challenges included misconceptions about guideline recommendations, clinician assumptions (e.g., drug cost or affordability), and clinical inertia. Patient-clinician level challenges included misalignment of priorities and insufficient communication. Clinician-clinician level challenges were primarily between generalists and specialists, including lack of role clarity, competing priorities of providing focused versus holistic care, and contrasting confidence regarding safety of newer drugs. Policy and system/organisation level challenges included insufficient access to timely/reliable patient data, and unintended care gaps for medications without financially incentivized metrics. CONCLUSION: This study presents current challenges faced by cardiology and primary care which can be used to strategically design interventions to improve guideline-directed care for HFrEF. The findings support the persistence of many challenges and also sheds light on new challenges. New challenges identified include conflicting perspectives between generalists and specialists, hesitancy to prescribe newer medications due to safety concerns, and unintended consequences related to value-based reimbursement metrics for select medications.

Comparative effectiveness of generic commercial versus locally customized clinical decision support tools to reduce prescription of nonsteroidal anti-inflammatory drugs for patients with heart failure.

OBJECTIVE: To compare the effectiveness of 2 clinical decision support (CDS) tools to avoid prescription of nonsteroidal anti-inflammatory drugs (NSAIDs) in patients with heart failure (HF): a "commercial" and a locally "customized" alert. METHODS: We conducted a retrospective cohort study of 2 CDS tools implemented within a large integrated health system. The commercial CDS tool was designed according to third-party drug content and EHR vendor specifications. The customized CDS tool underwent a user-centered design process informed by implementation science principles, with input from a cross disciplinary team. The customized CDS tool replaced the commercial CDS tool. Data were collected from the electronic health record via analytic reports and manual chart review. The primary outcome was effectiveness, defined as whether the clinician changed their behavior and did not prescribe an NSAID. RESULTS: A random sample of 366 alerts (183 per CDS tool) was evaluated that represented 355 unique patients. The commercial CDS tool was effective for 7 of 172 (4%) patients, while the customized CDS tool was effective for 81 of 183 (44%) patients. After adjusting for age, chronic kidney disease, ejection fraction, NYHA class, concurrent prescription of an opioid or acetaminophen, visit type (inpatient or outpatient), and clinician specialty, the customized alerts were at 24.3 times greater odds of effectiveness compared to the commercial alerts (OR: 24.3 CI: 10.20-58.06). CONCLUSION: Investing additional resources to customize a CDS tool resulted in a CDS tool that was more effective at reducing the total number of NSAID orders placed for patients with HF compared to a commercially available CDS tool.

Ontologizing health systems data at scale: making translational discovery a reality.

Common data models solve many challenges of standardizing electronic health record (EHR) data but are unable to semantically integrate all of the resources needed for deep phenotyping. Open Biological and Biomedical Ontology (OBO) Foundry ontologies provide computable representations of biological knowledge and enable the integration of heterogeneous data. However, mapping EHR data to OBO ontologies requires significant manual curation and domain expertise. We introduce OMOP2OBO, an algorithm for mapping Observational Medical Outcomes Partnership (OMOP) vocabularies to OBO ontologies. Using OMOP2OBO, we produced mappings for 92,367 conditions, 8611 drug ingredients, and 10,673 measurement results, which covered 68-99% of concepts used in clinical practice when examined across 24 hospitals. When used to phenotype rare disease patients, the mappings helped systematically identify undiagnosed patients who might benefit from genetic testing. By aligning OMOP vocabularies to OBO ontologies our algorithm presents new opportunities to advance EHR-based deep phenotyping.

Interpretable Machine Learning Prediction of Drug-Induced QT Prolongation: Electronic Health Record Analysis.

BACKGROUND: Drug-induced long-QT syndrome (diLQTS) is a major concern among patients who are hospitalized, for whom prediction models capable of identifying individualized risk could be useful to guide monitoring. We have previously demonstrated the feasibility of machine learning to predict the risk of diLQTS, in which deep learning models provided superior accuracy for risk prediction, although these models were limited by a lack of interpretability. OBJECTIVE: In this investigation, we sought to examine the potential trade-off between interpretability and predictive accuracy with the use of more complex models to identify patients at risk for diLQTS. We planned to compare a deep learning algorithm to predict diLQTS with a more interpretable algorithm based on cluster analysis that would allow medication- and subpopulation-specific evaluation of risk. METHODS: We examined the risk of diLQTS among 35,639 inpatients treated between 2003 and 2018 with at least 1 of 39 medications associated with risk of diLQTS and who had an electrocardiogram in the system performed within 24 hours of medication administration. Predictors included over 22,000 diagnoses and medications at the time of medication administration, with cases of diLQTS defined as a corrected QT interval over 500 milliseconds after treatment with a culprit medication. The interpretable model was developed using cluster analysis (K=4 clusters), and risk was assessed for specific medications and classes of medications. The deep learning model was created using all predictors within a 6-layer neural network, based on previously identified hyperparameters. RESULTS: Among the medications, we found that class III antiarrhythmic medications were associated with increased risk across all clusters, and that in patients who are noncritically ill without cardiovascular disease, propofol was associated with increased risk, whereas ondansetron was associated with decreased risk. Compared with deep learning, the interpretable approach was less accurate (area under the receiver operating characteristic curve: 0.65 vs 0.78), with comparable calibration. CONCLUSIONS: In summary, we found that an interpretable modeling approach was less accurate, but more clinically applicable, than deep learning for the prediction of diLQTS. Future investigations should consider this trade-off in the development of methods for clinical prediction.

Research and Scholarly Methods: Implementation Science Studies.

Traditional research focuses on efficacy or effectiveness of interventions but lacks evaluation of strategies needed for equitable uptake, scalable implementation, and sustainable evidence-based practice transformation. The purpose of this introductory review is to describe key implementation science (IS) concepts as they apply to medication management and pharmacy practice, and to provide guidance on literature review with an IS lens. There are five key ingredients of IS, including: (1) evidence-based intervention; (2) implementation strategies; (3) IS theory, model, or framework; (4) IS outcomes and measures; and (5) stakeholder engagement, which is key to a successful implementation. These key ingredients apply across the three stages of IS research: (1) pre-implementation; (2) implementation; and (3) sustainment. A case example using a combination of IS models, PRISM (Practical, Robust Implementation and Sustainability model) and RE-AIM (Reach, Effectiveness, Adoption, Implementation, Maintenance), is included to describe how an IS study is designed and conducted. This case is a cluster randomized trial comparing two clinical decision support tools to improve guideline-concordant prescribing for patients with heart failure and reduced ejection fraction. The review also includes information on the Standards for Reporting Implementation Studies (StaRI), which is used for literature review and reporting of IS studies,as well as IS-related learning resources.

How Dissemination and Implementation Science Can Contribute to the Advancement of Learning Health Systems.

Many health systems are working to become learning health systems (LHSs), which aim to improve the value of health care by rapidly, continuously generating evidence to apply to practice. However, challenges remain to advance toward the aspirational goal of becoming a fully mature LHS. While some important challenges have been well described (i.e., building system-level supporting infrastructure and the accessibility of inclusive, integrated, and actionable data), other key challenges are underrecognized, including balancing evaluation rapidity with rigor, applying principles of health equity and classic ethics, focusing on external validity and reproducibility (generalizability), and designing for sustainability. Many LHSs focus on continuous learning cycles, but with limited consideration of issues related to the rapidity of these learning cycles, as well as the sustainability or generalizability of solutions. Some types of data have been consistently underrepresented, including patient-reported outcomes and preferences, social determinants, and behavioral and environmental data, the absence of which can exacerbate health disparities. A promising approach to addressing many challenges that LHSs face may be found in dissemination and implementation (D&I) science. With an emphasis on multilevel dynamic contextual factors, representation of implementation partner engagement, pragmatic research, sustainability, and generalizability, D&I science methods can assist in overcoming many of the challenges facing LHSs. In this article, the authors describe the current state of LHSs and challenges to becoming a mature LHS, propose solutions to current challenges, focusing on the contributions of D&I science with other methods, and propose key components and characteristics of a mature LHS model that others can use to plan and develop their LHSs.

Pragmatic considerations and approaches for measuring staff time as an implementation cost in health systems and clinics: key issues and applied examples.

BACKGROUND: As the field of implementation science wrestles with the need for system decision-makers to anticipate the budget impact of implementing new programs, there has been a push to report implementation costs more transparently. For this purpose, the method of time-driven activity-based costing (TDABC) has been heralded as a pragmatic advance. However, a recent TDABC review found that conventional methods for estimating staff time remain resource-intensive and called for simpler alternatives. Our objective was to conceptually compare conventional and emerging TDABC approaches to measuring staff time. METHODS: Our environmental scan of TDABC methods identified several categories of approaches for staff time estimation; across these categories, staff time was converted to cost as a pro-rated fraction of salary/benefits. Conventional approaches used a process map to identify each step of program delivery and estimated the staff time used at each step in one of 3 ways: (a) uniform estimates of time needed for commonly occurring tasks (self-report), (b) retrospective "time diary" (self-report), or (c) periodic direct observation. In contrast, novel semi-automated electronic health record (EHR) approaches "nudge" staff to self-report time for specific process map step(s)-serving as a contemporaneous time diary. Also, novel EHR-based automated approaches include timestamps to track specific steps in a process map. We compared the utility of these TDABC approach categories according to the 5 R's model that measures domains of interest to system decision-makers: relevance, rapidity, rigor, resources, and replicability, and include two illustrative case examples. RESULTS: The 3 conventional TDABC staff time estimation methods are highly relevant to settings but have limited rapidity, variable rigor, are rather resource-intensive, and have varying replicability. In contrast to conventional TDABC methods, the semi-automated and automated EHR-based approaches have high rapidity, similar rigor, similar replicability, and are less resource-intensive, but have varying relevance to settings. CONCLUSIONS: This synthesis and evaluation of conventional and emerging methods for staff time estimation by TDABC provides the field of implementation science with options beyond the current approaches. The field remains pressed to innovatively and pragmatically measure costs of program delivery that rate favorably across all of the 5 R's domains.

An evaluation of clinical decision support tools for Patient Health Questionnaire-9 administration.

INTRODUCTION: Many health care institutions are working to improve depression screening and management with the use of the Patient Health Questionnaire 9 (PHQ-9). Clinical decision support (CDS) within the EHR is one strategy, but little is known about effective approaches to design or implement such CDS. The purpose of this study is to compare implementation outcomes of two versions of a CDS tool to improve PHQ-9 administration for patients with depression. METHODS: This was a retrospective, observational study comparing two versions of a CDS. Version 1 interrupted clinician workflow, and version 2 did not interrupt workflow. Outcomes of interest included reach, adoption, and effectiveness. PHQ-9 administration was determined by chart review. Chi-square tests were used to evaluate associations between PHQ-9 administration with versions 1 and 2. RESULTS: Version 1 resulted in PHQ-9 administration 77 times (15.3% of 504 unique encounters) compared with 49 times (9.8% of 502 unique encounters) with version 2 (P = .011). DISCUSSION: An interruptive CDS tool may be more effective at increasing PHQ-9 administration, but a noninterruptive CDS tool may be preferred to minimize alert fatigue despite a decrease in effectiveness.

Assessing Prescriber Behavior with a Clinical Decision Support Tool to Prevent Drug-Induced Long QT Syndrome.

OBJECTIVE: Clinical decision support (CDS) alerts built into the electronic health record (EHR) have the potential to reduce the risk of drug-induced long QT syndrome (diLQTS) in susceptible patients. However, the degree to which providers incorporate this information into prescription behavior and the impact on patient outcomes is often unknown. METHODS: We examined provider response data over a period from October 8, 2016 until November 8, 2018 for a CDS alert deployed within the EHR from a 13-hospital integrated health care system that fires when a patient with a QTc ≥ 500 ms within the past 14 days is prescribed a known QT-prolonging medication. We used multivariate generalized estimating equations to analyze the impact of therapeutic alternatives, relative risk of diLQTS for specific medications, and patient characteristics on provider response to the CDS and overall patient mortality. RESULTS: The CDS alert fired 15,002 times for 7,510 patients for which the most common response (51.0%) was to override the alert and order the culprit medication. In multivariate models, we found that patient age, relative risk of diLQTS, and presence of alternative agents were significant predictors of adherence to the CDS alerts and that nonadherence itself was a predictor of mortality. Risk of diLQTS and presence of an alternative agent are major factors in provider adherence to a CDS to prevent diLQTS; however, provider nonadherence was associated with a decreased risk of mortality. CONCLUSION: Surrogate endpoints, such as provider adherence, can be useful measures of CDS value but attention to hard outcomes, such as mortality, is likely needed.

Applying Clinical Decision Support Design Best Practices With the Practical Robust Implementation and Sustainability Model Versus Reliance on Commercially Available Clinical Decision Support Tools: Randomized Controlled Trial.

BACKGROUND: Limited consideration of clinical decision support (CDS) design best practices, such as a user-centered design, is often cited as a key barrier to CDS adoption and effectiveness. The application of CDS best practices is resource intensive; thus, institutions often rely on commercially available CDS tools that are created to meet the generalized needs of many institutions and are not user centered. Beyond resource availability, insufficient guidance on how to address key aspects of implementation, such as contextual factors, may also limit the application of CDS best practices. An implementation science (IS) framework could provide needed guidance and increase the reproducibility of CDS implementations. OBJECTIVE: This study aims to compare the effectiveness of an enhanced CDS tool informed by CDS best practices and an IS framework with a generic, commercially available CDS tool. METHODS: We conducted an explanatory sequential mixed methods study. An IS-enhanced and commercial CDS alert were compared in a cluster randomized trial across 28 primary care clinics. Both alerts aimed to improve beta-blocker prescribing for heart failure. The enhanced alert was informed by CDS best practices and the Practical, Robust, Implementation, and Sustainability Model (PRISM) IS framework, whereas the commercial alert followed vendor-supplied specifications. Following PRISM, the enhanced alert was informed by iterative, multilevel stakeholder input and the dynamic interactions of the internal and external environment. Outcomes aligned with PRISM's evaluation measures, including patient reach, clinician adoption, and changes in prescribing behavior. Clinicians exposed to each alert were interviewed to identify design features that might influence adoption. The interviews were analyzed using a thematic approach. RESULTS: Between March 15 and August 23, 2019, the enhanced alert fired for 61 patients (106 alerts, 87 clinicians) and the commercial alert fired for 26 patients (59 alerts, 31 clinicians). The adoption and effectiveness of the enhanced alert were significantly higher than those of the commercial alert (62% vs 29% alerts adopted, P<.001; 14% vs 0% changed prescribing, P=.006). Of the 21 clinicians interviewed, most stated that they preferred the enhanced alert. CONCLUSIONS: The results of this study suggest that applying CDS best practices with an IS framework to create CDS tools improves implementation success compared with a commercially available tool. TRIAL REGISTRATION: ClinicalTrials.gov NCT04028557; http://clinicaltrials.gov/ct2/show/NCT04028557.

Patient Outreaches for Clinical Pharmacy Services: A Population Health Management Program Assessment.

BACKGROUND: Pharmacists in ambulatory care can utilize population health approaches to identify patients needing disease management and improve outcomes. However, population health is only effective when identified patients are successfully outreached and show to appointments. OBJECTIVE: Describe a population health approach utilized by pharmacists in primary care, report outcomes of outreach attempts and scheduled appointments, and determine whether patient and referral characteristics predict no-show appointments. METHODS: Retrospective cohort study of patients referred for pharmacist management of hypertension or chronic pain through population health between 2013-2016. Outreach attempt and appointments outcomes were collected. Patient and referral characteristics were analyzed to determine whether predictive of no-show appointments using logistic regression. RESULTS: Of 450 outreach attempts, 250 (56%) patients were not reached, 164 (36%) scheduled appointments, and 36 (8%) were reached but declined an appointment. Of 164 patients with appointments, 71 (43%) no-showed. Patients with higher systolic blood pressure were more likely to no-show (OR: 1.02, 95% CI: 1.00-1.04). Other characteristics were not predictive of no-show appointments. CONCLUSION: Successful outreach and showed appointments are essential components of successful population health programs. Using multiple outreach modalities and further identifying factors predictive of no-show appointments to refine the current approach may lead to increased efficiency.

An Electronically Delivered Patient-Activation Tool for Intensification of Medications for Chronic Heart Failure With Reduced Ejection Fraction: The EPIC-HF Trial.

BACKGROUND: Major gaps exist in the routine initiation and dose up-titration of guideline-directed medical therapies (GDMT) for patients with heart failure with reduced ejection fraction. Without novel approaches to improve prescribing, the cumulative benefits of heart failure with reduced ejection fraction treatment will be largely unrealized. Direct-to-consumer marketing and shared decision making reflect a culture where patients are increasingly involved in treatment choices, creating opportunities for prescribing interventions that engage patients. METHODS: The EPIC-HF (Electronically Delivered, Patient-Activation Tool for Intensification of Medications for Chronic Heart Failure with Reduced Ejection Fraction) trial randomized patients with heart failure with reduced ejection fraction from a diverse health system to usual care versus patient activation tools-a 3-minute video and 1-page checklist-delivered electronically 1 week before, 3 days before, and 24 hours before a cardiology clinic visit. The tools encouraged patients to work collaboratively with their clinicians to "make one positive change" in heart failure with reduced ejection fraction prescribing. The primary endpoint was the percentage of patients with GDMT medication initiations and dose intensifications from immediately preceding the cardiology clinic visit to 30 days after, compared with usual care during the same period. RESULTS: EPIC-HF enrolled 306 patients, 290 of whom attended a clinic visit during the study period: 145 were sent the patient activation tools and 145 were controls. The median age of patients was 65 years; 29% were female, 11% were Black, 7% were Hispanic, and the median ejection fraction was 32%. Preclinic data revealed significant GDMT opportunities, with no patients on target doses of ß-blocker, sacubitril/valsartan, and mineralocorticoid receptor antagonists. From immediately preceding the cardiology clinic visit to 30 days after, 49.0% in the intervention and 29.7% in the control experienced an initiation or intensification of their GDMT (P=0.001). The majority of these changes were made at the clinician encounter itself and involved dose uptitrations. There were no deaths and no significant differences in hospitalization or emergency department visits at 30 days between groups. CONCLUSIONS: A patient activation tool delivered electronically before a cardiology clinic visit improved clinician intensification of GDMT. Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT03334188.

Twice-daily versus once-daily lisinopril and losartan for hypertension: Real-world effectiveness and safety.

BACKGROUND: Lisinopril and losartan manufacturer labels recommend twice-daily dosing (BID) if once-daily (QDay) is insufficient to lower blood pressure (BP). METHODS AND RESULTS: Retrospective cohort study of patients taking QDay lisinopril and losartan who experienced a dose-doubling (index date). A text-processing tool categorized BID and QDay groups at the index date based on administration instructions. We excluded: pregnant/hospice, regimens other than BID/QDay, and without BP measurements -6 months/+12 months of the index date. The most proximal BP measurements -6 months and +2 weeks to 12 months of the index date were used to evaluate BP differences. Propensity scores were generated, and differences in BP and adverse events (angioedema, acute kidney injury, hyperkalemia) between BID/QDay groups were analyzed within dosing cohorts using inverse propensity of treatment-weighted regression models. Of 11,210 and 6,051 patients who met all criteria for lisinopril and losartan, 784 (7.0%) and 453 (7.5%) were taking BID, respectively. BID patients were older and had higher comorbidity and medication burdens. There were no differences in systolic/diastolic BP between BID and QDay, with absolute differences in mean systolic BP ranging from -1.8 to 0.7 mmHg and diastolic BP ranging from -1.1 to 0.1 mmHg (all 95% confidence intervals [CI] cross 0). Lisinopril 10mg BID was associated with an increased odds of angioedema compared to lisinopril 20mg QDay (odds ratio 2.27, 95%CI 1.13-4.58). CONCLUSIONS: Adjusted models do not support improved effectiveness or safety of BID lisinopril and losartan.