Evidence-based Clinical Decision Support Tools Research Articles

Implementation and Evaluation of Educational Workshops to Increase Primary Care Provider and Medical Student Comfort in Psychiatric Care.

Mental health treatment is often initiated in primary care settings, but many primary care providers (PCPs), residents, and medical students report discomfort in managing psychiatric conditions. This study evaluated the effect of an educational workshop that featured an evidence-based psychopharmacology clinical decision support tool (CDST) on trainee confidence and willingness to treat psychiatric conditions. Participants completed pre- and post-workshop surveys. Nine months after the workshop, a subset of trainees participated in a focus group. Of the participants, 62.5% of the obstetrics-gynecology (OB-GYN) resident physicians (10/16) and 100% of the medical students (18/18) completed both pre- and post-surveys. Following the workshop, OB-GYN resident physicians reported significantly improved confidence in treating psychiatric disorders (p < 0.001), sense of having psychiatric support tools (p < 0.001), and knowledge of treating psychiatric disorders (p = 0.021). Medical students reported significantly improved confidence in treating psychiatric disorders (p < 0.001), willingness to devise treatment plans for psychiatric disorders (p = 0.024), sense of having psychiatric support tools (p < 0.001), knowledge of treating psychiatric disorders (p < 0.001), and comfort in presenting a psychiatric treatment plan to an attending (p = 0.003). Most focus group participants (93.75%; 15/16) reported that they continued to use the CDST, and it increased their confidence in formulating psychiatric treatment plans. These findings suggest that educational workshops that introduce high-quality psychopharmacology CDSTs may be an effective method for improving provider comfort in treating psychiatric disorders.

Impact of Deltoid Computer Tomography Image Data on the Accuracy of Machine Learning Predictions of Clinical Outcomes after Anatomic and Reverse Total Shoulder Arthroplasty.

Background: Despite the importance of the deltoid to shoulder biomechanics, very few studies have quantified the three-dimensional shape, size, or quality of the deltoid muscle, and no studies have correlated these measurements to clinical outcomes after anatomic (aTSA) and/or reverse (rTSA) total shoulder arthroplasty in any statistically/scientifically relevant manner. Methods: Preoperative computer tomography (CT) images from 1057 patients (585 female, 469 male; 799 primary rTSA and 258 primary aTSA) of a single platform shoulder arthroplasty prosthesis (Equinoxe; Exactech, Inc., Gainesville, FL) were analyzed in this study. A machine learning (ML) framework was used to segment the deltoid muscle for 1057 patients and quantify 15 different muscle characteristics, including volumetric (size, shape, etc.) and intensity-based Hounsfield (HU) measurements. These deltoid measurements were correlated to postoperative clinical outcomes and utilized as inputs to train/test ML algorithms used to predict postoperative outcomes at multiple postoperative timepoints (1 year, 2-3 years, and 3-5 years) for aTSA and rTSA. Results: Numerous deltoid muscle measurements were demonstrated to significantly vary with age, gender, prosthesis type, and CT image kernel; notably, normalized deltoid volume and deltoid fatty infiltration were demonstrated to be relevant to preoperative and postoperative clinical outcomes after aTSA and rTSA. Incorporating deltoid image data into the ML models improved clinical outcome prediction accuracy relative to ML algorithms without image data, particularly for the prediction of abduction and forward elevation after aTSA and rTSA. Analyzing ML feature importance facilitated rank-ordering of the deltoid image measurements relevant to aTSA and rTSA clinical outcomes. Specifically, we identified that deltoid shape flatness, normalized deltoid volume, deltoid voxel skewness, and deltoid shape sphericity were the most predictive image-based features used to predict clinical outcomes after aTSA and rTSA. Many of these deltoid measurements were found to be more predictive of aTSA and rTSA postoperative outcomes than patient demographic data, comorbidity data, and diagnosis data. Conclusions: While future work is required to further refine the ML models, which include additional shoulder muscles, like the rotator cuff, our results show promise that the developed ML framework can be used to evolve traditional CT-based preoperative planning software into an evidence-based ML clinical decision support tool.

American College of Radiology (ACR) Appropriateness Criteria and EURO-2000 Guidelines Offer Limited Guidance for MRI Imaging of Pediatric Patients

This study aims to evaluate the clinical scenarios addressed by the EURO-2000 guidelines and the ACR appropriateness criteria for referring children to MRI and assessing the referring physician compliance with both guidelines. In January 2022, clinical scenarios reported in the last 1000 consecutive MRI requests for children (0-16 years) in one university children's hospital and two general university hospitals in Belgium, Europe, were retrospectively matched to the EURO-2000 guidelines and ACR appropriateness criteria. The number of clinical scenarios addressed and the justification for MRI referral were independently assessed for both guidelines. Pooled data from the three centers were evaluated and then analyzed by center, body area and prescriber using McNemar's test for paired proportions and χ2-tests unpaired proportions. After excluding incomplete or missing MRI requests, 2932 of 3000 requests were included in the analysis. Overall, out of 2932 clinical scenarios, 1229 (37.99%) were addressed by EURO-2000 and 1081 (36.37%) were addressed by the ACR appropriateness criteria (McNemar test, p=0.12). The proportions of clinical scenarios covered by the two guidelines were statistically similar when comparing centers, but varied across body regions (p < 0.001) and referring physician specialty (p between 0.75 and 0.001). EURO-2000 guidelines provided better coverage for head and spine (p < 0.05), while the ACR appropriateness criteria provided broader coverage for abdomen, pelvis, and musculoskeletal system (p < 0.0001). For addressed clinical scenarios, prescriber compliance for both guidelines was excellent with > 94% of justified MRI examinations in all the centers. Both the EURO-2000 guidelines and the ACR appropriateness criteria did not address two-thirds of clinical scenarios in children. Head and neck, chest and abdominal-pelvic examinations are the anatomic regions which should receive a specific attention for the future implementation of evidence-based clinical decision support tools for all referring specialists.

Ordering of computed tomography scans for head and cervical spine: a qualitative study exploring influences on doctors’ decision-making

BackgroundOrdering of computed tomography (CT) scans needs to consideration of diagnostic utility as well as resource utilisation and radiation exposure. Several factors influence ordering decisions, including evidence-based clinical decision support tools to rule out serious disease. The aim of this qualitative study was to explore factors influencing Emergency Department (ED) doctors’ decisions to order CT of the head or cervical spine.MethodsIn-depth semi-structured interviews were conducted with purposively selected ED doctors from two affiliated public hospitals. An interview tool with 10 questions, including three hypothetical scenarios, was developed and validated to guide discussions. Interviews were audio recorded, transcribed verbatim, and compared with field notes. Transcribed data were imported into NVivo Release 1.3 to facilitate coding and thematic analysis.ResultsIn total 21 doctors participated in semi-structured interviews between February and December 2020; mean interview duration was 35 min. Data saturation was reached. Participants ranged from first-year interns to experienced consultants. Five overarching emerging themes were: 1) health system and local context, 2) work structure and support, 3) professional practices and responsibility, 4) reliable patient information, and 5) holistic patient-centred care. Mapping of themes and sub-themes against a behaviour change model provided a basis for future interventions.ConclusionsCT ordering is complex and multifaceted. Multiple factors are considered by ED doctors during decisions to order CT scans for head or c-spine injuries. Increased education on the use of clinical decision support tools and an overall strategy to improve awareness of low-value care is needed. Strategies to reduce low-yield CT ordering will need to be sustainable, sophisticated and supportive to achieve lasting change.

Developing and Demonstrating the Viability and Availability of the Multilevel Implementation Strategy for Syncope Optimal Care Through Engagement (MISSION) Syncope App: Evidence-Based Clinical Decision Support Tool.

BackgroundSyncope evaluation and management is associated with testing overuse and unnecessary hospitalizations. The 2017 American College of Cardiology/American Heart Association (ACC/AHA) Syncope Guideline aims to standardize clinical practice and reduce unnecessary services. The use of clinical decision support (CDS) tools offers the potential to successfully implement evidence-based clinical guidelines. However, CDS tools that provide an evidence-based differential diagnosis (DDx) of syncope at the point of care are currently lacking.ObjectiveWith input from diverse health systems, we developed and demonstrated the viability of a mobile app, the Multilevel Implementation Strategy for Syncope optImal care thrOugh eNgagement (MISSION) Syncope, as a CDS tool for syncope diagnosis and prognosis.MethodsDevelopment of the app had three main goals: (1) reliable generation of an accurate DDx, (2) incorporation of an evidence-based clinical risk tool for prognosis, and (3) user-based design and technical development. To generate a DDx that incorporated assessment recommendations, we reviewed guidelines and the literature to determine clinical assessment questions (variables) and likelihood ratios (LHRs) for each variable in predicting etiology. The creation and validation of the app diagnosis occurred through an iterative clinician review and application to actual clinical cases. The review of available risk score calculators focused on identifying an easily applied and valid evidence-based clinical risk stratification tool. The review and decision-making factors included characteristics of the original study, clinical variables, and validation studies. App design and development relied on user-centered design principles. We used observations of the emergency department workflow, storyboard demonstration, multiple mock review sessions, and beta-testing to optimize functionality and usability.ResultsThe MISSION Syncope app is consistent with guideline recommendations on evidence-based practice (EBP), and its user interface (UI) reflects steps in a real-world patient evaluation: assessment, DDx, risk stratification, and recommendations. The app provides flexible clinical decision making, while emphasizing a care continuum; it generates recommendations for diagnosis and prognosis based on user input. The DDx in the app is deemed a pragmatic model that more closely aligns with real-world clinical practice and was validated using actual clinical cases. The beta-testing of the app demonstrated well-accepted functionality and usability of this syncope CDS tool.ConclusionsThe MISSION Syncope app development integrated the current literature and clinical expertise to provide an evidence-based DDx, a prognosis using a validated scoring system, and recommendations based on clinical guidelines. This app demonstrates the importance of using research literature in the development of a CDS tool and applying clinical experience to fill the gaps in available research. It is essential for a successful app to be deliberate in pursuing a practical clinical model instead of striving for a perfect mathematical model, given available published evidence. This hybrid methodology can be applied to similar CDS tool development.

Search Behavior Regarding Cancer Susceptibility Genes Using a Clinical Decision Support Tool for Gene-Specific Penetrance: Content Analysis.

BackgroundGenetic testing for germline cancer susceptibility genes is widely available. The Ask2Me.org (All Syndromes Known to Man Evaluator) tool is a clinical decision support tool that provides evidence-based risk predictions for individuals with pathogenic variants in cancer susceptibility genes.ObjectiveThe aim of this study was to understand the search behavior of the Ask2Me.org tool users, identify the patterns of queries entered, and discuss how to further improve the tool.MethodsWe analyzed the Ask2Me.org user-generated queries collected between December 12, 2018, and October 8, 2019. The gene frequencies of the user-generated queries were compared with previously published panel testing data to assess the correspondence between usage and prevalence of pathogenic variants. The frequencies of prior cancer in the user-generated queries were compared with the most recent US population–based cancer incidence.ResultsA total of 10,085 search queries were evaluated. The average age submitted in the queries was 48.8 (SD 16.5) years, and 84.1% (8478/10,085) of the submitted queries were for females. BRCA2 (1671/10,085, 16.6%), BRCA1 (1627/10,085, 16.1%), CHEK2 (994/10,085, 9.9%), ATM (662/10,085, 6.6%), and APC (492/10,085, 4.9%) were the top 5 genes searched by users. There was a strong linear correlation between genes queried by users and the frequency of pathogenic variants reported in published panel testing data (r=0.95, r2=0.90, P<.001). Over half of the queries (5343/10,085, 53.0%) included a prior personal history of cancer. The frequencies of prior cancers in the queries on females were strongly correlated with US cancer incidences (r=0.97, r2=0.95, P<.001), while the same correlation was weaker among the queries on males (r=0.69, r2=0.47, P=.02).ConclusionsThe patients entered in the Ask2Me.org tool are a representative cohort of patients with pathogenic variants in cancer susceptibility genes in the United States. While a majority of the queries were on breast cancer susceptibility genes, users also queried susceptibility genes with lower prevalence, which may represent a transformation from single gene testing to multigene panel testing. Owing to these changing tides, more efforts are needed to improve evidence-based clinical decision support tools to better aid clinicians and their practice.

Implementing an Electronic Clinical Decision Support Tool Into Routine Care: A Qualitative Study of Stakeholders' Perceptions of a Post-Mastectomy Breast Reconstruction Tool.

Objective. To explore barriers and facilitators to implementing an evidence-based clinical decision support (CDS) tool (BREASTChoice) about post-mastectomy breast reconstruction into routine care. Materials and Methods. A stakeholder advisory group of cancer survivors, clinicians who discuss and/or perform breast reconstruction in women with cancer, and informatics professionals helped design and review the interview guide. Based on the Consolidated Framework for Implementation Research (CFIR), we conducted qualitative semistructured interviews with key stakeholders (patients, clinicians, informatics professionals) to explore intervention, setting characteristics, and process-level variables that can impact implementation. Interviews were transcribed, coded, and analyzed based on the CFIR framework using both inductive and deductive methods. Results. Fifty-seven potential participants were contacted; 49 (85.9%) were eligible, and 35 (71.4%) were enrolled, continuing until thematic saturation was reached. Participants consisted of 13 patients, 13 clinicians, and 9 informatics professionals. Stakeholders thought that BREASTChoice was useful and provided patients with an evidence-based source of information about post-mastectomy breast reconstruction, including their personalized risks. They felt that BREASTChoice could support shared decision making, improve workflow, and possibly save consultation time, but were uncertain about the best time to deliver BREASTChoice to patients. Some worried about cost, data availability, and security of integrating the tool into an electronic health record. Most acknowledged the importance of showing clinical utility to gain institutional buy-in and encourage routine adoption. Discussion and Conclusion. Stakeholders felt that BREASTChoice could support shared decision making, improve workflow, and reduce consultation time. Addressing key questions such as cost, data integration, and timing of delivering BREASTChoice could build institutional buy-in for CDS implementation. Results can guide future CDS implementation studies.

Risk prediction models to guide antibiotic prescribing: a study on adult patients with uncomplicated upper respiratory tract infections in an emergency department

BackgroundAppropriate antibiotic prescribing is key to combating antimicrobial resistance. Upper respiratory tract infections (URTIs) are common reasons for emergency department (ED) visits and antibiotic use. Differentiating between bacterial and viral infections is not straightforward. We aim to provide an evidence-based clinical decision support tool for antibiotic prescribing using prediction models developed from local data.MethodsSeven hundred-fifteen patients with uncomplicated URTI were recruited and analysed from Singapore’s busiest ED, Tan Tock Seng Hospital, from June 2016 to November 2018. Confirmatory tests were performed using the multiplex polymerase chain reaction (PCR) test for respiratory viruses and point-of-care test for C-reactive protein. Demographic, clinical and laboratory data were extracted from the hospital electronic medical records. Seventy percent of the data was used for training and the remaining 30% was used for validation. Decision trees, LASSO and logistic regression models were built to predict when antibiotics were not needed.ResultsThe median age of the cohort was 36 years old, with 61.2% being male. Temperature and pulse rate were significant factors in all 3 models. The area under the receiver operating curve (AUC) on the validation set for the models were similar. (LASSO: 0.70 [95% CI: 0.62–0.77], logistic regression: 0.72 [95% CI: 0.65–0.79], decision tree: 0.67 [95% CI: 0.59–0.74]). Combining the results from all models, 58.3% of study participants would not need antibiotics.ConclusionThe models can be easily deployed as a decision support tool to guide antibiotic prescribing in busy EDs.

Engaging stakeholders in the adaptation of the Connect for Health pediatric weight management program for national implementation

BackgroundConnect for Health is an evidence-based weight management program with clinical- and family-facing components for delivery in pediatric primary care for families of children ages 2 to 12 years. We used the Consolidated Framework for Implementation Research (CFIR) to guide formative work prior to national implementation. The purpose of this study was to describe the process and results of stakeholder engagement and program adaptation.MethodsWe used mixed qualitative and quantitative methods to iteratively adapt and optimize the program by assessing needs and perspectives of clinicians and parents, as well as contextual barriers, facilitators, and organizational readiness for the uptake of the proposed program tools and implementation strategies. We conducted interviews with primary care clinicians from four health care organizations in Boston, MA; Denver, CO; and Greenville, SC, and used principles of immersion-crystallization for qualitative analyses. We also conducted surveys of parents of children with a body mass index ≥ 85th percentile.ResultsWe reached thematic saturation after 52 clinician interviews. Emergent themes representing the CFIR domains of intervention characteristics, outer and inner setting, and process included (1) importance of evidence-based clinical decision support tools that integrate into the workflow and do not extend visit time, (2) developing resources that respond to family’s needs, (3) using multimodal delivery options for family resources, (4) addressing childhood obesity while balancing competing demands, (5) emphasizing patient care rather than documentation and establishing sustainability plans, and (6) offering multiple training methods that incorporate performance feedback. Of the parents surveyed (n = 400), approximately 50% were Spanish-speaking and over 75% reported an annual income < $50,000. Parents affirmed the importance of addressing weight management during well-child visits, being provided with referrals and resources, and offering multiple methods for resource delivery. Decisions about program modifications were made at the program and healthcare-system level and based on stakeholder engagement findings. Modifications included cultural, geographic, and target audience adaptations, as well as varied resource delivery options.ConclusionsTo ensure the fit between the Connect for Health program and national implementation settings, adaptations were systematically made through engagement of clinician and parent stakeholders to support adoption, sustainability, and health outcomes.Trial registrationNCT04042493

CYP2D6 Genotype-guided Metoprolol Therapy in Cardiac Surgery Patients: Rationale and Design of the Pharmacogenetic-guided Metoprolol Management for Postoperative Atrial Fibrillation in Cardiac Surgery (PREEMPTIVE) Pilot Study

The Preemptive Pharmacogenetic-guided Metoprolol Management for Atrial Fibrillation in Cardiac Surgery (PREEMPTIVE) pilot trial aims to use existing institutional resources to develop a process for integrating CYP2D6 pharmacogenetic test results into the patient electronic health record, to develop an evidence-based clinical decision support tool to facilitate CYP2D6 genotype-guided metoprolol administration in the cardiac surgery setting, and to determine the impact of implementing this CYP2D6 genotype-guided integrated approach on the incidence of postoperative atrial fibrillation (AF), provider, and cost outcomes. One-arm Bayesian adaptive design clinical trial. Single center, university hospital. The authors will screen (including CYP2D6 genotype) up to 600 (264 ± 144 expected under the adaptive design) cardiac surgery patients, and enroll up to 200 (88 ± 48 expected) poor, intermediate, and ultrarapid CYP2D6 metabolizers over a period of 2 years at a tertiary academic center. All consented and enrolled patients will receive the intervention of CYP2D6 genotype-guided metoprolol management based on CYP2D6 phenotype classified as a poor, intermediate, extensive (normal), or ultrarapid metabolizer. The primary outcome will be the incidence of postoperative AF. Secondary outcomes relating to rates of CYP2D6 genotype-guided prescription changes, costs, lengths of stay, and implementation metrics also will be investigated. The PREEMPTIVE pilot study is the first perioperative pilot trial to provide essential information for the design of a future, large-scale trial comparing CYP2D6 genotype-guided metoprolol management with a nontailored strategy in terms of managing AF. In addition, secondary outcomes regarding implementation, clinical benefit, safety, and cost-effectiveness in patients undergoing cardiac surgery will be examined.

Randomized Clinical Trial of a Clinical Decision Support Tool for Improving the Appropriateness Scores for Ordering Imaging Studies in Primary and Specialty Care Ambulatory Clinics.

OBJECTIVE. The objective of our study was to evaluate whether the use of a clinical decision support (CDS) tool improved the appropriateness scores of orders for advanced imaging in clinical practice. MATERIALS AND METHODS. We used a stepped-wedge, cluster randomized clinical trial to evaluate the effectiveness of a CDS tool in an integrated health care system. Clinicians entered structured indications for each CT and MRI order, and the indications were electronically scored against appropriateness criteria to assign an appropriateness score. We compared the proportion of orders with adjusted appropriateness scores of 7 or greater (on a 1-9 scale) before and after activation of best practice alerts (BPAs) triggered for orders with low or marginal appropriateness scores. Secondary outcomes included the rate per month of orders for advanced imaging and the proportion of orders for which the radiology department requested changes. RESULTS. Between October 2015 and February 2016, 941 clinicians ordered 22,279 CT or MRI studies that met eligibility criteria. Before activation of the BPA, the mean proportion of appropriate orders (adjusted for time and clinic effect) was 77.0% (95% CI, 75.5-78.4%), which increased to 80.1% (95% CI, 78.7-81.5%) after activation (p = 0.001). There was no significant change in the rate of orders per month for advanced imaging. The proportion of order changes requested by the radiology department decreased from 5.7% (95% CI, 5.6-5.9%) before CDS implementation to 5.3% (95% CI, 5.1-5.5%) after CDS implementation (p < 0.001). CONCLUSION. Using an evidence-based CDS tool in clinical practice was associated with a modest but significant improvement in the appropriateness scores of advanced imaging orders.

MP38: Barriers and facilitators to physician use of computerized clinical decision support for mild traumatic brain injury and suspected pulmonary embolism

Introduction: As utilization of CT imaging has risen dramatically, evidence-based decision rules and clinical decision support (CDS) tools have been developed to avoid unnecessary CT use in low risk patients. However, their ability to change physician practice has been limited to date, with a number of barriers cited. The purpose of this study was to identify the barriers and facilitators to CDS adoption following a local CDS implementation. Methods: All emergency physicians at 4 urban EDs and 1 urgent care center were randomized to voluntary evidence-based CT imaging CDS for patients with either mild traumatic brain injury (MTBI) or suspected pulmonary embolism (PE). CDS was integrated into the computerized physician order entry (CPOE) software and triggered whenever a CT scan for an eligible patient was ordered. Physicians in both the MTBI and PE arms were ranked according to their CDS use, and a stratified sampling strategy was used to randomly select 5 physicians from each of the low, medium and high CDS use tertiles in each study arm. Each physician was invited to participate in a 30-minute semi-structured interview to assess the barriers and facilitators to CDS use. Physician responses were reported using a thematic analysis. Results: A total of 202 emergency physicians were randomized to receive CDS for either MTBI or PE, triggering CDS 4561 times, and interacting with the CDS software 1936 times (42.4%). Variation in CDS use ranged from 0% to 88.9% of eligible encounters by physician. Fourteen physicians have participated in interviews to date, and data collection is ongoing. Physicians reported that CDS use was facilitated by their confidence in the evidence supporting the CDS algorithms and that it provided documentation to reduce medico-legal risk. CDS use was not impeded by concerns over missed diagnoses or patient expectations. Reported barriers to CDS use included suboptimal integration into the CPOE such as the inability to auto-populate test results, it disrupted the ordering process and was time consuming. A common concern was that CDS was implemented too late in workflow as most decision making takes place at the bedside. Physicians did not view CDS as infringing on physician autonomy, however they advised that CDS should be a passive educational option and should not automatically trigger for all physicians and eligible encounters. Conclusion: Physicians were generally supportive of CDS integration into practice, and were confident that CDS is an evidence-based way to reduce unnecessary CT studies. However, concerns were raised about the optimal integration of CDS into CPOE and workflow. Physicians also stated a preference to a passive educational approach to CDS rather than an automatic triggering mechanism requiring clinical documentation.

Implementing an evidence-based clinical decision support tool to improve the detection, evaluation, and referral patterns of adult chronic kidney disease patients in primary care.

Chronic kidney disease (CKD) is undertreated and under-recognized in primary care. The majority of primary care providers (PCPs) are not aware or knowledgeable of current CKD guidelines. The purpose of this project was to develop a quality improvement intervention for PCPs through the delivery of evidence-based guidelines at the point of care. An evidence-based clinical algorithm was developed in the electronic medical record for providers to access within one organization comprising 11 primary care offices with 80 PCPs. Baseline knowledge surveys and baseline data were obtained in August 2016. A CKD educational intervention and tutorial on a clinical decision support (CDS) tool was presented to physicians, nurse practitioners, and physician assistants. Postimplementation data and knowledge surveys were collected in December 2016. Most PCPs were willing to use a CKD CDS tool to help them with CKD patients. A CDS tool in addition to an educational intervention can improve PCP knowledge and identification of CKD and early referral to nephrology. CDS tools can promote evidence-based guided care for PCPs and CKD patients. By using these applications, patients can be properly identified, managed, treated, and appropriately referred to nephrology.

Embedded Clinical Decision Support in Electronic Health Record Decreases Use of High-cost Imaging in the Emergency Department: EmbED study.

The objective was to evaluate the impact of evidence-based clinical decision support tools integrated directly into provider workflow in the electronic health record on utilization of computed tomography (CT) brain, C-spine, and pulmonary embolism (PE). Validated, well-accepted scoring tools for head injury, C-spine injury, and PE were embedded into the electronic health record in a manner minimally disruptive to provider workflow. This was a longitudinal, before/after study in five emergency departments (EDs) in a healthcare system with a common electronic health record. Attending ED physicians practicing during the entire study period were included. The main outcome measure was proportion of CTs ordered by provider (total number of CT scans of a given type divided by total patients seen by that provider) in aggregate in the pre- and post intervention period. There were 235,858 total patient visits analyzed in this study with an absolute decrease of 6,106 CT scan ordering for the three studies. Across all sites, there was greater than 6% decrease in utilization of CT brain and CT C-spine (-10%, 95% CI= -13% to -7%, p<0.001; and -6%, 95% CI=-11% to -1%, p=0.03, respectively). The use of CT PE also decreased but was not significant (-2%, 95% CI= -9% to +5%, p=0.42). For all CT types, high utilizers in the pre-intervention period decreased usage over 14% in the post-intervention period with CT brain (-18%, 95% CI= -22% to -15%, p<0.001), CT C-spine (-14%, 95% CI= -20% to -8%, p=0.001), and CT PE (-23%, 95% CI= -31% to -14%, p<0.001). For all three studies, the average utilizers did not change their usage practices. For CT brain, the low utilizers also did not increase usage but for CT C-spine and CT PE usage was increased (+29%, 95% CI= 10% to 52%, p=0.003; and +46%, 95% CI= 26% to 70%, p<0.001, respectively). Embedded clinical decision support is associated with decreased overall utilization of high-cost imaging, especially among higher utilizers. It also affected low utilizers, increasing their usage consistent with improved adherence to guidelines, but this effect did not offset the overall decreased utilization for CT brain or CT C-spine. Thus, integrating clinical decision support into the provider workflow promotes usage of validated tools across providers, which can standardize the delivery of care and improve compliance with evidence-based guidelines.

Abstract P5-08-06: Impact of a decision-support tool on the utilization of colony-stimulating factors and incidence of febrile neutropenia among patients with breast cancer

Abstract Background: Following the 2012 American Society of Clinical Oncology's Choosing Wisely campaign recommendation against the routine use of colony-stimulating factors (CSFs) for the primary prevention of febrile neutropenia (FN) in patients with ≤ 20% risk, an evidence-based clinical decision-support tool (CSF decision tool) was implemented to promote risk-appropriate CSF use in breast cancer patients receiving chemotherapy by a national payer in the United States (US). We hypothesized that there should be no change in pre- and post-implementation FN rates if the CSF decision tool had promoted appropriate FN risk stratification among breast cancer patients. Methods: A retrospective observational cohort study design was used to analyze data from a national payer administrative claims database of nearly 40 million lives geographically spread across the US. The CSF decision tool was first implemented in 2014, with a staggered implementation across states (July 1, 2014 - November 1, 2014). Study subjects were female patients, aged ≥ 18 years, who initiated chemotherapy for breast cancer in the time periods before or after the implementation of the decision tool (July 1, 2014 through March 30, 2015). Patients were assigned to case (defined as patients in the states where the CSF decision tool had been implemented) or control (defined as patients in states where the CSF decision tool had yet to be implemented) cohort. Patients in each cohort were followed up to 6 months after the first chemotherapy dose in the pre- and post-implementation periods. The outcomes were changes in the incidence of FN and CSF use rates, respectively. Rates of FN and CSF use were compared between the cohorts using difference-in-differences models; generalized estimating equations were used to adjust for differences in baseline risk factors including age, history of neutropenia or infections. Results: The final study population comprised 7,224 patients: 4,001 and 3,223 in the case and control cohorts, respectively. There was a higher proportion of patients who were 65 years or older in the case cohort compared to the control (22% vs 18%, p: &amp;lt;0.001). Otherwise, the cohorts were comparable in FN risk factors at baseline in pre- and post-implementation periods. In adjusted regression results, pre- and post-implementation FN rates were not significantly different for both case (5.38% to 5.65%) and control (5.07% to 5.13%) cohorts, [p=0.778]. Use of CSF in the pre- and post-implementation periods decreased from 75% to 69% in the case cohort compared with a reduction from 72% to 71% in the control cohort: an absolute difference of 5.4% decrease in CSF use associated with the implementation of the decision support tool [p= 0.006]. Conclusion: Despite a modest reduction in CSF use, we found no evidence of an increase in FN rates after the implementation of the CSF decision tool. Given the lack of impact of the Choosing Wisely campaign on inappropriate CSF use; our findings suggest that beyond the educational efforts and media campaigns, a greater reduction in unnecessary CSF use can be achieved through the use of clinical decision algorithms to reduce practice variation and improve adherence to national guideline recommendations. Citation Format: Adeboyeje G, Agiro A, Goodwin A, DeVries A, Malin J. Impact of a decision-support tool on the utilization of colony-stimulating factors and incidence of febrile neutropenia among patients with breast cancer [abstract]. In: Proceedings of the 2016 San Antonio Breast Cancer Symposium; 2016 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2017;77(4 Suppl):Abstract nr P5-08-06.

Connecting Education to Quality: Engaging Medical Students in the Development of Evidence-Based Clinical Decision Support Tools.

Evidence-based practice (EBP) skills are crucial for delivering high-quality patient care. It is essential that medical students learn EBP concepts through a practical, in-depth research project. To date, literature on preparing students in this manner is limited. In academic year 2014-2015, the Medical University of South Carolina's (MUSC's) Center for Evidence-Based Practice (now known as the Value Institute) partnered with College of Medicine faculty to revitalize the undergraduate medical student EBP curriculum. Without adding to the number of the lecture hours, the curriculum was restructured to be more process driven, project based, and clinically relevant. The resulting yearlong EBP course partnered small teams of medical students with interprofessional clinical teams to engage the students in developing evidence-based clinical decision support tools. The content developed during the EBP projects is currently being used to develop evidence-based clinical practice guidelines and accompanying order sets. It is likely that this model will serve as a new framework for guideline development and will greatly expand the breadth of evidence-based content currently produced and available for clinicians at the MUSC. It would be feasible to offer a similar course within the MUSC to other disciplines and colleges, or at other institutions, if there were support from administration, interest on the part of clinicians and medical faculty, and individuals with the required expertise available to develop the curriculum and facilitate the course. It is worth considering how to improve the course and evaluating opportunities to implement it within other settings.

Attitudes toward evidence-based clinical decision support tools to reduce exposure to ionizing radiation: The Canadian CT Head Rule.

A large degree of variation in clinical practice exists among clinicians evaluating and treating individuals with minor head injuries. Noncontrast head computerized tomography (CT) scans are commonly used to assess for intracranial damage in patients presenting with head injury. This practice is not supported by the evidence and poses harm to patients by increasing exposure to ionizing radiation. This form of radiation exposure increases the risk of developing cancers over the course of the individual's life, and further strains the limited resources of the healthcare system. This article describes the findings of an evidence-based practice project assessing the attitudes of clinicians toward an evidence-based clinical decision support tool (Canadian CT Head Rule [CCHR]). The CCHR has 100% sensitivity in detecting all clinically important brain injuries and any injury requiring neurosurgical intervention. This clinical decision support (CDS) tool is designed to help guide clinicians in the prudent use of head CT scans in people ages 16-64 that have sustained minor head injuries. The Evidence-Based Attitude Scale was also used to identify which domains were most influential on willingness to adopt into clinical practice. The results revealed an 84% increase in clinician knowledge of the use of the CCHR. A majority (83%) of participants reported moderate likelihood of adoption of the CDS tool into clinical practice if they found the tool appealing, and it was required by a governing authority. The use of CDS tools can help healthcare providers mitigate the risk associated with caring for complex patients. CDS tools provide a systematic method to evaluate patients with minor head injuries while assuring consistency of care and quality outcomes. This practice of assuring consistency and good patient outcomes is foundational to the concept of standard of care, which serves to improve clinical practice.

Rates of PE Diagnosis by CT Angiography When Clinical Decision Support Advice Is Overridden

This study describes physician noncompliance with an evidence-based clinical decision support (CDS) tool for pulmonary embolism (PE) in a

Aspirin for Primary Prevention of Atherosclerotic Cardiovascular Disease: Advances in Diagnosis and Treatment.

Clinical decision making regarding the appropriate use of aspirin for the primary prevention of atherosclerotic cardiovascular disease (ASCVD) events is complex, and requires an individualized benefit to risk assessment. To review advances in the individualized assessment for ASCVD and bleeding risk, and to provide an update of the randomized clinical trial evidence that examined the use of aspirin for primary prevention (primarily for ASCVD, and secondarily for colorectal cancer). The recently released 2016 US Preventive Services Task Force recommendations are discussed, as well as the role of ASCVD risk, age, sex, and aspirin dose/formulation in clinical decision making. We performed a detailed review of peer-reviewed publications that were identified through searches of MEDLINE and the Cochrane Database through 2016 using the literature search terms "aspirin," "primary prevention," "cardiovascular disease," "mortality," "cancer." Bibliographies from these references as well as meta-analyses of these randomized clinical trials were also reviewed. Evidence from a total of 11 trials involving more than 118 000 patients is available to guide clinical decision making for aspirin use in the primary prevention of ASCVD. Clinicians should balance the benefit to risk ratio and the individual's preferences, calculating the 10-year ASCVD risk and evaluating risk factors for gastrointestinal bleeding, to facilitate a safer and more personalized approach to appropriate selection of candidates for low-dose aspirin (75 to 81 mg/d) for the primary prevention of ASCVD, with secondary considerations for reducing colorectal cancer risk when taken for longer periods (>10 years). Both the net ASCVD benefit and the bleeding risk of aspirin therapy increased as the absolute ASCVD risk increased, but the net benefits generally exceeded the risks at higher baseline ASCVD risk (≥10% ASCVD 10-year risk). The Aspirin-Guide is a clinical decision making support tool (app for mobile devices) with internal risk calculators to help clinicians with this dual assessment by calculating the ASCVD risk and the bleeding risk in the individual patient, and incorporating age- and sex-specific guidance based on randomized trial results. Balancing the benefit of ASCVD reduction with the risk of bleeding from low-dose aspirin is difficult but essential for informed decision making and achieving a net clinical benefit from aspirin for primary prevention. This is facilitated by a free and readily available evidence-based clinical decision support tool.

Clinical Decision Support Reduces Overuse of Red Blood Cell Transfusions: Interrupted Time Series Analysis

BackgroundRed blood cell transfusion is the most common procedure in hospitalized patients in the US. Growing evidence suggests that a sizeable percentage of these transfusions are inappropriate, putting patients at significant risk and increasing costs to the health care system. MethodsWe performed a retrospective quasi-experimental study from November 2008 until November 2014 in a 576-bed tertiary care hospital. The intervention consisted of an interruptive clinical decision support alert shown to a provider when a red blood cell transfusion was ordered in a patient whose most recent hematocrit was ≥21%. We used interrupted time series analysis to determine whether our primary outcome of interest, rate of red blood cell transfusion in patients with hematocrit ≥21% per 100 patient (pt) days, was reduced by the implementation of the clinical decision support tool. The rate of platelet transfusions was used as a nonequivalent dependent control variable. ResultsA total of 143,000 hospital admissions were included in our analysis. Red blood cell transfusions decreased from 9.4 to 7.8 per 100 pt days after the clinical decision support intervention was implemented. Interrupted time series analysis showed that significant decline of 0.05 (95% confidence interval [CI], 0.03-0.07; P < .001) units of red blood cells transfused per 100 pt days per month was already underway in the preintervention period. This trend accelerated to 0.1 (95% CI, 0.09-0.12; P < .001) units of red blood cells transfused per 100 pt days per month following the implementation of the clinical decision support tool. There was no statistical change in the rate of platelet transfusion resulting from the intervention. ConclusionsThe implementation of an evidence-based clinical decision support tool was associated with a significant decline in the overuse of red blood cell transfusion. We believe this intervention could be easily replicated in other hospitals using commercial electronic health records and a similar reduction in overuse of red blood cell transfusions achieved.