Drivers of mortality in COVID ARDS depend on patient sub-type.

The most common cause of death in people with COVID-19 is Acute Respiratory Distress Syndrome (ARDS). Prior studies have demonstrated that ARDS is a heterogeneous syndrome and have identified ARDS sub-types (phenoclusters). However, non-COVID-19 ARDS phenoclusters do not clearly apply to COVID-19 ARDS patients. In this retrospective cohort study, we implemented an iterative approach, combining supervised and unsupervised machine learning methodologies, to identify clinically relevant COVID-19 ARDS phenoclusters, as well as characteristics that are predictive of the outcome for each phenocluster. To this end, we applied a supervised model to identify risk factors for hospital mortality for each phenocluster and compared these between phenoclusters and the entire cohort. We trained the models using a comprehensive, preprocessed dataset of 2,864 hospitalized COVID-19 ARDS patients. Our research demonstrates that the risk factors predicting mortality in the overall cohort of COVID-19 ARDS may not necessarily apply to specific phenoclusters. Additionally, some risk factors increase the risk of hospital mortality in some phenoclusters but decrease mortality in others. These phenocluster-specific risk factors would not have been observed with a single predictive model. Heterogeneity in phenoclusters of COVID-19 ARDS as well as the drivers of mortality may partially explain challenges in finding effective treatments for all patients with ARDS.

Impact of Clinical Decision Support on Antibiotic Prescribing for Acute Respiratory Infections: a Cluster Randomized Implementation Trial.

BACKGROUND: Clinical decision support (CDS) is a promising tool for reducing antibiotic prescribing for acute respiratory infections (ARIs). OBJECTIVE: To assess the impact of previously effective CDS on antibiotic-prescribing rates for ARIs when adapted and implemented in diverse primary care settings. DESIGN: Cluster randomized clinical trial (RCT) implementing a CDS tool designed to guide evidence-based evaluation and treatment of streptococcal pharyngitis and pneumonia. SETTING: Two large academic health system primary care networks with a mix of providers. PARTICIPANTS: All primary care practices within each health system were invited. All providers within participating clinic were considered a participant. Practices were randomized selection to a control or intervention group. INTERVENTIONS: Intervention practice providers had access to an integrated clinical prediction rule (iCPR) system designed to determine the risk of bacterial infection from reason for visit of sore throat, cough, or upper respiratory infection and guide evidence-based evaluation and treatment. MAIN OUTCOME(S): Change in overall antibiotic prescription rates. MEASURE(S): Frequency, rates, and type of antibiotics prescribed in intervention and controls groups. RESULTS: 33 primary care practices participated with 541 providers and 100,573 patient visits. Intervention providers completed the tool in 6.9% of eligible visits. Antibiotics were prescribed in 35% and 36% of intervention and control visits, respectively, showing no statistically significant difference. There were also no differences in rates of orders for rapid streptococcal tests (RR, 0.94; P = 0.11) or chest X-rays (RR, 1.01; P = 0.999) between groups. CONCLUSIONS: The iCPR tool was not effective in reducing antibiotic prescription rates for upper respiratory infections in diverse primary care settings. This has implications for the generalizability of CDS tools as they are adapted to heterogeneous clinical contexts. TRIAL REGISTRATION: Clinicaltrials.gov (NCT02534987). Registered August 26, 2015 at https://clinicaltrials.gov.

Using normalisation process theory to understand workflow implications of decision support implementation across diverse primary care settings.

BACKGROUND: Effective implementation of technologies into clinical workflow is hampered by lack of integration into daily activities. Normalisation process theory (NPT) can be used to describe the kinds of 'work' necessary to implement and embed complex new practices. We determined the suitability of NPT to assess the facilitators, barriers and 'work' of implementation of two clinical decision support (CDS) tools across diverse care settings. METHODS: We conducted baseline and 6-month follow-up quantitative surveys of clinic leadership at two academic institutions' primary care clinics randomised to the intervention arm of a larger study. The survey was adapted from the NPT toolkit, analysing four implementation domains: sense-making, participation, action, monitoring. Domains were summarised among completed responses (n=60) and examined by role, institution, and time. RESULTS: The median score for each NPT domain was the same across roles and institutions at baseline, and decreased at 6 months. At 6 months, clinic managers' participation domain (p=0.003), and all domains for medical directors (p<0.003) declined. At 6 months, the action domain decreased among Utah respondents (p=0.03), and all domains decreased among Wisconsin respondents (p≤0.008). CONCLUSIONS: This study employed NPT to longitudinally assess the implementation barriers of new CDS. The consistency of results across participant roles suggests similarities in the work each role took on during implementation. The decline in engagement over time suggests the need for more frequent contact to maintain momentum. Using NPT to evaluate this implementation provides insight into domains which can be addressed with participants to improve success of new electronic health record technologies. TRIAL REGISTRATION NUMBER: NCT02534987.

Live Usability Testing of Two Complex Clinical Decision Support Tools: Observational Study.

BACKGROUND: Potential of the electronic health records (EHR) and clinical decision support (CDS) systems to improve the practice of medicine has been tempered by poor design and the resulting burden they place on providers. CDS is rarely tested in the real clinical environment. As a result, many tools are hard to use, placing strain on providers and resulting in low adoption rates. The existing CDS usability literature relies primarily on expert opinion and provider feedback via survey. This is the first study to evaluate CDS usability and the provider-computer-patient interaction with complex CDS in the real clinical environment. OBJECTIVE: This study aimed to further understand the barriers and facilitators of meaningful CDS usage within a real clinical context. METHODS: This qualitative observational study was conducted with 3 primary care providers during 6 patient care sessions. In patients with the chief complaint of sore throat, a CDS tool built with the Centor Score was used to stratify the risk of group A Streptococcus pharyngitis. In patients with a chief complaint of cough or upper respiratory tract infection, a CDS tool built with the Heckerling Rule was used to stratify the risk of pneumonia. During usability testing, all human-computer interactions, including audio and continuous screen capture, were recorded using the Camtasia software. Participants' comments and interactions with the tool during clinical sessions and participant comments during a postsession brief interview were placed into coding categories and analyzed for generalizable themes. RESULTS: In the 6 encounters observed, primary care providers toggled between addressing either the computer or the patient during the visit. Minimal time was spent listening to the patient without engaging the EHR. Participants mostly used the CDS tool with the patient, asking questions to populate the calculator and discussing the results of the risk assessment; they reported the ability to do this as the major benefit of the tool. All providers were interrupted during their use of the CDS tool by the need to refer to other sections of the chart. In half of the visits, patients' clinical symptoms challenged the applicability of the tool to calculate the risk of bacterial infection. Primary care providers rarely used the incorporated incentives for CDS usage, including progress notes and patient instructions. CONCLUSIONS: Live usability testing of these CDS tools generated insights about their role in the patient-provider interaction. CDS may contribute to the interaction by being simultaneously viewed by the provider and patient. CDS can improve usability and lessen the strain it places on providers by being short, flexible, and customizable to unique provider workflow. A useful component of CDS is being as widely applicable as possible and ensuring that its functions represent the fastest way to perform a particular task.

Adaptive design of a clinical decision support tool: What the impact on utilization rates means for future CDS research.

OBJECTIVE: We employed an agile, user-centered approach to the design of a clinical decision support tool in our prior integrated clinical prediction rule study, which achieved high adoption rates. To understand if applying this user-centered process to adapt clinical decision support tools is effective in improving the use of clinical prediction rules, we examined utilization rates of a clinical decision support tool adapted from the original integrated clinical prediction rule study tool to determine if applying this user-centered process to design yields enhanced utilization rates similar to the integrated clinical prediction rule study.MATERIALS & METHODS: We conducted pre-deployment usability testing and semi-structured group interviews at 6 months post-deployment with 75 providers at 14 intervention clinics across the two sites to collect user feedback. Qualitative data analysis is bifurcated into immediate and delayed stages; we reported on immediate-stage findings from real-time field notes used to generate a set of rapid, pragmatic recommendations for iterative refinement. Monthly utilization rates were calculated and examined over 12 months. RESULTS: We hypothesized a well-validated, user-centered clinical decision support tool would lead to relatively high adoption rates. Then 6 months post-deployment, integrated clinical prediction rule study tool utilization rates were substantially lower than anticipated based on the original integrated clinical prediction rule study trial (68%) at 17% (Health System A) and 5% (Health System B). User feedback at 6 months resulted in recommendations for tool refinement, which were incorporated when possible into tool design; however, utilization rates at 12 months post-deployment remained low at 14% and 4% respectively. DISCUSSION: Although valuable, findings demonstrate the limitations of a user-centered approach given the complexity of clinical decision support. CONCLUSION: Strategies for addressing persistent external factors impacting clinical decision support adoption should be considered in addition to the user-centered design and implementation of clinical decision support.

Improving Provider Adoption With Adaptive Clinical Decision Support Surveillance: An Observational Study.

BACKGROUND: Successful clinical decision support (CDS) tools can help use evidence-based medicine to effectively improve patient outcomes. However, the impact of these tools has been limited by low provider adoption due to overtriggering, leading to alert fatigue. We developed a tracking mechanism for monitoring trigger (percent of total visits for which the tool triggers) and adoption (percent of completed tools) rates of a complex CDS tool based on the Wells criteria for pulmonary embolism (PE). OBJECTIVE: We aimed to monitor and evaluate the adoption and trigger rates of the tool and assess whether ongoing tool modifications would improve adoption rates. METHODS: As part of a larger clinical trial, a CDS tool was developed using the Wells criteria to calculate pretest probability for PE at 2 tertiary centers' emergency departments (EDs). The tool had multiple triggers: any order for D-dimer, computed tomography (CT) of the chest with intravenous contrast, CT pulmonary angiography (CTPA), ventilation-perfusion scan, or lower extremity Doppler ultrasound. A tracking dashboard was developed using Tableau to monitor real-time trigger and adoption rates. Based on initial low provider adoption rates of the tool, we conducted small focus groups with key ED providers to elicit barriers to tool use. We identified overtriggering of the tool for non-PE-related evaluations and inability to order CT testing for intermediate-risk patients. Thus, the tool was modified to allow CT testing for the intermediate-risk group and not to trigger for CT chest with intravenous contrast orders. A dialogue box, "Are you considering PE for this patient?" was added before the tool triggered to account for CTPAs ordered for aortic dissection evaluation. RESULTS: In the ED of tertiary center 1, 95,295 patients visited during the academic year. The tool triggered for an average of 509 patients per month (average trigger rate 2036/30,234, 6.73%) before the modifications, reducing to 423 patients per month (average trigger rate 1629/31,361, 5.22%). In the ED of tertiary center 2, 88,956 patients visited during the academic year, with the tool triggering for about 473 patients per month (average trigger rate 1892/29,706, 6.37%) before the modifications and for about 400 per month (average trigger rate 1534/30,006, 5.12%) afterward. The modifications resulted in a significant 4.5- and 3-fold increase in provider adoption rates in tertiary centers 1 and 2, respectively. The modifications increased the average monthly adoption rate from 23.20/360 (6.5%) tools to 81.60/280.20 (29.3%) tools and 46.60/318.80 (14.7%) tools to 111.20/263.40 (42.6%) tools in centers 1 and 2, respectively. CONCLUSIONS: Close postimplementation monitoring of CDS tools may help improve provider adoption. Adaptive modifications based on user feedback may increase targeted CDS with lower trigger rates, reducing alert fatigue and increasing provider adoption. Iterative improvements and a postimplementation monitoring dashboard can significantly improve adoption rates.

Do clinicians want recommendations? A multicenter study comparing evidence summaries with and without GRADE recommendations.

OBJECTIVES: Evidence-based clinical practice guidelines provide recommendations to assist clinicians in decision-making and to reduce the gap between best current research evidence and clinical practice. However, some argue that providing preappraised evidence summaries alone, rather than recommendations, is more appropriate. The objective of the study is to evaluate clinicians' preferences, and understanding of the evidence and intended course of action in response to evidence summaries with and without recommendations. STUDY DESIGN SETTING: We included practicing clinicians attending educational sessions across 10 countries. Clinicians were randomized to receive relevant clinical scenarios supported by research evidence of low or very low certainty and accompanied by either strong or weak recommendations developed with the GRADE system. Within each group, participants were further randomized to receive the recommendation plus the corresponding evidence summary or the evidence summary alone. We evaluated participants' preferences and understanding for the presentation strategy, as well as their intended course of action. RESULTS: One hundred eighty-nine of 219 (86%) and 201 of 248 (81%) participants preferred having recommendations accompanying evidence summaries for both strong and weak recommendations, respectively. Across all scenarios, less than half of participants correctly interpreted information provided in the evidences summaries (e.g., estimates of effect, certainty in the research evidence). The presence of a recommendation resulted in a more appropriate intended course of action for two scenarios involving strong recommendations. CONCLUSION: Evidence summaries alone are not enough to impact clinicians' course of action. Clinicians clearly prefer having recommendations accompanying evidence summaries in the context of low or very low certainty of evidence (Trial registration NCT02006017).

"Think aloud" and "Near live" usability testing of two complex clinical decision support tools.

OBJECTIVES: Low provider adoption continues to be a significant barrier to realizing the potential of clinical decision support. "Think Aloud" and "Near Live" usability testing were conducted on two clinical decision support tools. Each was composed of an alert, a clinical prediction rule which estimated risk of either group A Streptococcus pharyngitis or pneumonia and an automatic order set based on risk. The objective of this study was to further understanding of the facilitators of usability and to evaluate the types of additional information gained from proceeding to "Near Live" testing after completing "Think Aloud". METHODS: This was a qualitative observational study conducted at a large academic health care system with 12 primary care providers. During "Think Aloud" testing, participants were provided with written clinical scenarios and asked to verbalize their thought process while interacting with the tool. During "Near Live" testing participants interacted with a mock patient. Morae usability software was used to record full screen capture and audio during every session. Participant comments were placed into coding categories and analyzed for generalizable themes. Themes were compared across usability methods. RESULTS: "Think Aloud" and "Near Live" usability testing generated similar themes under the coding categories visibility, workflow, content, understand-ability and navigation. However, they generated significantly different themes under the coding categories usability, practical usefulness and medical usefulness. During both types of testing participants found the tool easier to use when important text was distinct in its appearance, alerts were passive and appropriately timed, content was up to date, language was clear and simple, and each component of the tool included obvious indicators of next steps. Participant comments reflected higher expectations for usability and usefulness during "Near Live" testing. For example, visit aids, such as automatically generated order sets, were felt to be less useful during "Near-Live" testing because they would not be all inclusive for the visit. CONCLUSIONS: These complementary types of usability testing generated unique and generalizable insights. Feedback during "Think Aloud" testing primarily helped to improve the tools' ease of use. The additional feedback from "Near Live" testing, which mimics a real clinical encounter, was helpful for eliciting key barriers and facilitators to provider workflow and adoption.

Design and implementation of electronic health record integrated clinical prediction rules (iCPR): a randomized trial in diverse primary care settings.

BACKGROUND: Clinical prediction rules (CPRs) represent a method of determining individual patient risk to help providers make more accurate decisions at the point of care. Well-validated CPRs are underutilized but may decrease antibiotic overuse for acute respiratory infections. The integrated clinical prediction rules (iCPR) study builds on a previous single clinic study to integrate two CPRs into the electronic health record and assess their impact on practice. This article discusses study design and implementation of a multicenter cluster randomized control trial of the iCPR clinical decision support system, including the tool adaptation, usability testing, staff training, and implementation study to disseminate iCPR at multiple clinical sites across two health care systems. METHODS: The iCPR tool is based on two well-validated CPRs, one for strep pharyngitis and one for pneumonia. The iCPR tool uses the reason for visit to trigger a risk calculator. Provider completion of the risk calculator provides a risk score, which is linked to an order set. Order sets guide evidence-based care and include progress note documentation, tests, prescription medications, and patient instructions. The iCPR tool was refined based on interviews with providers, medical assistants, and clinic managers, and two rounds of usability testing. "Near live" usability testing with simulated patients was used to ensure that iCPR fit into providers' clinical workflows. Thirty-three Family Medicine and General Internal Medicine primary care clinics were recruited at two institutions. Clinics were randomized to academic detailing about strep pharyngitis and pneumonia diagnosis and treatment (control) or academic detailing plus use of the iCPR tool (intervention). The primary outcome is the difference in antibiotic prescribing rates between the intervention and control groups with secondary outcomes of difference in rapid strep and chest x-ray ordering. Use of the components of the iCPR will also be assessed. DISCUSSION: The iCPR study uses a strong user-centered design and builds on the previous initial study, to assess whether CPRs integrated in the electronic health record can change provider behavior and improve evidence-based care in a broad range of primary care clinics. TRIAL REGISTRATION: Clinicaltrials.gov ( NCT02534987 ).

Avoiding alert fatigue in pulmonary embolism decision support: a new method to examine 'trigger rates'.

A clinical decision support system (CDSS) is integrated into the electronic health record (EHR) and allows physicians to easily use a clinical decision support (CDS) tool. However, often CDSSs are integrated into the EHR with poor adoption rates. One reason for this is secondary to 'trigger fatigue'. Therefore, we developed a new and innovative usability process named 'sensitivity and specificity trigger analysis' (SSTA) as part of our larger project around a pulmonary embolism decision support tool. SSTA will enable programmers to examine optimal trigger rates prior to the integration of a CDS tool into the EHR, by using a formal method of analysis. We performed a retrospective chart review. The outcome of interest was physician ordering of a CT angiography (CTA). Phrases that signify common symptoms associated with pulmonary embolism were assessed as possible triggers for the CDSS tool. We then analysed each trigger's ability to predict physician ordering of a CTA. We found that the most sensitive way to trigger the Pulmonary Embolism CDS tool while still maintaining a high specificity was by combining 1 or more pertinent symptoms with 1 or more elements of the Wells criteria. This study explored a unique methodology, SSTA, used to limit inaccurate triggering of a CDS tool prior to integration into the EHR. This methodology can be applied to other studies aiming to decrease triggering rates and increase adoption rates of previously validated CDSS tools.

Usability Testing of a National Substance Use Screening Tool Embedded in Electronic Health Records.

BACKGROUND: Screening, brief intervention, and referral to treatment (SBIRT) is currently being implemented into health systems nationally via paper and electronic methods. OBJECTIVE: The purpose of this study was to evaluate the integration of an electronic SBIRT tool into an existing paper-based SBIRT clinical workflow in a patient-centered medical home. METHODS: Usability testing was conducted in an academic ambulatory clinic. Two rounds of usability testing were done with medical office assistants (MOAs) using a paper and electronic version of the SBIRT tool, with two and four participants, respectively. Qualitative and quantitative data was analyzed to determine the impact of both tools on clinical workflow. A second round of usability testing was done with the revised electronic version and compared with the first version. RESULTS: Personal workflow barriers cited in the first round of testing were that the electronic health record (EHR) tool was disruptive to patient's visits. In Round 2 of testing, MOAs reported favoring the electronic version due to improved layout and the inclusion of an alert system embedded in the EHR. For example, using the system usability scale (SUS), MOAs reported a grade "1" for the statement, "I would like to use this system frequently" during the first round of testing but a "5" during the second round of analysis. CONCLUSIONS: The importance of testing usability of various mediums of tools used in health care screening is highlighted by the findings of this study. In the first round of testing, the electronic tool was reported as less user friendly, being difficult to navigate, and time consuming. Many issues faced in the first generation of the tool were improved in the second generation after usability was evaluated. This study demonstrates how usability testing of an electronic SBRIT tool can help to identify challenges that can impact clinical workflow. However, a limitation of this study was the small sample size of MOAs that participated. The results may have been biased to Northwell Health workers' perceptions of the SBIRT tool and their specific clinical workflow.

External validation of the IMPROVE Bleeding Risk Assessment Model in medical patients.

The IMPROVE Bleed Risk Assessment Model (RAM) remains the only bleed RAM in hospitalised medical patients using 11 clinical and laboratory factors. The aim of our study was to externally validate the IMPROVE Bleed RAM. A retrospective chart review was conducted between October 1, 2012 and July 31, 2014. We applied the point scoring system to compute risk scores for each patient in the validation sample. We then dichotomised the patients into those with a score <7 (low risk) vs ≥ 7 (high risk), as outlined in the original study, and compared the rates of any bleed, non-major bleed, and major bleed. Among the 12,082 subjects, there was an overall 2.6 % rate of any bleed within 14 days of admission. There was a 2.12 % rate of any bleed in those patients with a score of < 7 and a 4.68 % rate in those with a score ≥ 7 [Odds Ratio (OR) 2.3 (95 % CI=1.8-2.9), p<0.0001]. MB rates were 1.5 % in the patients with a score of < 7 and 3.2 % in the patients with a score of ≥ 7, [OR 2.2 (95 % CI=1.6-2.9), p<0.0001]. The ROC curve was 0.63 for the validation sample. This study represents the largest externally validated Bleed RAM in a hospitalised medically ill patient population. A cut-off point score of 7 or above was able to identify a high-risk patient group for MB and any bleed. The IMPROVE Bleed RAM has the potential to allow for more tailored approaches to thromboprophylaxis in medically ill hospitalised patients.

Developing a Clinical Prediction Rule for First Hospital-Onset Clostridium difficile Infections: A Retrospective Observational Study.

BACKGROUND The healthcare burden of hospital-acquired Clostridium difficile infection (CDI) demands attention and calls for a solution. Identifying patients' risk of developing a primary nosocomial CDI is a critical first step in reducing the development of new cases of CDI. OBJECTIVE To derive a clinical prediction rule that can predict a patient's risk of acquiring a primary CDI. DESIGN Retrospective cohort study. SETTING Large tertiary healthcare center. PATIENTS Total of 61,482 subjects aged at least 18 admitted over a 1-year period (2013). INTERVENTION None. METHODS Patient demographic characteristics, evidence of CDI, and other risk factors were retrospectively collected. To derive the CDI clinical prediction rule the patient population was divided into a derivation and validation cohort. A multivariable analysis was performed in the derivation cohort to identify risk factors individually associated with nosocomial CDI and was validated on the validation sample. RESULTS Among 61,482 subjects, CDI occurred in 0.46%. CDI outcome was significantly associated with age, admission in the past 60 days, mechanical ventilation, dialysis, history of congestive heart failure, and use of antibiotic medications. The sensitivity and specificity of the score, in the validation set, were 82.0% and 75.7%, respectively. The area under the receiver operating characteristic curve was 0.85. CONCLUSION This study successfully derived a clinical prediction rule that will help identify patients at high risk for primary CDI. This tool will allow physicians to systematically recognize those at risk for CDI and will allow for early interventional strategies. Infect Control Hosp Epidemiol 2016;37:896-900.

Improving GRADE evidence tables part 1: a randomized trial shows improved understanding of content in summary of findings tables with a new format.

OBJECTIVES: The current format of summary of findings (SoFs) tables for presenting effect estimates and associated quality of evidence improve understanding and assist users finding key information in systematic reviews. Users of SoF tables have demanded alternative formats to express findings from systematic reviews. STUDY DESIGN AND SETTING: We conducted a randomized controlled trial among systematic review users to compare the relative merits of a new format with the current formats of SoF tables regarding understanding, accessibility of information, satisfaction, and preference. Our primary goal was to show that the new format is not inferior to the current format. RESULTS: Of 390 potentially eligible subjects, 290 were randomized. Of seven items testing understanding, three showed similar results, two showed small differences favoring the new format, and two (understanding risk difference and quality of the evidence associated with a treatment effect) showed large differences favoring the new format [63% (95% confidence interval {CI}: 55, 71) and 62% (95% CI: 52, 71) more correct answers, respectively]. Respondents rated information in the alternative format as more accessible overall and preferred the new format over the current format. CONCLUSIONS: While providing at least similar levels of understanding for some items and increased understanding for others, users prefer the new format of SoF tables.

Formative assessment and design of a complex clinical decision support tool for pulmonary embolism.

Electronic health record (EHR)-based clinical decision support (CDS) tools are rolled out with the urgency to meet federal requirements without time for usability testing and refinement of the user interface. As part of a larger project to design, develop and integrate a pulmonary embolism CDS tool for emergency physicians, we conducted a formative assessment to determine providers' level of interest and input on designs and content. This was a study to conduct a formative assessment of emergency medicine (EM) physicians that included focus groups and key informant interviews. The focus of this study was twofold, to determine the general attitude towards CDS tool integration and the ideal integration point into the clinical workflow. To accomplish this, we first approached EM physicians in a focus group, then, during key informant interviews, we presented workflow designs and gave a scenario to help the providers visualise how the CDS tool works. Participants were asked questions regarding the trigger location, trigger words, integration into their workflow, perceived utility and heuristic of the tool. Results from the participants' survey responses to trigger location, perceived utility and efficiency, indicated that the providers felt the tool would be more of a hindrance than an aid. However, some providers commented that they had not had exposure to CDS tools but had used online calculators, and thought the tools would be helpful at the point-of-care if integrated into the EHR. Furthermore, there was a preference for an order entry wireframe. This study highlights several factors to consider when designing CDS tools: (1) formative assessment of EHR functionality and clinical environment workflow, (2) focus groups and key informative interviews to incorporate providers' perceptions of CDS and workflow integration and/or (3) the demonstration of proposed workflows through wireframes to help providers visualise design concepts.

Healthcare provider perceptions of clinical prediction rules.

OBJECTIVES: To examine internal medicine and emergency medicine healthcare provider perceptions of usefulness of specific clinical prediction rules. SETTING: The study took place in two academic medical centres. A web-based survey was distributed and completed by participants between 1 January and 31 May 2013. PARTICIPANTS: Medical doctors, doctors of osteopathy or nurse practitioners employed in the internal medicine or emergency medicine departments at either institution. PRIMARY AND SECONDARY OUTCOME MEASURES: The primary outcome was to identify the clinical prediction rules perceived as most useful by healthcare providers specialising in internal medicine and emergency medicine. Secondary outcomes included comparing usefulness scores of specific clinical prediction rules based on provider specialty, and evaluating associations between usefulness scores and perceived characteristics of these clinical prediction rules. RESULTS: Of the 401 healthcare providers asked to participate, a total of 263 (66%), completed the survey. The CHADS2 score was chosen by most internal medicine providers (72%), and Pulmonary Embolism Rule-Out Criteria (PERC) score by most emergency medicine providers (45%), as one of the top three most useful from a list of 24 clinical prediction rules. Emergency medicine providers rated their top three significantly more positively, compared with internal medicine providers, as having a better fit into their workflow (p=0.004), helping more with decision-making (p=0.037), better fitting into their thought process when diagnosing patients (p=0.001) and overall, on a 10-point scale, more useful (p=0.009). For all providers, the perceived qualities of useful at point of care, helps with decision making, saves time diagnosing, fits into thought process, and should be the standard of clinical care correlated highly (≥0.65) with overall 10-point usefulness scores. CONCLUSIONS: Healthcare providers describe clear preferences for certain clinical prediction rules, based on medical specialty.

A Framework for Usable and Effective Clinical Decision Support: Experience from the iCPR Randomized Clinical Trial.

INTRODUCTION: The promise of Clinical Decision Support (CDS) has always been to transform patient care and improve patient outcomes through the delivery of timely and appropriate recommendations that are patient specific and, more often than not, are appropriately actionable. However, the users of CDS-providers-are frequently bombarded with inappropriate and inapplicable CDS that often are not informational, not integrated into the workflow, not patient specific, and that may present out of date and irrelevant recommendations. METHODS: The integrated clinical prediction rule (iCPR) project was a randomized clinical trial (RCT) conducted to determine if a novel form of CDS, i.e., clinical prediction rules (CPRs), could be efficiently integrated into workflow and result in changes in outcomes (e.g., antibiotic ordering) when embedded within a commercial electronic health record (EHR). We use the lessons learned from the iCPR project to illustrate a framework for constructing usable, useful, and effective actionable CDS while employing off-the-shelf functionality in a production system. Innovations that make up the framework combine the following: (1) active and actionable decision support, (2) multiple rounds of usability testing with iterative development for user acceptance, (3) numerous context sensitive triggers, (4) dedicated training and support for users of the CDS tool for user adoption, and (5) support from clinical and administrative leadership. We define "context sensitive triggers" as being workflow events (i.e., context) that result in a CDS intervention. DISCUSSION: Success of the framework can be measured by CDS adoption (i.e., intervention is being used), acceptance (compliance with recommendations), and clinical outcomes (where appropriate). This framework may have broader implications for the deployment of Health Information Technology (HIT). RESULTS AND CONCLUSION: iCPR was well adopted(57.4% of users) and accepted (42.7% of users). Usability testing identified and fixed many issues before the iCPR RCT. The level of leadership support and clinical guidance for iCPR was key in establishing a culture of acceptance for both the tool and its recommendations contributing to adoption and acceptance. The dedicated training and support lead to the majority of the residents reporting a high level of comfort with both iCPR tools strep pharyngitis (64.4 percent) and pneumonia (62.7 percent) as well as a high likelihood of using the tools in the future. A surprising framework addition resulted from usability testing: context sensitive triggers.

Comparison between the standard and a new alternative format of the Summary-of-Findings tables in Cochrane review users: study protocol for a randomized controlled trial.

BACKGROUND: Systematic reviews represent one of the most important tools for knowledge translation but users often struggle with understanding and interpreting their results. GRADE Summary-of-Findings tables have been developed to display results of systematic reviews in a concise and transparent manner. The current format of the Summary-of-Findings tables for presenting risks and quality of evidence improves understanding and assists users with finding key information from the systematic review. However, it has been suggested that additional methods to present risks and display results in the Summary-of-Findings tables are needed. METHODS/DESIGN: We will conduct a non-inferiority parallel-armed randomized controlled trial to determine whether an alternative format to present risks and display Summary-of-Findings tables is not inferior compared to the current standard format. We will measure participant understanding, accessibility of the information, satisfaction, and preference for both formats. We will invite systematic review users to participate (that is clinicians, guideline developers, and researchers). The data collection process will be undertaken using the online 'Survey Monkey' system. For the primary outcome understanding, non-inferiority of the alternative format (Table A) to the current standard format (Table C) of Summary-of-Findings tables will be claimed if the upper limit of a 1-sided 95% confidence interval (for the difference of proportion of participants answering correctly a given question) excluded a difference in favor of the current format of more than 10%. DISCUSSION: This study represents an effort to provide systematic reviewers with additional options to display review results using Summary-of-Findings tables. In this way, review authors will have a variety of methods to present risks and more flexibility to choose the most appropriate table features to display (that is optional columns, risks expressions, complementary methods to display continuous outcomes, and so on). TRIALS REGISTRATION: NCT02022631 (21 December 2013).

Usability Testing of a Complex Clinical Decision Support Tool in the Emergency Department: Lessons Learned.

BACKGROUND: As the electronic health record (EHR) becomes the preferred documentation tool across medical practices, health care organizations are pushing for clinical decision support systems (CDSS) to help bring clinical decision support (CDS) tools to the forefront of patient-physician interactions. A CDSS is integrated into the EHR and allows physicians to easily utilize CDS tools. However, often CDSS are integrated into the EHR without an initial phase of usability testing, resulting in poor adoption rates. Usability testing is important because it evaluates a CDSS by testing it on actual users. This paper outlines the usability phase of a study, which will test the impact of integration of the Wells CDSS for pulmonary embolism (PE) diagnosis into a large urban emergency department, where workflow is often chaotic and high stakes decisions are frequently made. We hypothesize that conducting usability testing prior to integration of the Wells score into an emergency room EHR will result in increased adoption rates by physicians. OBJECTIVE: The objective of the study was to conduct usability testing for the integration of the Wells clinical prediction rule into a tertiary care center's emergency department EHR. METHODS: We conducted usability testing of a CDS tool in the emergency department EHR. The CDS tool consisted of the Wells rule for PE in the form of a calculator and was triggered off computed tomography (CT) orders or patients' chief complaint. The study was conducted at a tertiary hospital in Queens, New York. There were seven residents that were recruited and participated in two phases of usability testing. The usability testing employed a "think aloud" method and "near-live" clinical simulation, where care providers interacted with standardized patients enacting a clinical scenario. Both phases were audiotaped, video-taped, and had screen-capture software activated for onscreen recordings. RESULTS: Phase I: Data from the "think-aloud" phase of the study showed an overall positive outlook on the Wells tool in assessing a patient for a PE diagnosis. Subjects described the tool as "well-organized" and "better than clinical judgment". Changes were made to improve tool placement into the EHR to make it optimal for decision-making, auto-populating boxes, and minimizing click fatigue. Phase II: After incorporating the changes noted in Phase 1, the participants noted tool improvements. There was less toggling between screens, they had all the clinical information required to complete the tool, and were able to complete the patient visit efficiently. However, an optimal location for triggering the tool remained controversial. CONCLUSIONS: This study successfully combined "think-aloud" protocol analysis with "near-live" clinical simulations in a usability evaluation of a CDS tool that will be implemented into the emergency room environment. Both methods proved useful in the assessment of the CDS tool and allowed us to refine tool usability and workflow.

InformedTogether: Usability Evaluation of a Web-Based Decision Aid to Facilitate Shared Advance Care Planning for Severe Chronic Obstructive Pulmonary Disease.

BACKGROUND: Advance care planning may help patients receive treatments that better align with their goals for care. We developed a Web-based decision aid called InformedTogether to facilitate shared advance care planning between chronic obstructive pulmonary disease (COPD) patients and their doctors. OBJECTIVE: Our objective was to assess the usability of the InformedTogether decision aid, including whether users could interact with the decision aid to engage in tasks required for shared decision making, whether users found the decision aid acceptable, and implications for redesign. METHODS: We conducted an observational study with 15 patients and 8 doctors at two ethnically and socioeconomically diverse outpatient clinics. Data included quantitative and qualitative observations of patients and doctors using the decision aid on tablet or laptop computers and data from semistructured interviews. Patients were shown the decision aid by a researcher acting as the doctor. Pulmonary doctors were observed using the decision aid independently and asked to think aloud (ie, verbalize their thoughts). A thematic analysis was implemented to explore key issues related to decision aid usability. RESULTS: Although patients and doctors found InformedTogether acceptable and would recommend that doctors use the decision aid with COPD patients, many patients had difficulty understanding the icon arrays that were used to communicate estimated prognoses and could not articulate the definitions of the two treatment choices-Full Code and Do Not Resuscitate (DNR). Minor usability problems regarding content, links, layout, and consistency were also identified and corresponding recommendations were outlined. In particular, participants suggested including more information about potential changes in quality of life resulting from the alternative advance directives. Some doctor participants thought the decision aid was too long and some thought it may cause nervousness among patients due to the topic area. CONCLUSIONS: A decision aid for shared advance care planning for severe COPD was found acceptable to most COPD patients and their doctors. However, many patient participants did not demonstrate understanding of the treatment options or prognostic estimates. Many participants endorsed the use of the decision aid between doctors and their patients with COPD, although they desired more information about quality of life. The design must optimize comprehensibility, including revising the presentation of statistical information in the icon array, and feasibility of integration into clinical workflow, including shortening the decision aid.