Improved blood utilization using real‐time clinical decision support

Improved Hospital-Wide RBC Utilization Via Clinical Decision Support Is Associated With Stable Or Improving Patient Outcomes

Best practices for preventing malfunctions in rule-based clinical decision support alerts and reminders: Results of a Delphi study

To evaluate the capability of using generative artificial intelligence (AI) in summarizing alert comments and to determine if the AI-generated summary could be used to improve clinical decision support (CDS) alerts. We extracted user comments to alerts generated from September 1, 2022 to September 1, 2023 at Vanderbilt University Medical Center. For a subset of 8 alerts, comment summaries were generated independently by 2 physicians and then separately by GPT-4. We surveyed 5 CDS experts to rate the human-generated and AI-generated summaries on a scale from 1 (strongly disagree) to 5 (strongly agree) for the 4 metrics: clarity, completeness, accuracy, and usefulness. Five CDS experts participated in the survey. A total of 16 human-generated summaries and 8 AI-generated summaries were assessed. Among the top 8 rated summaries, five were generated by GPT-4. AI-generated summaries demonstrated high levels of clarity, accuracy, and usefulness, similar to the human-generated summaries. Moreover, AI-generated summaries exhibited significantly higher completeness and usefulness compared to the human-generated summaries (AI: 3.4 ± 1.2, human: 2.7 ± 1.2, P = .001). End-user comments provide clinicians' immediate feedback to CDS alerts and can serve as a direct and valuable data resource for improving CDS delivery. Traditionally, these comments may not be considered in the CDS review process due to their unstructured nature, large volume, and the presence of redundant or irrelevant content. Our study demonstrates that GPT-4 is capable of distilling these comments into summaries characterized by high clarity, accuracy, and completeness. AI-generated summaries are equivalent and potentially better than human-generated summaries. These AI-generated summaries could provide CDS experts with a novel means of reviewing user comments to rapidly optimize CDS alerts both online and offline.

Real-time clinical decision support (CDS) integrated with anesthesia information management systems (AIMS) can generate point of care reminders to improve quality of care. To develop, implement and evaluate a real-time clinical decision support system for anesthetic management of pediatric traumatic brain injury (TBI) patients undergoing urgent neurosurgery. We iteratively developed a CDS system for pediatric TBI patients undergoing urgent neurosurgery. The system automatically detects eligible cases and evidence-based key performance indicators (KPIs). Unwanted clinical events trigger and display real-time messages on the AIMS computer screen. Main outcomes were feasibility of detecting eligible cases and KPIs, and user acceptance. The CDS system was triggered in 22 out of 28 (79%) patients. The sensitivity of detecting continuously sampled KPIs reached 93.8%. For intermittently sampled KPIs, sensitivity and specificity reached 90.9% and 100%, respectively. 88% of providers reported that CDS helped with TBI anesthesia care. CDS implementation is feasible and acceptable with a high rate of case capture and appropriate generation of alert and guidance messages for TBI anesthesia care.

To determine if the implementation of automated clinical decision support (CDS) with embedded minor severe community-acquired pneumonia (sCAP) criteria was associated with improved ICU utilization among emergency department (ED) patients with pneumonia who did not require vasopressors or positive pressure ventilation at admission. Planned secondary analysis of a stepped-wedge, cluster-controlled CDS implementation trial. Sixteen hospitals in six geographic clusters from Intermountain Health; a large, integrated, nonprofit health system in Utah and Idaho. Adults admitted to the hospital from the ED with pneumonia identified by: 1) discharge International Classification of Diseases , 10th Revision codes for pneumonia or sepsis/respiratory failure and 2) ED chest imaging consistent with pneumonia, who did not require vasopressors or positive pressure ventilation at admission. After implementation, patients were exposed to automated, open-loop, comprehensive CDS that aided disposition decision (ward vs. ICU), based on objective severity scores (sCAP). The analysis included 2747 patients, 1814 before and 933 after implementation. The median age was 71, median Elixhauser index was 17, 48% were female, and 95% were Caucasian. A mixed-effects regression model with cluster as the random effect estimated that implementation of CDS utilizing sCAP increased 30-day ICU-free days by 1.04 days (95% CI, 0.48-1.59; p < 0.001). Among secondary outcomes, the odds of being admitted to the ward, transferring to the ICU within 72 hours, and receiving a critical therapy decreased by 57% (odds ratio [OR], 0.43; 95% CI, 0.26-0.68; p < 0.001) post-implementation; mortality within 72 hours of admission was unchanged (OR, 1.08; 95% CI, 0.56-2.01; p = 0.82) while 30-day all-cause mortality was lower post-implementation (OR, 0.71; 95% CI, 0.52-0.96; p = 0.03). Implementation of electronic CDS using minor sCAP criteria to guide disposition of patients with pneumonia from the ED was associated with safe reduction in ICU utilization.

Clinical Decision Support Tools

Clinical decision support (CDS) alerts are designed to work according to a set of clearly defined criteria and have the potential to improve clinical care. To efficiently and proactively review abnormally functioning CDS alerts, we postulate that the introduction of a dashboard with statistical process control (SPC) charting will lead to effective detection of erratic alert behavior. We identified custom CDS alerts from an academic medical center that were recorded and monitored in a longitudinal fashion and the data warehouses where this information was stored. We created a dashboard of alert frequency using SPC charts, applied SPC rules for classification of variation, and validated dashboard data. From June-August 2022, the dashboard effectively pulled in data to visually depict alert behavior. SPC-defined parameters for standard deviation from the mean were applied to visualizations and allowed for rapid review of alerts with greatest variation. These alerts were subsequently investigated, and it was determined that they were functioning correctly. The most profound abnormalities detected during implementation reflected changes in practice and not system errors, though further investigation into thresholds for statistical significance will benefit this field. We conclude that SPC visualizations are a time-efficient and effective method of identifying CDS malfunctions.

P2Y12 inhibitor selection involves numerous factors, including CYP2C19 genetics, since evidence demonstrates reduced clopidogrel efficacy in patients with decreased or no function CYP2C19 variants. In 2020, Indiana University health embedded interruptive clinical decision support (CDS) alerts in the electronic health record (EHR) to recommend alternative P2Y12 inhibitors for patients with decreased CYP2C19 function who had undergone percutaneous coronary intervention (PCI). The objective of this study was to evaluate prescriber response to these CDS alerts. Utilizing alert response data and P2Y12 inhibitor prescriptions from October 2020 to December 2023, we evaluated prescriber response for 362 patients who had a mean of 2.2 (SD: 1.7) CYP2C19-clopidogrel alerts fire post-PCI. Alert recommendations were accepted 24.5% ± 36.8% (mean ± SD) of the time. Alternative (i.e., non-clopidogrel) P2Y12 inhibitors were prescribed for 22.4% ± 36.8% of days during the year following PCI. Alerts were accepted more for CYP2C19 poor metabolizers than for intermediate metabolizers (P = 0.03). Each year after 2020 was associated with a 4.6% increase in the days prescribed alternative P2Y12 inhibitors. In contrast, increasing age was associated with decreased alert acceptance and decreased percentage of days prescribed alternatives, and concomitant oral anticoagulant use was associated with decreased percentage of days prescribed alternatives. Provider clinical judgment was the most common alert override reason, accounting for 68% of clinician responses. Our findings demonstrate that CYP2C19-clopidogrel CDS alerts promoted genotype-guided P2Y12 inhibitor prescribing in some cases (~22% of study days). Future research should better determine prescriber reasons for rejecting alert recommendations and establish best implementation practices to complement CDS alerts.

INTRODUCTION:We assessed the influence of a best practice alert (BPA) embedded within the electronic medical record on improving hepatitis C virus (HCV) birth-cohort screening by primary care physicians (PCPs).METHODS:Screening by 155 PCPs was monitored during 2 consecutive 9-month periods before and after implementation of the BPA. All tests were reviewed to differentiate true screening from other testing indications.RESULTS:Of 155 PCPs, 131 placed screening orders before and after BPA. Twenty-two PCPs started testing after BPA (P = 0.02). The number of tests placed and screening rates per PCP increased from 16 to 84 and from 3.3% to 13.2%, respectively (P < 0.0001). Before BPA, most PCPs rarely ordered screening HCV tests, whereas a small group of physicians generated most tests, indicative of an underlying power-law distribution. After the BPA, a new group of high-performing PCPs emerged, whose screening patterns were again characterized by a power-law distribution. However, pre-BPA test rates of individual PCPs were not predictive of their post-BPA rates. Overall, the introduction of the BPA narrowed the gap between low- and high-performing testers, indicating that modest increases in testing by a large number of low-performing PCPs could drive substantial improvement in program implementation.DISCUSSION:HCV birth-cohort screening by PCPs was shaped by an underlying power-law distribution. This distribution was preserved after the implementation of a BPA, although pre-BPA test rates were not predictive of post-BPA rates. Increases in test rates by high- and low-performing PCPs both contributed to the overall success of the BPA.

Does Clinical Decision Support Reduce Unwarranted Variation in Yield of CT Pulmonary Angiogram?

BackgroundThe ongoing Appalachian opioid epidemic has led to increasing hepatitis C virus (HCV) infections among people who inject drugs (PWID), and Human Immunodeficiency Virus (HIV) outbreaks have been observed. The primary aim of this study was to assess the potential increase in screening for HIV and HCV in an academic central Appalachian emergency department (ED) through the use of Best Practice Alerts (BPAs) in the electronic medical record (EMR). A secondary aim was to assess for an increase in linkage to care using patient navigators.MethodsEMR algorithms based on current Centers for Disease Control and Prevention HIV and HCV testing recommendations were created that triggered Best Practice Alerts (BPAs), giving providers a one-click acceptance option to order HIV and/or HCV testing. Placards were placed in care areas, informing patients of the availability of routine screening. Patient navigators facilitated linkage to care for seropositive patients.ResultsThe BPA appeared 58,936 times on 21,098 patients eligible for HIV screening and 24,319 times on 11,989 patients eligible for HCV screening over a one-year period. Of those, 7106 (33.7%) patients were screened for HIV and 3496 (29.2%) patients were screened for HCV, for an overall testing increase of 2269% and 1065% for HIV and HCV, respectively. Linkage to care increased by 15% for HIV to 100, and 14% for HCV to 64%.ConclusionHIV and HCV screening and linkage to care were increased in an academic ED setting in central Appalachia using EMR alerts. This approach could be utilized in multiple ambulatory settings. Increased testing and earlier linkage to care may help combat the current injection drug use-related HCV epidemic and avoid additional HIV outbreaks.

SummaryObjectives: Objective: Precision medicine uses individualized patient data, including genomic and social determinants of health SDoH), to provide optimized personalized patient treatment. In this scoping review, we summarize studies published in the last two years that reported on implementation of precision medicine in clinical decision support (CDS) related to precision medicine.Methods: We searched PubMed for manuscripts published in 2022 and 2023 to retrieve publications that included CDS and precision medicine keywords and Mesh terms. We reviewed the abstracts and full texts to apply the inclusion criteria that the study must have described the implementation of precision medicine related CDS within electronic health records. We extracted the domain, type of data used in CDS, target population included in the implementation from the final set of included manuscripts.Results: Our search retrieved 285 manuscripts and papers. Sixteen (16) papers met inclusion criteria after manual review of the full text. Eight of the reviewed papers studied the successful implementation of pharmacogenomics in CDS, four studies investigated the implementation of disease risk, and only one paper described the implementation of CDS integrating social determinants of health.Conclusion: Our scoping review of recent literature highlighted several findings. Pharmacogenomics is the most implemented precision medicine intervention based on published studies. Few reports describing disease risk and polygenic risk scores were found and no study addressed CDS for continuous biometric monitoring. Despite the increasing attention to social determinants of health as a key predictor of health outcomes, only one CDS incorporating SDoH have been publicly reported. Regular updates to scoping reviews can investigate barriers to implementation and identify solutions.

Despite their potential, Clinical Decision Support (CDS) systems often lack alignment with clinicians' needs and are underutilized in practice. Pilot implementations can help to improve the fit between systems and local needs by engaging users in real-world testing and refinement. Although pilot implementations of CDS have been reported, limited evidence has explored the factors contributing to pilot success.This study aimed to explore the opportunities and challenges associated with the pilot implementation of a CDS system that ultimately did not progress to full-scale implementation.We conducted interviews with clinicians, health service managers, and vendors involved in the pilot implementation and use of a mobile application-based CDS, and a dashboard-based CDS in two departments (Emergency and Patient Flow) of a rural Australian hospital. A semistructured interview guide was developed using the Non-adoption, Abandonment, Sustainability, Scale-up, and Spread (NASSS) framework. Interviews were audio-recorded, transcribed, and thematically analyzed.Analysis revealed four major themes: system performance and design, implementation processes, organizational support and resources, and perceived benefits of the CDS. The pilot implementation allowed for greater user input into the iterative design of CDS in practice, particularly in the Emergency Department (ED), where clinicians had both the capacity and willingness to engage. However, technical issues encountered early in the pilot deterred many users who did not re-engage even after issues were resolved. Although some users remained engaged, they became frustrated as organizational resource constraints meant that critical issues impacting the CDS's clinical utility went unresolved.Successful CDS pilots depend on the readiness of organizations, departments, and users to engage in pilot activities. Pilot implementations should be pursued in settings where users have both the capacity and willingness to participate in iterative feedback processes and where organizations have sufficient resources to address emerging needs.

Implementation of Best Practice Alert in an Electronic Medical Record to Limit Lower-Value Inpatient Echocardiograms

P3.11-08 Lung Cancer Screening at an Academic Medical Center: Early Patterns of Practice