Building and maintaining trust in clinical decision support: Recommendations from the Patient-Centered CDS Learning Network.

Knowledge artifacts in digital repositories for clinical decision support (CDS) can promote the use of CDS in clinical practice. However, stakeholders will benefit from knowing which they can trust before adopting artifacts from knowledge repositories. We discuss our investigation into trust for knowledge artifacts and repositories by the Patient-Centered CDS Learning Network's Trust Framework Working Group (TFWG). The TFWG identified 12 actors (eg, vendors, clinicians, and policy makers) within a CDS ecosystem who each may play a meaningful role in prioritizing, authoring, implementing, or evaluating CDS and developed 33 recommendations distributed across nine "trust attributes." The trust attributes and recommendations represent a range of considerations such as the "Competency" of knowledge artifact engineers and the "Organizational Capacity" of institutions that develop and implement CDS. The TFWG findings highlight an initial effort to make trust explicit and embedded within CDS knowledge artifacts and repositories and thus more broadly accepted and used.

Use of Health Information Technology among Patient Navigators in Community Health Interventions.

Overview: As chronic disease and comorbidities increase, so does the complexity of patient care.This complexity requires interdisciplinary care teams and multifactor interventions to ensure that patients get the most efficient care. Patient navigators-defined as individuals who help patients move through the complex care continuum-can improve access to care and patient engagement, which can translate into better outcomes. Health information technology (health IT) can support timely communication and information sharing for patient navigators and the providers with whom they interact to better coordinate care. We explored the health IT that patient navigators used, how they used it, and their health IT needs in community-based interventions. Methods: We analyzed three years of qualitative program evaluation data captured though progress reports, site visits, and telephone interviews as part of a larger evaluation of community-based demonstration projects. We used inductive analysis to identify preliminary themes to develop a codebook. Using QSR International's NVivo qualitative analysis software (version 11.0), we then used the preliminary themes in a second round of independent coding. We identified themes relevant to navigators and to barriers and facilitators for health IT. Coders achieved a final kappa of 0.8, suggesting excellent interrater reliability. Results: Navigators used various types of health IT (e.g., health information exchanges, electronic health records, short message service) to capture and share information with the rest of the care team. Navigators used technology to document patient information, track services, and schedule appointments for patients; however, some respondents reported challenges with systems that were not integrated. Navigators must learn to use health IT systems of varying complexity to complete their job duties. Discussion: Health IT can improve workflow by facilitating task organization and communication with the care team. Ultimately, integrating the health IT systems used by navigators with those used by other care team members was most beneficial. Because of the various types of health IT used, patient navigators should receive training to ensure that they have the technical skills to use these systems efficiently and reduce duplication of effort. Conclusion: Managing the care of patients with chronic disease requires comprehensive care teams, which can include patient navigators. Integrating navigators' documentation into other health IT systems can keep providers updated on information while patients are outside of the providers' care. With the growth of health IT use in recent years, technical skills are becoming increasingly important. These findings can help leaders who are planning complex health interventions involving navigators to ensure that technology is used efficiently to support coordination and allow navigators to reach more patients.

A qualitative framework-based evaluation of radiology clinical decision support initiatives: eliciting key factors to physician adoption in implementation.

OBJECTIVES: To illustrate key contextual factors that may have effects on clinical decision support (CDS) adoption and, ultimately, success. MATERIALS AND METHODS: We conducted a qualitative evaluation of 2 similar radiology CDS innovations for near-term endpoints affecting adoption and present the findings using an evaluation framework. We identified key contextual factors between these 2 innovations and determined important adoption differences between them. RESULTS: Degree of electronic health record integration, approach to education and training, key drivers of adoption, and tailoring of the CDS to the clinical context were handled differently between the 2 innovations, contributing to variation in their relative degrees of adoption and use. Attention to these factors had impacts on both near and later-term measures of success (eg, patient outcomes). DISCUSSION: CDS adoption is a well-studied early-term measure of CDS success that directly impacts outcomes. Adoption requires attention throughout the design phases of an intervention especially to key factors directly affecting it, including how implementation across multiple sites and systems complicates adoption, which prior experience with CDS matters, and that practice guidelines invariably require tailoring to the clinical context. CONCLUSION: With better planning for the capture of early-term measures of successful CDS implementation, especially adoption, critical adjustments may be made to ensure that the CDS is effectively implemented to be successful.

Barriers, Facilitators, and Potential Solutions to Advancing Interoperable Clinical Decision Support: Multi-Stakeholder Consensus Recommendations for the Opioid Use Case.

With the advent of interoperability standards such as FHIR, SMART, CDS Hooks, and CQL, interoperable clinical decision support (CDS) holds great promise for improving healthcare. In 2018, the Agency for Healthcare Research and Quality (AHRQ)-sponsored Patient-Centered CDS Learning Network (PCCDS LN) chartered a Technical Framework Working Group (TechFWG) to identify barriers, facilitators, and potential solutions for interoperable CDS, with a specific focus on addressing the opioid epidemic. Through an open, multi-stakeholder process that engaged 54 representatives from healthcare, industry, and academia, the TechFWG identified barriers in 6 categories: regulatory environment, data integration, scalability, business case, effective and useful CDS, and care planning and coordination. Facilitators and key recommendations were also identified for overcoming these barriers. The key insights were also extrapolated to CDS-facilitated care improvement outside of the specific opioid use case. If applied broadly, the recommendations should help advance the availability and impact of interoperable CDS delivered at scale.

The Imperative for Patient-Centered Clinical Decision Support.

This commentary introduces the Patient-Centered Clinical Decision Support (PCCDS) Learning Network, which is collaborating with AcademyHealth to publish "Better Decisions Together" as part of eGEMs. Patient-centered clinical decision support (CDS) is an important vehicle to address broad issues in the U.S. health care system regarding quality and safety while also achieving better outcomes and better patient and provider satisfaction. Defined as CDS that supports individual patients and their care givers and/or care teams in health-related decisions and actions, PCCDS is an important step forward in advancing endeavors to move patient-centered care forward. The PCCDS Learning Network has developed a framework, referred to as the Analytic Framework for Action (AFA), to organize thinking and activities around PCCDS. A wide array of activities the PCCDS Learning Network is engaging in to inform and connect stakeholders is discussed.

Improving acceptance of computerized prescribing alerts in ambulatory care.

Computerized drug prescribing alerts can improve patient safety, but are often overridden because of poor specificity and alert overload. Our objective was to improve clinician acceptance of drug alerts by designing a selective set of drug alerts for the ambulatory care setting and minimizing workflow disruptions by designating only critical to high-severity alerts to be interruptive to clinician workflow. The alerts were presented to clinicians using computerized prescribing within an electronic medical record in 31 Boston-area practices. There were 18,115 drug alerts generated during our six-month study period. Of these, 12,933 (71%) were noninterruptive and 5,182 (29%) interruptive. Of the 5,182 interruptive alerts, 67% were accepted. Reasons for overrides varied for each drug alert category and provided potentially useful information for future alert improvement. These data suggest that it is possible to design computerized prescribing decision support with high rates of alert recommendation acceptance by clinicians.

Design and implementation of an application and associated services to support interdisciplinary medication reconciliation efforts at an integrated healthcare delivery network.

Confusion about patients' medication regimens during the hospital admission and discharge process accounts for many preventable and serious medication errors. Many organizations have begun to redesign their clinical processes to address this patient safety concern. Partners HealthCare, an integrated delivery network in Boston, Massachusetts, has answered this interdisciplinary challenge by leveraging its multiple outpatient electronic medical records (EMR) and inpatient computerized provider order entry (CPOE) systems to facilitate the process of medication reconciliation. This manuscript describes the design of a novel application and the associated services that aggregate medication data from EMR and CPOE systems so that clinicians can efficiently generate an accurate pre-admission medication list. Information collected with the use of this application subsequently supports the writing of admission and discharge orders by physicians, performance of admission assessment by nurses, and reconciliation of inpatient orders by pharmacists. Results from early pilot testing suggest that this new medication reconciliation process is well accepted by clinicians and has significant potential to prevent medication errors during transitions of care.

Evaluation of a commercial rule engine as a basis for a clinical decision support service.

Current implementation techniques constrain our ability to rapidly deploy and augment clinical decision support systems at Partners Healthcare Systems. We report on the use of a commercially-available rule engine system-iLog Rules-as the basis for a series of prototypes typifying Partners decision support applications. For three prototypical systems, we successfully decoupled the decision support component from application and support logic, and reimplemented that component using iLog. We found that the rule engine itself provides high-performance execution for the small rulesets we evaluated, and that overall application performance was found to be generally acceptable. We note that the major bottleneck to application performance is the ability to rapidly deliver patient data to the rule engine for execution. Future investigation will focus on abstracting features from each of the prototypes and incorporating them into a scalable and reusable decision support service architecture.

Improving override rates for computerized prescribing alerts in ambulatory care.

Computerized drug prescribing alerts can improve patient safety, but are often overridden because of poor specificity and alert overload. We developed a selective knowledge base of only clinically significant drug alerts and designated only critical-high severity alerts to be interruptive to clinician workflow (a tiered approach). Using this approach, we were able to achieve a 67% clinician accept rate for ambulatory computerized prescribing alerts.

Designing an electronic medication reconciliation system.

Unintended medication discrepancies at hospital admission and discharge potentially harm patients. Explicit medication reconciliation (MR) can prevent unintended discrepancies among care settings and is mandated by JCAHO for 2005. Enterprise-wide, we are linking pre-admission and discharge medication lists in our outpatient electronic health records (EHR) with our inpatient order entry applications (OE) - currently not interoperable - to support MR and inform the development of comprehensive MR among hospitalized patients.

Enterprise-wide drug-drug interaction alerting system.

According to the Institute of Medicine's (IOM) 1999 report To Err is Human: Building a safer Health System, "medical errors kill some 44,000-98,0001 people in U.S. hospitals each year. Partners HealthCare System (PHS) is a large integrated delivery network in Boston, MA, which has as a goal improving patient care by preventing adverse drug events (ADE) and reducing medication errors enterprise-wide. PHS has developed a drug-drug Interaction (DDI) detection feature, for the suite of clinical applications currently used by its two major teaching institutions, Brigham & Women's Hospital (BWH) and Mass General Hospital (MGH). The following clinical applications will be using this drug-drug interaction feature: NICU Order Entry (OE) at BWH, MGH OE for pediatrics and adults, the Partners outpatient medical record, The LMR, and BICS OE at BWH.

End of visit: design considerations for an ambulatory order entry module.

Current paper-based processes for performing billing documentation and test ordering at the end of a clinic visit are fraught with problems, resulting in numerous workflow inefficiencies and significant revenue losses for a healthcare organization. Paper forms are often filled out inaccurately or incompletely, or can be misrouted or lost. Computerizing these processes can alleviate many of these problems. We are building a new module for our ambulatory electronic medical record system to automate these "end of visit" (EOV) activities, which includes completing encounter forms, ordering lab and diagnostic tests, and printing patient visit summaries. An EOV module must be carefully designed to incorporate the needs of clinicians, front office staff, ancillary labs, medical records, and finance departments. An optimally designed EOV system should be customizable to fit into the clinician's workflow, and should help reduce financial losses, improve clinical documentation, and reduce workflow inefficiencies.

Creating an enterprise-wide allergy repository at Partners HealthCare System.

A significant fraction of medication errors and preventable adverse drug events are related to drug-allergy interactions (DAIs). Computerized prescribing can help prevent DAIs, but an accurate record of the patient's allergies is required. At Partners HealthCare System in Boston, the patient's allergy list is distributed across several applications including computer physician order entry (CPOE), the outpatient medical record, pharmacy applications, and nurse charting applications. Currently, each application has access only to its own allergy data. This paper presents details of a project designed to integrate the various allergy repositories at Partners. We present data documenting that patients have allergy data stored in multiple repositories. We give detail about issues we are encountering such as which applications should participate in the repository, whether "NKA" or "NKDA" should be used to document known absence of allergies, and which personnel should be allowed to enter allergies. The issues described in this paper may well be faced by other initiatives intended to create comprehensive allergy repositories.