Computer clinical decision support that automates personalized clinical care: a challenging but needed healthcare delivery strategy.

How to deliver best care in various clinical settings remains a vexing problem. All pertinent healthcare-related questions have not, cannot, and will not be addressable with costly time- and resource-consuming controlled clinical trials. At present, evidence-based guidelines can address only a small fraction of the types of care that clinicians deliver. Furthermore, underserved areas rarely can access state-of-the-art evidence-based guidelines in real-time, and often lack the wherewithal to implement advanced guidelines. Care providers in such settings frequently do not have sufficient training to undertake advanced guideline implementation. Nevertheless, in advanced modern healthcare delivery environments, use of eActions (validated clinical decision support systems) could help overcome the cognitive limitations of overburdened clinicians. Widespread use of eActions will require surmounting current healthcare technical and cultural barriers and installing clinical evidence/data curation systems. The authors expect that increased numbers of evidence-based guidelines will result from future comparative effectiveness clinical research carried out during routine healthcare delivery within learning healthcare systems.

Enabling a learning healthcare system with automated computer protocols that produce replicable and personalized clinician actions.

Clinical decision-making is based on knowledge, expertise, and authority, with clinicians approving almost every intervention-the starting point for delivery of "All the right care, but only the right care," an unachieved healthcare quality improvement goal. Unaided clinicians suffer from human cognitive limitations and biases when decisions are based only on their training, expertise, and experience. Electronic health records (EHRs) could improve healthcare with robust decision-support tools that reduce unwarranted variation of clinician decisions and actions. Current EHRs, focused on results review, documentation, and accounting, are awkward, time-consuming, and contribute to clinician stress and burnout. Decision-support tools could reduce clinician burden and enable replicable clinician decisions and actions that personalize patient care. Most current clinical decision-support tools or aids lack detail and neither reduce burden nor enable replicable actions. Clinicians must provide subjective interpretation and missing logic, thus introducing personal biases and mindless, unwarranted, variation from evidence-based practice. Replicability occurs when different clinicians, with the same patient information and context, come to the same decision and action. We propose a feasible subset of therapeutic decision-support tools based on credible clinical outcome evidence: computer protocols leading to replicable clinician actions (eActions). eActions enable different clinicians to make consistent decisions and actions when faced with the same patient input data. eActions embrace good everyday decision-making informed by evidence, experience, EHR data, and individual patient status. eActions can reduce unwarranted variation, increase quality of clinical care and research, reduce EHR noise, and could enable a learning healthcare system.

Clinician Perceptions of Timing and Presentation of Drug-Drug Interaction Alerts.

OBJECTIVE: Alert presentation of clinical decision support recommendations is a common method for providing information; however, many alerts are overridden suggesting presentation design improvements can be made. This study attempts to assess pediatric prescriber information needs for drug-drug interactions (DDIs) alerts and to evaluate the optimal presentation timing and presentation in the medication ordering process. METHODS: Six case scenarios presented interactions between medications used in pediatric specialties of general medicine, infectious disease, cardiology, and neurology. Timing varied to include alert interruption at medication selection versus order submission; or was noninterruptive. Interviews were audiotaped, transcribed, and independently analyzed to derive central themes. RESULTS: Fourteen trainee and attending clinicians trained in pediatrics, cardiology, and neurology participated. Coders derived 8 central themes from 929 quotes. Discordance exists between medication prescribing frequency and DDI knowledge; providers may commonly prescribe medications for which they do not recognize DDIs. Providers wanted alerts at medication selection rather than at order signature. Alert presentation themes included standardizing text, providing interaction-specific incidence/risk information, DDI rating scales, consolidating alerts, and providing alternative therapies. Providers want alerts to be actionable, for example, allowing medication discontinuation and color visual cues for essential information. Despite alert volume, participants did not "mind being reminded because there is always the chance that at that particular moment (they) do not remember it" and acknowledged the importance of alerts as "essential in terms of patient safety." CONCLUSION: Clinicians unanimously agreed on the importance of receiving DDI alerts to improve patient safety. The perceived alert value can be improved by incorporating clinician preferences for timing and presentation.

Community pharmacists' and residents' decision making and unmet information needs when completing comprehensive medication reviews.

OBJECTIVE: To (1) characterize community pharmacists' and community pharmacy residents' decision making and unmet information needs when conducting comprehensive medication reviews (CMRs) as part of medication therapy management and (2) explore any differences between community pharmacists and community pharmacy residents in CMR decision making and unmet information needs. DESIGN: Thirty-to 60-minute semistructured interviews framed using a clinical decision-making model (CDMM) were conducted with community pharmacists and residents. SETTING AND PARTICIPANTS: Participants were recruited from practice-based research networks and researchers' professional networks. Eligible participants had completed or supported the completion of at least 2 CMRs in the last 30 days. OUTCOME MEASURES: Two researchers independently coded transcripts using a combination of inductive and deductive methods to identify themes pertaining to community pharmacists' and residents' decision making and unmet information needs in the provision of CMRs. Discrepancies among researchers' initial coding decisions were resolved through discussion. RESULTS: Sixteen participants (8 pharmacists and 8 residents) were interviewed. Themes were mapped to 5 CDMM steps. Participants primarily used subjective information during "case familiarization"; objective information was secondary. Information used for "generating initial hypotheses" varied by medication therapy problem (MTP) type. During "case assessment," if information was not readily available, participants sought information from patients. Thus, patients' levels of self-management and health literacy influenced participants' ability to identify and resolve MTPs, as described under "identifying final hypotheses." Finally, participants described "decision-making barriers," including communication with prescribers to resolve MTPs. Although pharmacist and resident participants varied in the types of MTPs identified, both groups cited the use and need of similar information. CONCLUSION: Community pharmacists and residents often rely primarily on patient-provided information for decision making during CMRs because of unmet information needs, specifically, objective information. Moreover, confidence in MTP identification and resolution is reduced by communication challenges with prescribers and limitations in patients' ability to convey accurate and necessary information.

High-priority and low-priority drug-drug interactions in different international electronic health record systems: A comparative study.

OBJECTIVES: To investigate whether alert warnings for high-priority and low-priority drug-drug interactions (DDIs) were present in five international electronic health record (EHR) systems, to compare and contrast the severity level assigned to them, and to establish the proportion of alerts that were overridden. METHODS: We conducted a comparative, retrospective, multinational study using a convenience sample of 5 EHRs from the U.S., U.K., Republic of Korea and Belgium. RESULTS: Of the 15 previously defined, high-priority, class-based DDIs, alert warnings were found to exist for 11 in both the Korean and UK systems, 9 in the Belgian system, and all 15 in the two US systems. The specific combinations that were included in these class-based DDIs varied considerably in number, type and level of severity amongst systems. Alerts were only active for 8.4% (52/619) and 52.4% (111/212) of the specific drug-drug combinations contained in the Belgian and UK systems, respectively. Hard stops (not possible to override) existed in the US and UK systems only. The override rates for high-priority alerts requiring provider action ranged from 56.7% to 83.3%. Of the 33 previously defined low-priority DDIs, active alerts existed only in the US systems, for three class-based DDIs. The majority were non-interruptive. CONCLUSIONS: Alert warnings existed for most of the high-priority DDIs in the different EHRs but overriding them was easy in most of the systems. In addition to validating the high- and low-priority DDIs, this study reported a lack of standardization in DDI levels across different international knowledge bases.

Lost in Translation: No Effect of a High-Profile Publication on the Concomitant Use of Interacting Drugs.

We sought to assess whether a high-profile publication that demonstrated serious clinical consequences of specific drug-drug interactions (DDIs) reduced the concomitant use of those drugs. We conducted a quasi-experimental study using 2000-2008 prescription claims from a commercial health insurer to examine trends in the dispensing of the interacting drug pairs (angiotensin-converting enzyme inhibitors[ACEI] + potassium-sparing diuretic, digoxin + clarithromycin, and glyburide + cotrimoxazole) and control drug pairs previously reported in a top-tier general medicine journal. We examined prepublication and postpublication dispensing trends using Poisson regression. ACEI + potassium-sparing diuretic use did not differ postpublication vs. prepublication (P = 0.11). Digoxin + clarithromycin use decreased minimally postpublication vs. prepublication (relative rate = 0.9996: 95% confidence interval [CI] = 0.9993-0.9998). Glyburide + cotrimoxazole use increased minimally postpublication vs. prepublication (relative rate = 1.0220; 95% CI = 1.0187-1.0254). Therefore, the high-profile DDI publication had minimal to no measurable effect in reducing the concomitant use of the interacting drugs studied. We believe that better strategies are needed to translate knowledge about DDIs into clinical practice.

Analysis of variations in the display of drug names in computerized prescriber-order-entry systems.

PURPOSE: The variations in how drug names are displayed in computerized prescriber-order-entry (CPOE) systems were analyzed to determine their contribution to potential medication errors. METHODS: A diverse set of 10 inpatient and outpatient CPOE system vendors and self-developed CPOE systems in 6 U.S. healthcare institutions was evaluated. A team of pharmacists, physicians, patient-safety experts, and informatics experts created a CPOE assessment tool to standardize the assessment of CPOE features across the systems studied. Hypothetical scenarios were conducted with test patients to study the medication ordering workflow and ways in which medications were displayed in each system. Brand versus generic drug name ordering was studied at 1 large outpatient system to understand why prescribers ordered both brand and generic forms of the same drug. RESULTS: Widespread variations in the display of drug names were observed both within and across the 6 study sites and 10 systems, including the inconsistent display of brand and generic names. Some displayed drugs differently even on the same screen. Combination products were often displayed inconsistently, and some systems required prescribers to know the first drug listed in the combination in order for the correct product to appear in a search. It also appeared that prescribers may have prescribed both brand and generic forms of the same medication, creating the potential for drug duplication errors. CONCLUSION: A review of 10 CPOE systems revealed that medication names were displayed inconsistently, which can result in confusion or errors in reviewing, selecting, and ordering medications.

Recommendations for Providers on Person-Centered Approaches to Assess and Improve Medication Adherence.

Medication non-adherence is a significant clinical challenge that adversely affects psychosocial factors, costs, and outcomes that are shared by patients, family members, providers, healthcare systems, payers, and society. Patient-centered care (i.e., involving patients and their families in planning their health care) is increasingly emphasized as a promising approach for improving medication adherence, but clinician education around what this might look like in a busy primary care environment is lacking. We use a case study to demonstrate key skills such as motivational interviewing, counseling, and shared decision-making for clinicians interested in providing patient-centered care in efforts to improve medication adherence. Such patient-centered approaches hold considerable promise for addressing the high rates of non-adherence to medications for chronic conditions.

Recommendations to improve the usability of drug-drug interaction clinical decision support alerts.

OBJECTIVE: To establish preferred strategies for presenting drug-drug interaction (DDI) clinical decision support alerts. MATERIALS AND METHODS: A DDI Clinical Decision Support Conference Series included a workgroup consisting of 24 clinical, usability, and informatics experts representing academia, health information technology (IT) vendors, healthcare organizations, and the Office of the National Coordinator for Health IT. Workgroup members met via web-based meetings 12 times from January 2013 to February 2014, and two in-person meetings to reach consensus on recommendations to improve decision support for DDIs. We addressed three key questions: (1) what, how, where, and when do we display DDI decision support? (2) should presentation of DDI decision support vary by clinicians? and (3) how should effectiveness of DDI decision support be measured? RESULTS: Our recommendations include the consistent use of terminology, visual cues, minimal text, formatting, content, and reporting standards to facilitate usability. All clinicians involved in the medication use process should be able to view DDI alerts and actions by other clinicians. Override rates are common but may not be a good measure of effectiveness. DISCUSSION: Seven core elements should be included with DDI decision support. DDI information should be presented to all clinicians. Finally, in their current form, override rates have limited capability to evaluate alert effectiveness. CONCLUSION: DDI clinical decision support alerts need major improvements. We provide recommendations for healthcare organizations and IT vendors to improve the clinician interface of DDI alerts, with the aim of reducing alert fatigue and improving patient safety.

Impact of incorporating pharmacy claims data into electronic medication reconciliation.

PURPOSE: The potential value of adding pharmacy claims data to the medication history in the electronic health record (EHR) to improve the accuracy of medication reconciliation was studied. METHODS: Three medication history sources were used for this evaluation: a gold-standard preadmission medication list (PAML) created by reviewing all available medication history information, an EHR-generated PAML, and pharmacy claims data. The study population consisted of patients from the Partners Medication Reconciliation Study with medication history information available from all three medication history sources. The aggregated medication list from each medication history source was compared with the gold-standard PAML to identify and categorize missing medications, additional medications, and discrepancies in the various attributes of a medication order, including dose, route, and frequency. McNemar's test was used to compare paired proportions of medication entries across each source to the gold-standard PAMLs. RESULTS: Fifteen patients had medication histories in all three medication history sources. Medication entries across all three sources included 169 from the gold- standard PAMLs, 158 from the EHR-PAMLs, and 351 from pharmacy claims data. The EHR-PAMLs and pharmacy claims data correctly reflected 52.1% and 43.2% of the gold-standard PAMLs, respectively. Combining the EHR-PAMLs and pharmacy claims resulted in 69.2% of the gold-standard PAMLs correctly reflected (p < 0.0001). Combining these two data sources increased the accuracy of medication history by 17.1%. CONCLUSION: Combining the EHR-PAML and pharmacy claims data resulted in a significant increase in the number of medications correctly reflected in the gold-standard PAML compared with the EHR-PAML or claims data separately.

Patient-centered priorities for improving medication management and adherence.

OBJECTIVE: The Centers for Education and Research on Therapeutics convened a workshop to examine the scientific evidence on medication adherence interventions from the patient-centered perspective and to explore the potential of patient-centered medication management to improve chronic disease treatment. METHODS: Patients, providers, researchers, and other stakeholders (N = 28) identified and prioritized ideas for future research and practice. We analyzed stakeholder voting on priorities and reviewed themes in workshop discussions. RESULTS: Ten priority areas emerged. Three areas were highly rated by all stakeholder groups: creating tools and systems to facilitate and evaluate patient-centered medication management plans; developing training on patient-centered prescribing for providers; and increasing patients' knowledge about medication management. However, priorities differed across stakeholder groups. Notably, patients prioritized using peer support to improve medication management while researchers did not. CONCLUSION: Engaging multiple stakeholders in setting a patient-centered research agenda and broadening the scope of adherence interventions to include other aspects of medication management resulted in priorities outside the traditional scope of adherence research. PRACTICE IMPLICATIONS: Workshop participants recognized the potential benefits of patient-centered medication management but also identified many challenges to implementation that require additional research and innovation.

Patient-centered interventions to improve medication management and adherence: a qualitative review of research findings.

OBJECTIVE: Patient-centered approaches to improving medication adherence hold promise, but evidence of their effectiveness is unclear. This review reports the current state of scientific research around interventions to improve medication management through four patient-centered domains: shared decision-making, methods to enhance effective prescribing, systems for eliciting and acting on patient feedback about medication use and treatment goals, and medication-taking behavior. METHODS: We reviewed literature on interventions that fell into these domains and were published between January 2007 and May 2013. Two reviewers abstracted information and categorized studies by intervention type. RESULTS: We identified 60 studies, of which 40% focused on patient education. Other intervention types included augmented pharmacy services, decision aids, shared decision-making, and clinical review of patient adherence. Medication adherence was an outcome in most (70%) of the studies, although 50% also examined patient-centered outcomes. CONCLUSIONS: We identified a large number of medication management interventions that incorporated patient-centered care and improved patient outcomes. We were unable to determine whether these interventions are more effective than traditional medication adherence interventions. PRACTICE IMPLICATIONS: Additional research is needed to identify effective and feasible approaches to incorporate patient-centeredness into the medication management processes of the current health care system, if appropriate.

Evaluation of medication alerts in electronic health records for compliance with human factors principles.

INTRODUCTION: Increasing the adoption of electronic health records (EHRs) with integrated clinical decision support (CDS) is a key initiative of the current US healthcare administration. High over-ride rates of CDS alerts strongly limit these potential benefits. As a result, EHR designers aspire to improve alert design to achieve better acceptance rates. In this study, we evaluated drug-drug interaction (DDI) alerts generated in EHRs and compared them for compliance with human factors principles. METHODS: We utilized a previously validated questionnaire, the I-MeDeSA, to assess compliance with nine human factors principles of DDI alerts generated in 14 EHRs. Two reviewers independently assigned scores evaluating the human factors characteristics of each EHR. Rankings were assigned based on these scores and recommendations for appropriate alert design were derived. RESULTS: The 14 EHRs evaluated in this study received scores ranging from 8 to 18.33, with a maximum possible score of 26. Cohen's κ (κ=0.86) reflected excellent agreement among reviewers. The six vendor products tied for second and third place rankings, while the top system and bottom five systems were home-grown products. The most common weaknesses included the absence of characteristics such as alert prioritization, clear and concise alert messages indicating interacting drugs, actions for clinical management, and a statement indicating the consequences of over-riding the alert. CONCLUSIONS: We provided detailed analyses of the human factors principles which were assessed and described our recommendations for effective alert design. Future studies should assess whether adherence to these recommendations can improve alert acceptance.

Human factors considerations for contraindication alerts.

Alert fatigue is a ubiquitous problem in clinical decision support systems. Several remedies to alert fatigue have been proposed including improving the specificity of alerts and compliance with human factors principles. Human factors principles that are relevant for drug safety alerting have been identified and operationalized for drug-drug interactions (DDIs), resulting in a previously developed and validated quantitative instrument. Such an instrument is lacking for contraindications. This study describes the operationalization of human factors principles for contraindication alerting. Thirty items associated with 10 human factors principles are included in the instrument: 4 items are new, 5 are similar, and 21 are equal to the DDI-instrument. The instrument was further operationalized to a test protocol. Three independent persons used the test protocol. Inter-rater reliability indicated moderate agreement (κ=0.540) It is feasible to test the implementation of human factors in contraindication alert design with the newly developed instrument.

Criteria for assessing high-priority drug-drug interactions for clinical decision support in electronic health records.

BACKGROUND: High override rates for drug-drug interaction (DDI) alerts in electronic health records (EHRs) result in the potentially dangerous consequence of providers ignoring clinically significant alerts. Lack of uniformity of criteria for determining the severity or validity of these interactions often results in discrepancies in how these are evaluated. The purpose of this study was to identify a set of criteria for assessing DDIs that should be used for the generation of clinical decision support (CDS) alerts in EHRs. METHODS: We conducted a 20-year systematic literature review of MEDLINE and EMBASE to identify characteristics of high-priority DDIs. These criteria were validated by an expert panel consisting of medication knowledge base vendors, EHR vendors, in-house knowledge base developers from academic medical centers, and both federal and private agencies involved in the regulation of medication use. RESULTS: Forty-four articles met the inclusion criteria for assessing characteristics of high-priority DDIs. The panel considered five criteria to be most important when assessing an interaction- Severity, Probability, Clinical Implications of the interaction, Patient characteristics, and the Evidence supporting the interaction. In addition, the panel identified barriers and considerations for being able to utilize these criteria in medication knowledge bases used by EHRs. CONCLUSIONS: A multi-dimensional approach is needed to understanding the importance of an interaction for inclusion in medication knowledge bases for the purpose of CDS alerting. The criteria identified in this study can serve as a first step towards a uniform approach in assessing which interactions are critical and warrant interruption of a provider's workflow.

Design of decision support interventions for medication prescribing.

OBJECTIVE: Describe optimal design attributes of clinical decision support (CDS) interventions for medication prescribing, emphasizing perceptual, cognitive and functional characteristics that improve human-computer interaction (HCI) and patient safety. METHODS: Findings from published reports on success, failures and lessons learned during implementation of CDS systems were reviewed and interpreted with regard to HCI and software usability principles. We then formulated design recommendations for CDS alerts that would reduce unnecessary workflow interruptions and allow clinicians to make informed decisions quickly, accurately and without extraneous cognitive and interactive effort. RESULTS: Excessive alerting that tends to distract clinicians rather than provide effective CDS can be reduced by designing only high severity alerts as interruptive dialog boxes and less severe warnings without explicit response requirement, by curating system knowledge bases to suppress warnings with low clinical utility and by integrating contextual patient data into the decision logic. Recommended design principles include parsimonious and consistent use of color and language, minimalist approach to the layout of information and controls, the use of font attributes to convey hierarchy and visual prominence of important data over supporting information, the inclusion of relevant patient data in the context of the alert and allowing clinicians to respond with one or two clicks. CONCLUSION: Although HCI and usability principles are well established and robust, CDS and EHR system interfaces rarely conform to the best known design conventions and are seldom conceived and designed well enough to be truly versatile and dependable tools. These relatively novel interventions still require careful monitoring, research and analysis of its track record to mature. Clarity and specificity of alert content and optimal perceptual and cognitive attributes, for example, are essential for providing effective decision support to clinicians.

Drug-drug interactions that should be non-interruptive in order to reduce alert fatigue in electronic health records.

OBJECTIVE: Alert fatigue represents a common problem associated with the use of clinical decision support systems in electronic health records (EHR). This problem is particularly profound with drug-drug interaction (DDI) alerts for which studies have reported override rates of approximately 90%. The objective of this study is to report consensus-based recommendations of an expert panel on DDI that can be safely made non-interruptive to the provider's workflow, in EHR, in an attempt to reduce alert fatigue. METHODS: We utilized an expert panel process to rate the interactions. Panelists had expertise in medicine, pharmacy, pharmacology and clinical informatics, and represented both academic institutions and vendors of medication knowledge bases and EHR. In addition, representatives from the US Food and Drug Administration and the American Society of Health-System Pharmacy contributed to the discussions. RESULTS: Recommendations and considerations of the panel resulted in the creation of a list of 33 class-based low-priority DDI that do not warrant being interruptive alerts in EHR. In one institution, these accounted for 36% of the interactions displayed. DISCUSSION: Development and customization of the content of medication knowledge bases that drive DDI alerting represents a resource-intensive task. Creation of a standardized list of low-priority DDI may help reduce alert fatigue across EHR. CONCLUSIONS: Future efforts might include the development of a consortium to maintain this list over time. Such a list could also be used in conjunction with financial incentives tied to its adoption in EHR.

High-priority drug-drug interactions for use in electronic health records.

OBJECTIVE: To develop a set of high-severity, clinically significant drug-drug interactions (DDIs) for use in electronic health records (EHRs). METHODS: A panel of experts was convened with the goal of identifying critical DDIs that should be used for generating medication-related decision support alerts in all EHRs. Panelists included medication knowledge base vendors, EHR vendors, in-house knowledge base developers from academic medical centers, and both federal and private agencies involved in the regulation of medication use. Candidate DDIs were assessed by the panel based on the consequence of the interaction, severity levels assigned to them across various medication knowledge bases, availability of therapeutic alternatives, monitoring/management options, predisposing factors, and the probability of the interaction based on the strength of evidence available in the literature. RESULTS: Of 31 DDIs considered to be high risk, the panel approved a final list of 15 interactions. Panelists agreed that this list represented drugs that are contraindicated for concurrent use, though it does not necessarily represent a complete list of all such interacting drug pairs. For other drug interactions, severity may depend on additional factors, such as patient conditions or timing of co-administration. DISCUSSION: The panel provided recommendations on the creation, maintenance, and implementation of a central repository of high severity interactions. CONCLUSIONS: A set of highly clinically significant drug-drug interactions was identified, for which warnings should be generated in all EHRs. The panel highlighted the complexity of issues surrounding development and implementation of such a list.

Preventability of adverse drug events involving multiple drugs using publicly available clinical decision support tools.

PURPOSE: The results of a retrospective evaluation of the frequency and preventability of adverse drug events (ADEs) involving multiple drugs among hospital inpatients are reported. METHODS: Data collected in a previous cohort study of 180 actual ADEs and 552 potential ADEs (PADEs) at six community hospitals in Massachusetts were analyzed to determine the frequency and types of multiple-drug ADEs and the extent to which the ADEs might have been prevented using publicly available clinical decision-support (CDS) knowledge bases. None of the hospitals had a computerized prescriber-order-entry system at the time of data collection (January 2005-August 2006). RESULTS: A total of 17 ADEs (rate, 1.4 per 100 admissions) and 146 PADEs (rate, 12.2 per 100 admissions) involving multiple drugs were identified. The documented events were related to drug duplication (n = 126), drug-drug interaction (n = 21), additive effects (n = 14), and therapeutic duplication (n = 7) or a combination of those factors. The majority of actual ADEs were due to drug-drug interactions, most commonly involving opioids, benzodiazepines, or cardiac medications; about 75% of the PADEs involved excessive drug doses resulting from order duplication or the prescribing of combination drugs with overlapping ingredients, usually products containing acetaminophen and an opioid. It was determined that 5 (29.4%) of the ADEs and 131 (89.7%) of the PADEs could have been detected through the use of the evaluated CDS tools. CONCLUSION: A substantial number of actual ADEs and PADEs in the community hospital setting may be preventable through the use of publicly available CDS knowledge bases.