Robert A. Jenders

Clinical Decision Support in Electronic Prescribing: Recommendations and an Action Plan Report of the Joint Clinical Decision Support Workgroup

Clinical decision support (CDS) in electronic prescribing (eRx) systems can improve the safety, quality, efficiency, and cost-effectiveness of care. However, at present, these potential benefits have not been fully realized. In this consensus white paper, we set forth recommendations and action plans in three critical domains: (1) advances in system capabilities, including basic and advanced sets of CDS interventions and knowledge, supporting database elements, operational features to improve usability and measure performance, and management and governance structures; (2) uniform standards, vocabularies, and centralized knowledge structures and services that could reduce rework by vendors and care providers, improve dissemination of well-constructed CDS interventions, promote generally applicable research in CDS methods, and accelerate the movement of new medical knowledge from research to practice; and (3) appropriate financial and legal incentives to promote adoption.

A systematic literature review of automated clinical coding and classification systems

Clinical coding and classification processes transform natural language descriptions in clinical text into data that can subsequently be used for clinical care, research, and other purposes. This systematic literature review examined studies that evaluated all types of automated coding and classification systems to determine the performance of such systems. Studies indexed in Medline or other relevant databases prior to March 2009 were considered. The 113 studies included in this review show that automated tools exist for a variety of coding and classification purposes, focus on various healthcare specialties, and handle a wide variety of clinical document types. Automated coding and classification systems themselves are not generalizable, nor are the results of the studies evaluating them. Published research shows these systems hold promise, but these data must be considered in context, with performance relative to the complexity of the task and the desired outcome.

Clinical Decision Support Systems

Integrating medical knowledge and advances into the clinical setting is often difficult due to the complexity of the involved algorithms and protocols. Clinical decision support systems (CDSS) assist the clinician in applying new information to patient care through the analysis of patient-specific clinical variables. Many of these systems are used to enhance diagnostic efforts and include computer-based programs such as DxplainTM that provide extensive differential diagnoses based on clinical information entered by the clinician. Other forms of clinical decision support systems, including antibiotic management programs and anticoagulation dosing calculators, seek to prevent medical errors and improve patient safety.

The computer-based clinical record--where do we stand?

The practice of medicine depends on how we record, process, retrieve, and communicate information. Physicians are often frustrated with the inadequacies and duplication of the existing paper-based medical record and with the time wasted in locating medical information. The recognition of the need for more comprehensive and available documentation of patient care is not new. In her 1863 book Notes on a Hospital, Florence Nightingale wrote, In attempting to arrive at the truth, I have applied everywhere for information, but in scarcely an instance have I been able to obtain hospital records fit for any purposes of comparison. If they could be obtained they would show subscribers how their money was being spent, what amount of good was really being done with it, or whether the money was not doing mischief rather than good [1]. The need to improve the management of medical information is more critical now because of the explosion of medical knowledge and because of the need to provide comprehensive documentation of patient care for an ever-growing list of interested parties [2]. The article by van der Lei and colleagues in this issue of Annals [3], which describes the introduction of computer-based records in the Netherlands, is encouraging. The authors report that more than one fourth of the 6400 Dutch general practitioners have instituted a computer-based clinical record system in their offices. We discuss the status and issues involved with the use of computer-based records in the United States in the context of the Dutch experience. The diverse and heterogenous patterns of care and the various medical provider and institutional environments characteristic of U.S. health care have resulted in a fragmented patient medical record, with no single provider, institution, or third-party payer responsible for maintaining a comprehensive record. Consequently, the major thrust of the successful computer-supported medical information systems in the United States has been to support the financial, administrative, and communication functions of individual institutions. The primary emphasis of these computer systems has not been the clinical record but functions such as billing, admission and discharge, scheduling, and laboratory reporting. Some systems have incorporated the retrieval of previously transcribed clinical data such as radiology reports, discharge summaries, problem lists, and visit notes. Once stored in the computer-based clinical record system, the data can be viewed simultaneously by multiple persons at different sites. Impressive examples of such systems are in place both in U.S. hospitals [4-7] and in some ambulatory practices [4, 7-10]. For example, several hundred ambulatory care sites use COSTAR, a public domain computer-based ambulatory medical record system developed at Massachusetts General Hospital [8, 9]. In COSTAR, the medical data for a patient visit are recorded on a paper-based encounter form and then transcribed into the computer system by clerical personnel. Other examples of computer-based systems include the electronic record developed at the Regenstrief Institute at Indiana University [4], where a clinician can view a patients problem list and laboratory data interactively as flowsheets, allowing easier detection of trends. An ambulatory computer-based record at Bostons Brigham and Womens Hospital [10] also provides a summary screen displaying a patient-at-a-glance with a problem list, allergies, and medications. In these systems, like many similar systems, the patient information is accessed either through direct inquiry at a computer terminal or through computer-generated summaries and reports. A major impediment to the development of a computer-based clinical record system has been the lack of agreement in standards both for the clinical terminology to be used and for the computer technology. The American Society for Testing and Materials (ASTM) recently promulgated a standard to describe the content and structure of a computer-based system [11], but it is not widely reflected in currently used systems. A consortium of vendors and hospitals, Health Level Seven, is developing standards for transmitting billing; admission, discharge, and transfer; order entry; and the reporting of results between a network of computers [12]. Health Level Seven collaborates closely with ASTM and has defined a standard for the protocol to be used in the communication of laboratory data in an electronic format; this standard has been adopted by many vendors. The absence of standards for the other sections of the clinical record and the lack of support for standards by the government and professional organizations has resulted in the use of many competing computer operating systems, hardware platforms, user interfaces, and software tools, making every computer-based record system implementation almost hopelessly proprietary. Little attention has been focused on establishing a standard for a system with an open architecture, a standard that would allow computer hardware and software products of many different manufacturers to function together. Given the diversity of computer technology, such an open architecture will be essential for the dissemination and national adoption of a common computer-based system. The successful development of the automated medical record in the Dutch system is based largely on the countrys progress in four crucial areas [9, 13, 14]. These are the development of a standard clinical vocabulary, effective methods for direct physician interaction with the computer-based system, support of key professional societies, and judicious use of government funding. Standard Clinical Vocabulary One clear advantage of computer-based medical records is that clinical information can be retrieved almost instantaneously and simultaneously from many different sites. Simply recording and storing the medical information in a narrative format in a computer system would accomplish this and would improve the legibility of previously handwritten notes. However, using the computer as nothing more than a large word-processing program would make analysis of the nature, extent, and time-course of the disease processes, therapies, and outcomes difficult and time consuming. Without a more structured method of data collection using a standard controlled vocabulary, it will be impossible to make rational decisions about which treatments are cost-effective and how patient outcomes are affected by our clinical decisions. A controlled vocabulary implies a standard set of common terms (including accepted synonyms and abbreviations) for recording clinical information. A controlled vocabulary would allow the computer to search and sort data quickly, summarize the information (for example, the active problems and active medications), identify important clinical manifestations (such as a drug allergy), and retrieve selectively (for example, the last visit note discussing the problem of congestive heart failure). In addition, a structured clinical record with a controlled vocabulary would enable the computer to identify and retrieve relevant medical knowledge (such as the contraindications of a particular drug), to provide problem-specific guidelines, to alert the provider to the need for indicated preventive medicine interventions, and to highlight an anomalous test result. Most commercial medical record systems (as well as the Elias system described in the article by van der Lei and colleagues) do not require a controlled vocabulary. The development and national adoption of a controlled vocabulary is a prerequisite for a computer-based clinical record to achieve its full potential [15]. Direct Physician Interaction with the Computer System For maximum effectiveness, the computer-based record system must completely replace the paper record, and the clinician responsible must interact directly with the computer to enter and retrieve medical information. This would reduce transcription errors as well as personnel costs and minimize delay in the availability of clinical information. An additional advantage of direct physician use of the computer-based system would be the provision of reminders and warnings when a clinical decision is being made. For example, a physician writing a prescription interactively can be warned of an adverse drugdrug interaction before the medication is given to the patient and possible harm ensues. This capability, which cannot be provided in a paper-based record, is a key advantage of a computer-based record and is supported by some hospital information systems in the United States. Changing from narrative text recording (either written or dictated) to interacting with a computer requires modification of longstanding traditions of medical recordkeeping. Although many medical students and young physicians have extensive experience using computer technology, there is little continuation of this in their training years. In addition, many older physicians, unfamiliar with the technology, are reluctant to enter data directly into the computer. Again, it is encouraging to note the progress toward this goal in the Dutch system. System designers continue to improve computer interfaces to permit rapid direct entry of narrative data into the computer while still maintaining the flexibility of the dictated note. For example, PEN&PAD, a prototype workstation being developed at the University of Manchester [16] in the United Kingdom, uses a graphic interface, user-defined templates for common clinical problems, and point-and-click technology to permit the user to enter rapidly a description of a patients symptoms and physical findings. In another example, interactive encoding of diagnoses by physicians has been a part of the electronic medical record at the University of Geneva Hospital in Switzerland since 1985 [17]. Despite such advances, the design of interfaces for direct entry of clinical information

Standards for Scalable Clinical Decision Support: Need, Current and Emerging Standards, Gaps, and Proposal for Progress

Despite their potential to significantly improve health care, advanced clinical decision support (CDS) capabilities are not widely available in the clinical setting. An important reason for this limited availability of CDS capabilities is the application-specific and institution-specific nature of most current CDS implementations. Thus, a critical need for enabling CDS capabilities on a much larger scale is the development and adoption of standards that enable current and emerging CDS resources to be more effectively leveraged across multiple applications and care settings. Standards required for such effective scaling of CDS include (i) standard terminologies and information models to represent and communicate about health care data; (ii) standard approaches to representing clinical knowledge in both human-readable and machine-executable formats; and (iii) standard approaches for leveraging these knowledge resources to provide CDS capabilities across various applications and care settings. A number of standards do exist or are under development to meet these needs. However, many gaps and challenges remain, including the excessive complexity of many standards; the limited availability of easily accessible knowledge resources implemented using standard approaches; and the lack of tooling and other practical resources to enable the efficient adoption of existing standards. Thus, the future development and widespread adoption of current CDS standards will depend critically on the availability of tooling, knowledge bases, and other resources that make the adoption of CDS standards not only the right approach to take, but the cost-effective path to follow given the alternative of using a traditional, ad hoc approach to implementing CDS.

Best Practices in Clinical Decision Support: the Case of Preventive Care Reminders.

BACKGROUND: Evidence demonstrates that clinical decision support (CDS) is a powerful tool for improving healthcare quality and ensuring patient safety. However, implementing and maintaining effective decision support interventions presents multiple technical and organizational challenges. PURPOSE: To identify best practices for CDS, using the domain of preventive care reminders as an example. METHODS: We assembled a panel of experts in CDS and held a series of facilitated online and in-person discussions. We analyzed the results of these discussions using a grounded theory method to elicit themes and best practices. RESULTS: Eight best practice themes were identified as important: deliver CDS in the most appropriate ways, develop effective governance structures, consider use of incentives, be aware of workflow, keep content current, monitor and evaluate impact, maintain high quality data, and consider sharing content. Keys themes within each of these areas were also described. CONCLUSION: Successful implementation of CDS requires consideration of both technical and socio-technical factors. The themes identified in this study provide guidance on crucial factors that need consideration when CDS is implemented across healthcare settings. These best practice themes may be useful for developers, implementers, and users of decision support.

Towards Meaningful Medication-Related Clinical Decision Support: Recommendations for an Initial Implementation

SUMMARY Clinical decision support (CDS) can improve safety, quality, and cost-effectiveness of patient care, especially when implemented in computerized provider order entry (CPOE) applications. Medication-related decision support logic forms a large component of the CDS logic in any CPOE system. However, organizations wishing to implement CDS must either purchase the computable clinical content or develop it themselves. Content provided by vendors does not always meet local expectations. Most organizations lack the resources to customize the clinical content and the expertise to implement it effectively. In this paper, we describe the recommendations of a national expert panel on two basic medication-related CDS areas, specifically, drug-drug interaction (DDI) checking and duplicate therapy checking. The goals of this study were to define a starter set of medication-related alerts that healthcare organizations can implement in their clinical information systems. We also draw on the experiences of diverse institutions to highlight the realities of implementing medication decision support. These findings represent the experiences of institutions with a long history in the domain of medication decision support, and the hope is that this guidance may improve the feasibility and efficiency CDS adoption across healthcare settings.

Use of open standards to implement health maintenance guidelines in a clinical workstation

We are developing a clinical workstation which integrates access to health maintenance guidelines with access to a computer-based medical record. In order to enhance the portability of such a system, we emphasize the use of open standards which can be used in diverse clinical environments. We discuss the use of relational database and expert system technology to provide both patient-specific and patient-independent access to clinical guidelines. We use the Arden Syntax as the format for a textual library which facilitates the storage of structured medical knowledge.

Advances in Clinical Decision Support: Highlights of Practice and the Literature 2015-2016

Introduction: Advances in clinical decision support (CDS) continue to evolve to support the goals of clinicians, policymakers, patients and professional organizations to improve clinical practice, patient safety, and the quality of care. Objectives: Identify key thematic areas or foci in research and practice involving clinical decision support during the 2015-2016 time period. Methods: Thematic analysis consistent with a grounded theory approach was applied in a targeted review of journal publications, the proceedings of key scientific conferences as well as activities in standards development organizations in order to identify the key themes underlying work related to CDS. Results: Ten key thematic areas were identified, including: 1) an emphasis on knowledge representation, with a focus on clinical practice guidelines; 2) various aspects of precision medicine, including the use of sensor and genomic data as well as big data; 3) efforts in quality improvement; 4) innovative uses of computer-based provider order entry (CPOE) systems, including relevant data displays; 5) expansion of CDS in various clinical settings; 6) patient-directed CDS; 7) understanding the potential negative impact of CDS; 8) obtaining structured data to drive CDS interventions; 9) the use of diagnostic decision support; and 10) the development and use of standards for CDS. Conclusions: Active research and practice in 2015-2016 continue to underscore the importance and broad utility of CDS for effecting change and improving the quality and outcome of clinical care.

Evolution of the Arden Syntax: Key Technical Issues from the Standards Development Organization Perspective

BACKGROUND The initial version of the Arden Syntax for Medical Logic Systems was created to facilitate explicit representation of medical logic in a form that could be easily composed and interpreted by clinical experts in order to facilitate clinical decision support (CDS). Because of demand from knowledge engineers and programmers to improve functionality related to complex use cases, the Arden Syntax evolved to include features typical of general programming languages but that were specialized to meet the needs of the clinical decision support environment, including integration into a clinical information system architecture. METHOD Review of the design history and evolution of the Arden Syntax by workers who participated in this evolution from the perspective of the standards development organization (SDO). RESULTS In order to meet user needs, a variety of features were successively incorporated in Arden Syntax. These can be grouped in several classes of change, including control flow, data structures, operators and external links. These changes included expansion of operators to manipulate lists and strings; a formalism for structured output; iteration constructs; user-defined objects and operators to manipulate them; features to support international use and output in different natural languages; additional control features; fuzzy logic formalisms; and mapping of the entire syntax to XML. The history and rationale of this evolution are summarized. CONCLUSION In response to user demand and to reflect its growing role in clinical decision support, the Arden Syntax has evolved to include a number of powerful features. These depart somewhat from the original vision of the syntax as simple and easily understandable but from the SDO perspective increase the utility of this standard for implementation of CDS. Backwards compatibility has been maintained, allowing continued support of the earlier, simpler decision support models.