Beatriz H. Rocha

Decision support in medicine: lessons from the help system

PURPOSE This report describes an ongoing transition from the HELP Hospital Information System to HELP II, a replacement Health Information System built to manage clinical information captured in a variety of medical settings. The focus of the article is on the medical decision support provided by this system and studied by researchers at the University of Utah and Intermountain Health Care (IHC), a large health care organization in Utah, for many years. METHODS Select success features of the original HELP systems decision support environment are identified and lessons learned are related. Plans for transferring these features to HELP II are discussed. RESULTS The article focuses on four features: (1) the importance of easy access to patient data essential for decision support, (2) the commitment to continued measurement and revision of both the logic and the interventional strategy in a decision support application, (3) experience with data mining as a tool for developing decision support tools, and (4) the role of clinical reports in supporting the decision making process.

A multi-layered framework for disseminating knowledge for computer-based decision support.

BACKGROUND There are several challenges in encoding guideline knowledge in a form that is portable to different clinical sites, including the heterogeneity of clinical decision support (CDS) tools, of patient data representations, and of workflows. METHODS We have developed a multi-layered knowledge representation framework for structuring guideline recommendations for implementation in a variety of CDS contexts. In this framework, guideline recommendations are increasingly structured through four layers, successively transforming a narrative text recommendation into input for a CDS system. We have used this framework to implement rules for a CDS service based on three guidelines. We also conducted a preliminary evaluation, where we asked CDS experts at four institutions to rate the implementability of six recommendations from the three guidelines. CONCLUSION The experience in using the framework and the preliminary evaluation indicate that this approach has promise in creating structured knowledge, to implement in CDS systems, that is usable across organizations.

A highly scalable, interoperable clinical decision support service.

OBJECTIVE To create a clinical decision support (CDS) system that is shareable across healthcare delivery systems and settings over large geographic regions. MATERIALS AND METHODS The enterprise clinical rules service (ECRS) realizes nine design principles through a series of enterprise java beans and leverages off-the-shelf rules management systems in order to provide consistent, maintainable, and scalable decision support in a variety of settings. RESULTS The ECRS is deployed at Partners HealthCare System (PHS) and is in use for a series of trials by members of the CDS consortium, including internally developed systems at PHS, the Regenstrief Institute, and vendor-based systems deployed at locations in Oregon and New Jersey. Performance measures indicate that the ECRS provides sub-second response time when measured apart from services required to retrieve data and assemble the continuity of care document used as input. DISCUSSION We consider related work, design decisions, comparisons with emerging national standards, and discuss uses and limitations of the ECRS. CONCLUSIONS ECRS design, implementation, and use in CDS consortium trials indicate that it provides the flexibility and modularity needed for broad use and performs adequately. Future work will investigate additional CDS patterns, alternative methods of data passing, and further optimizations in ECRS performance.

An Electronic Protocol for Translation of Research Results to Clinical Practice: A Preliminary Report

Introduction: We evaluated the feasibility of using an electronic protocol developed for research use (Research-eProtocol-insulin) for blood glucose management in usual intensive care unit clinical practice. Methods: We implemented the rules of Research-eProtocol-insulin in the electronic medical record of the Intermountain Healthcare hospital system (Clinical-eProtocol-insulin) for use in usual clinical practice. We evaluated the performance of Clinical-eProtocol-insulin rules in the intensive care units of seven Intermountain Healthcare hospitals and compared this performance with the performance of Research-eProtocol-insulin at the LDS Hospital Shock/Trauma/Respiratory Intensive Care Unit. Results: Clinician (nurse or physician) compliance with computerized protocol recommendations was 95% (of 21,325 recommendations) with Research-eProtocol-insulin and 92% (of 109,458 recommendations) with Clinical-eProtocol-insulin. The blood glucose distribution in clinical practice (Clinical-eProtocol-insulin) was similar to the research use distribution (Research-eProtocol-insulin); however, the mean values (119 mg/dl vs 113 mg/dl) were statistically different (P = 0.0001). Hypoglycemia rates in the research and practice settings did not differ: the percentage of measurements ≤40 mg/dl (0.11% vs 0.1%, P = 0.65) and the percentage of patients with at least one blood glucose ≤40 mg/dl (4.2% vs 3%, P = 0.23) were not statistically significantly different. Conclusion: Our electronic blood glucose protocol enabled translation of a research decision-support tool (Research-eProtocol-insulin) to usual clinical practice (Clinical-eProtocol-insulin).

Taking advantage of continuity of care documents to populate a research repository

OBJECTIVE Clinical data warehouses have accelerated clinical research, but even with available open source tools, there is a high barrier to entry due to the complexity of normalizing and importing data. The Office of the National Coordinator for Health Information Technologys Meaningful Use Incentive Program now requires that electronic health record systems produce standardized consolidated clinical document architecture (C-CDA) documents. Here, we leverage this data source to create a low volume standards based import pipeline for the Informatics for Integrating Biology and the Bedside (i2b2) clinical research platform. We validate this approach by creating a small repository at Partners Healthcare automatically from C-CDA documents. MATERIALS AND METHODS We designed an i2b2 extension to import C-CDAs into i2b2. It is extensible to other sites with variances in C-CDA format without requiring custom code. We also designed new ontology structures for querying the imported data. RESULTS We implemented our methodology at Partners Healthcare, where we developed an adapter to retrieve C-CDAs from Enterprise Services. Our current implementation supports demographics, encounters, problems, and medications. We imported approximately 17 000 clinical observations on 145 patients into i2b2 in about 24 min. We were able to perform i2b2 cohort finding queries and view patient information through SMART apps on the imported data. DISCUSSION This low volume import approach can serve small practices with local access to C-CDAs and will allow patient registries to import patient supplied C-CDAs. These components will soon be available open source on the i2b2 wiki. CONCLUSIONS Our approach will lower barriers to entry in implementing i2b2 where informatics expertise or data access are limited.

The clinical knowledge management infrastructure of intermountain healthcare

Publisher Summary Intermountains core clinical strategy is to provide high value care by effectively managing clinical conditions and processes, while improving medical outcomes and member satisfaction at the lowest necessary cost. This chapter discusses the Clinical Knowledge Management (CKM) software infrastructure that has been implemented at Intermountain, along with some utilization data demonstrating how extensively it is being used. Since 1995, Intermountain has been building a new clinical information systems infrastructure, known as HELP2. The clinical systems are being delivered to care providers through a web-based shell developed in-house. Currently, it offers functionality such as laboratory results, radiology images and reports, surgery reports, etc. The main components of the HELP2 core infrastructure are the Clinical Data Repository, the Healthcare Data Dictionary, and the Enterprise Master Patient Index. Another important component of the overall information systems infrastructure of Intermountain is the Enterprise Data Warehouse, which receives data feeds from almost all administrative and clinical databases used by Intermountain systems. The Clinical Knowledge Repository and Foresight are the primary components of Intermountains CKM software infrastructure. The data presented reflects the knowledge content and software infrastructure that were in production use as of September 2005, unless stated otherwise.

Use of a remote clinical decision support service for a multicenter trial to implement prediction rules for children with minor blunt head trauma

OBJECTIVE To evaluate the architecture, integration requirements, and execution characteristics of a remote clinical decision support (CDS) service used in a multicenter clinical trial. The trial tested the efficacy of implementing brain injury prediction rules for children with minor blunt head trauma. MATERIALS AND METHODS We integrated the Epic(®) electronic health record (EHR) with the Enterprise Clinical Rules Service (ECRS), a web-based CDS service, at two emergency departments. Patterns of CDS review included either a delayed, near-real-time review, where the physician viewed CDS recommendations generated by the nursing assessment, or a real-time review, where the physician viewed recommendations generated by their own documentation. A backstopping, vendor-based CDS triggered with zero delay when no recommendation was available in the EHR from the web-service. We assessed the execution characteristics of the integrated system and the source of the generated recommendations viewed by physicians. RESULTS The ECRS mean execution time was 0.74 ±0.72 s. Overall execution time was substantially different at the two sites, with mean total transaction times of 19.67 and 3.99 s. Of 1930 analyzed transactions from the two sites, 60% (310/521) of all physician documentation-initiated recommendations and 99% (1390/1409) of all nurse documentation-initiated recommendations originated from the remote web service. DISCUSSION The remote CDS system was the source of recommendations in more than half of the real-time cases and virtually all the near-real-time cases. Comparisons are limited by allowable variation in user workflow and resolution of the EHR clock. CONCLUSION With maturation and adoption of standards for CDS services, remote CDS shows promise to decrease time-to-trial for multicenter evaluations of candidate decision support interventions.

Design, implementation and evaluation of a clinical decision support system to prevent adverse drug events.

Adverse drug events are known to be a major health problem worldwide. It is estimated that the annual costs related to these events in the United States are greater than the total costs with cardiovascular disease care. Decision support systems that assist drug ordering have demonstrated to be a powerful tool to prevent prescription errors and adverse drug events. On the other hand, some issues related to the development, implementation, configuration, and evaluation of these decision support systems still need further research. This paper presents the development and evaluation of a decision support system prototype that helps with the prevention of adverse drug events by detecting drug-drug interactions in drug orders. The structure of the system tries to solve some of the problems described by the literature, such as integration with hospital information systems, adaptability to local needs, and knowledge base maintenance. The proposed model has shown to be an effective method for representing drug-drug interactions. The prototype was evaluated by a retrospective study using a dataset with 37.237 prescriptions. The system was able to detect 10.044 (27.0%) orders containing one or more drug-drug interactions. Among these interactions, 6.4% had high severity. In a future study, it is intended to apply the developed system in a real-time on-line environment, evaluating the benefits achieved in terms of improvement in medical practice and patient outcomes.

Clinical Decision Support for a Multicenter Trial of Pediatric Head Trauma: Development, Implementation, and Lessons Learned.

INTRODUCTION For children who present to emergency departments (EDs) due to blunt head trauma, ED clinicians must decide who requires computed tomography (CT) scanning to evaluate for traumatic brain injury (TBI). The Pediatric Emergency Care Applied Research Network (PECARN) derived and validated two age-based prediction rules to identify children at very low risk of clinically-important traumatic brain injuries (ciTBIs) who do not typically require CT scans. In this case report, we describe the strategy used to implement the PECARN TBI prediction rules via electronic health record (EHR) clinical decision support (CDS) as the intervention in a multicenter clinical trial. METHODS Thirteen EDs participated in this trial. The 10 sites receiving the CDS intervention used the Epic(®) EHR. All sites implementing EHR-based CDS built the rules by using the vendors CDS engine. Based on a sociotechnical analysis, we designed the CDS so that recommendations could be displayed immediately after any provider entered prediction rule data. One central site developed and tested the intervention package to be exported to other sites. The intervention package included a clinical trial alert, an electronic data collection form, the CDS rules and the format for recommendations. RESULTS The original PECARN head trauma prediction rules were derived from physician documentation while this pragmatic trial led each site to customize their workflows and allow multiple different providers to complete the head trauma assessments. These differences in workflows led to varying completion rates across sites as well as differences in the types of providers completing the electronic data form. Site variation in internal change management processes made it challenging to maintain the same rigor across all sites. This led to downstream effects when data reports were developed. CONCLUSIONS The process of a centralized build and export of a CDS system in one commercial EHR system successfully supported a multicenter clinical trial.

Modeling a decision support system to prevent adverse drug events

Adverse drug events are known to be a major health problem worldwide. Decision support systems (DSSs) that assist drug ordering have demonstrated to be a powerful tool to prevent prescription errors and adverse drug events. On the other hand, some issues related to the development, implementation, configuration and evaluation of these DDSs still need further research. The objective of this project was the development of a DSS prototype that helps with the prevention of adverse drug events by detecting drug-drug interactions in drug orders. The structure of the system tries to solve some of the problems described by the literature, such as integration with hospital information systems, adaptability to local needs, and knowledge base maintenance. The proposed model has been shown to be an effective method for representing drug-drug interactions.