DESIGN OF DECOUPLED CLINICAL DECISION SUPPORT FOR SERVICE-ORIENTED ARCHITECTURES

Author(s):  
JENS WEBER-JAHNKE

Computer-based clinical decision support (CDS) contributes to cost savings, increased patient safety and quality of medical care. Most existing CDS systems are stand-alone products (first generation) or part of complete electronic medical record packages (second generation). Experience shows that creating and maintaining CDS systems is expensive and requires effort that should be economized by sharing them among multiple users. It makes good economic sense to share CDS service installations among a larger set of client systems. The paradigm of a service-oriented architecture (SOA) embraces this idea of sharing distributed services. Some attempts making CDS services available to distributed health information systems exist. However, these approaches have not gained much adoption. We argue that they do not provide a sufficient level of decoupling between client and CDS in order to be broadly reusable in SOAs. In this paper, we present a new CDS service component called EGADSS, which has been designed and implemented with the declared objective to minimize the coupling between client and CDS server. We present our key design decisions, which are guided by empirical research in SOA development. We evaluate our result theoretically by measuring the level of decoupling achieved compared to existing CDS approaches. Furthermore, we report on an empirical evaluation of the resulting design, integrating the EGADSS service with an example client system.

2019 ◽  
Vol 6 (Supplement_2) ◽  
pp. S806-S807
Author(s):  
Cindy L Hoegg ◽  
Katie L Williams ◽  
Eric Shelov ◽  
Talene A Metjian ◽  
Ana Maria Cardenas ◽  
...  

Abstract Background Clinical decision support for Clostridioides difficile infection (CDI) diagnostics reduces inappropriate testing, leading to decreased need for isolation and antibiotic use. Our institution utilized manual discontinuation by laboratory staff of CDI testing for inappropriate specimens, including formed stool and age < 1 year. We aimed to assess the financial impact of instituting a CDI best practice alert at a quaternary care children’s hospital. Methods A multidisciplinary team mapped inappropriate testing criteria identified from literature review with discrete fields in our electronic health record (EHR, EpicCare) to design an alert. The exclusion criteria identified included: (1) age < 1 year; (2) positive C. difficile test within past 14 days; (3) less than or equal to 3 unformed stools in past 24 hours; (4) current receipt of CDI-directed therapy; or (5) laxative use or barium exposure in prior 48 hours. 6 months of data prior to implementation were reviewed to estimate impact of the alert. At implementation, any exclusion criteria detected in the EHR at the time of order entry triggered an alert to deter CDI testing. Cost estimates for averted tests (Quick Check Complete Assay/Illumigene) included cost of test ($50), cost of isolation/personal protective equipment ($159/day), and cost of treatment with oral vancomycin in false-positives ($2250/treatment course). Results In a 6-month pre-implementation period, 586 tests for CDI were ordered; of which, 23% were identified by our criteria as inappropriate. During the first 3 months of alert implementation, 256 tests were ordered, of which 105 (41%) caused the alert to fire. Of those, 56 tests were not ordered, for a 22% reduction in testing. Laboratory staff continued to manually stop tests not meeting criteria, such as patient age <1 year when possible. Based on avoidance of testing, use of PPE, and 10 day antibiotic treatment for false-positives (assumed 25% by literature review), this translated to cost savings of $69,916, and an annual cost savings of $279,664. Conclusion Implementation of an alert for select patients using a bioinformatics algorithm reduced inappropriate CDI testing. Clinical decision support for CDI can lead to substantial cost savings for both antibiotic use and isolation precautions. Disclosures All authors: No reported disclosures.


2011 ◽  
Vol 02 (03) ◽  
pp. 284-303 ◽  
Author(s):  
A. Wright ◽  
M. Burton ◽  
G. Fraser ◽  
M. Krall ◽  
S. Maviglia ◽  
...  

SummaryBackground: Computer-based clinical decision support (CDS) systems have been shown to improve quality of care and workflow efficiency, and health care reform legislation relies on electronic health records and CDS systems to improve the cost and quality of health care in the United States; however, the heterogeneity of CDS content and infrastructure of CDS systems across sites is not well known.Objective: We aimed to determine the scope of CDS content in diabetes care at six sites, assess the capabilities of CDS in use at these sites, characterize the scope of CDS infrastructure at these sites, and determine how the sites use CDS beyond individual patient care in order to identify characteristics of CDS systems and content that have been successfully implemented in diabetes care.Methods: We compared CDS systems in six collaborating sites of the Clinical Decision Support Consortium. We gathered CDS content on care for patients with diabetes mellitus and surveyed institutions on characteristics of their site, the infrastructure of CDS at these sites, and the capabilities of CDS at these sites.Results: The approach to CDS and the characteristics of CDS content varied among sites. Some commonalities included providing customizability by role or user, applying sophisticated exclusion criteria, and using CDS automatically at the time of decision-making. Many messages were actionable recommendations. Most sites had monitoring rules (e.g. assessing hemoglobin A1c), but few had rules to diagnose diabetes or suggest specific treatments. All sites had numerous prevention rules including reminders for providing eye examinations, influenza vaccines, lipid screenings, nephropathy screenings, and pneumococcal vaccines.Conclusion: Computer-based CDS systems vary widely across sites in content and scope, but both institution-created and purchased systems had many similar features and functionality, such as integration of alerts and reminders into the decision-making workflow of the provider and providing messages that are actionable recommendations.


2014 ◽  
Vol 31 (5) ◽  
pp. 497-498 ◽  
Author(s):  
M. E. Murphy ◽  
T. Fahey ◽  
S. M. Smith

Sign in / Sign up

Export Citation Format

Share Document