Home Icon
Search Icon
This information is for reference purposes only. It was current when produced and may now be outdated. Archive material is no longer maintained, and some links may not work. Persons with disabilities having difficulty accessing this information should contact us at: https://digital.ahrq.gov/contact-us. Let us know the nature of the problem, the Web address of what you want, and your contact information.
Please go to digital.ahrq.gov for current information.

Clinical Decision Support

AHRQ-Funded Projects |  Selected CDS Resources |  Areas of Current Investigation |  AHRQ Podcasts |  Background |

AHRQ-Funded Projects

The Agency for Healthcare Research and Quality (AHRQ) has funded organizations across the country that are integrating clinical decision support into the delivery of health care. Some of these include:

Title: Structuring Care Recommendations for Clinical Decision Support
Principal Investigator: Osheroff, Jerry
State: CA

Title: Ambulatory Care Compact to Organize Risk and Decisionmaking (ACCORD)
Principal Investigator: Henry Chueh
State: MA

Title: A Systems Engineering Approach: Improving Medication Safety with Clinician Use of Health IT
Principal Investigator: Gurdev Singh
State: NY

Title: Harnessing Health IT to Prevent Medication-Induced Birth Defects
Principal Investigator: Eleanor Schwarz
State: PA

Title: Impact of a Wellness Portal on the Delivery of Patient-Centered Prospective Care
Principal Investigator: James Mold
State: OK

Title: Improving Laboratory Monitoring in Community Practices: A Randomized Trial
Principal Investigator: Steven Simon
State: MA

Title: Improving Quality In Cancer Screening: The Excellence Report For Colonoscopy
Principal Investigator: Judith Logan
State: OR

Title: Improving Quality through Decision Support for Evidence-Based Pharmacotherapy
Principal Investigator: David Lobach
State: NC

Title: Enhancing self-management of T2DM with an Automated Reminder and Feedback System
Principal Investigator: Edith Burns
State: WI

Title: Evaluation of a computerized clinical decision support system and EHR-linked registry to improve management of hypertension in community based health centers
Principal Investigator: Helene Kopal
State: NY

Title: Feedback of Treatment Intensification Data to Reduce Cardiovascular Disease Risk
Principal Investigator: Joe Selby
State: CA

Title: Health Information Technology in the Nursing Home
Principal Investigator: Jerry Gurwitz
State: MA

Title: Medication Monitoring for Vulnerable Populations via IT
Principal Investigator: Christoph Lehmann
State: MD

Title: Can Risk Score Alerts Improve Office Care for Chest Pain?
Principal Investigator: Thomas Sequist
State: MA

Title: STEPStools: Developing Web Services for Safe Pediatric Dosing
Principal Investigator: Kevin Johnson
State: TN

Title: Surveillance for Adverse Drug Events in Ambulatory Pediatrics
Principal Investigator: Thomas Bailey
State: MO

Title: Using An Electronic Personal Health Record To Empower Patient With Hypertension
Principal Investigator: Peggy Wagner
State: GA

Title: Using Information Technology to Provide Measurement Based Care for Chronic Illness
Principal Investigator: Madhukar Trivedi
State: TX


Selected CDS Resources

The following resources were selected from the Health IT Bibliography and represent peer-reviewed articles that describe best practices for the implementation and use of clinical decision support systems.

Impact of a Computerized Clinical Decision Support System on Reducing Inappropriate Antimicrobial Use: a Randomized Controlled Trial
Author(s): McGregor JC, Weekes E, Forrest GN, et al.
Source: J Am Med Inform Assoc (JAMIA). 2006 Jul-Aug;13(4):378-384 Epub 2006 Apr 18.
Summary: Many hospitals utilize antimicrobial management teams (AMTs) to improve patient care but function with minimal computer support. This randomized controlled trial evaluated the effectiveness and cost-effectiveness of a computerized clinical decision support (CDS) system for the management of antimicrobial utilization. The system used was developed to alert the AMT of potentially inadequate antimicrobial therapy. Outcomes assessed were hospital antimicrobial expenditures, mortality, length of hospitalization, and time spent managing antimicrobial utilization. The AMT intervened and spent approximately one hour less each day on the intervention arm. Hospital antimicrobial expenditures were a savings of $84,194 (23 percent), or $37.64 per patient in the intervention arm. Use of the system facilitated the management of antimicrobial utilization by allowing the AMT to intervene on more patients receiving inadequate antimicrobial therapy and to achieve substantial time and cost savings for the hospital. This is the first study that demonstrates in a patient-randomized controlled trial that computerized clinical decision support systems can improve existing antimicrobial management programs.

A Roadmap for National Action on Clinical Decision Support
Author(s): Osheroff JA, Teich JM, Middleton B, Steen EB, Wright A, Detmer DE
Source: J Am Med Inform Assoc (JAMIA). 2007 Mar-Apr;14(2):141-45 Epub 2007 Jan 9.
Summary: Clinical decision support (CDS) provides clinicians, staff, patients, or other individuals with knowledge and person-specific information to enhance health and health care. This document, a white paper approved by the AMIA Board of Directors, presents a roadmap for national action on clinical decision support. The roadmap identifies three pillars for fully realizing the promise of CDS: having the best available clinical knowledge well-organized for CDS interventions; high adoption and effective use of CDS tools; and continuous improvement of knowledge and CDS methods. Two levels of activity are presented in the roadmap: a comprehensive work plan and a critical path for CDS activities. The comprehensive work plan outlines the full set of tasks necessary to create a robust infrastructure in which to develop CDS interventions. The critical path tasks represent a subset of the comprehensive work plan that can be readily implemented and produce results in the short term. The full text of this paper is published on the AMIA Web site (http://www.amia.org/public-policy/reports-and-fact-sheets/a-roadmap-for-national-action-on-clinical-decision-support).

Effects of Computerized Physician Order Entry and Clinical Decision Support Systems on Medication Safety: A Systematic Review
Author(s): Kaushal R, Shojania KG, Bates DW
Source: Arch Intern Med 2003 Jun 23;163(12):1409-16.
Summary: Latrogenic injuries related to medications are common, costly, and clinically significant, and the use of computerized physician order entry (CPOE) and clinical decision support systems (CDSS) may reduce medication error rates. Studies were included for systematic review if the design was a controlled trial (randomized or nonrandomized), or an observational study with controls and if the measured outcomes were clinical or surrogate markers. The five CPOE studies showed improvement in: marked decrease in serious medication error rate; corollary orders; five prescribing behaviors; and nephrotoxic drug dose and frequency. The seven studies evaluating isolated CDSSs demonstrated statistically significantimprovements in antibiotic-associated medication errors or adverse drug events, and an improvement in theophylline-associated medication errors. The remaining three studies had nonsignificant results. Use of CPOE and isolated CDSS can substantially reduce medication error rates, but most studies have not been powered to detect differences in adverse drug events and have evaluated a small number of "homegrown" systems.

Effects of Computerized Clinical Decision Support Systems on Practitioner Performance and Patient Outcomes: A Systematic Review
Author(s): Garg AX, Adhikari NK, McDonald H, Rosas-Arellano MP, Devereaux PJ, Beyene J, Sam J, Haynes RB
Source: JAMA: The Journal of the American Medical Association. 2005 Mar 9;293(10):1223-1238.
Summary: This article reviews controlled trials assessing the effects of computerized clinical decision support systems (CDSSs) and identifing study characteristics predicting benefit to patient care. We included randomized and nonrandomized controlled trials that evaluated the effect of a CDSS compared with care provided without a CDSS on practitioner performance or patient outcomes. One hundred studies met our inclusion criteria and CDSS improved practitioner performance in 62 of the 97 studies assessing this outcome. Improved practitioner performance was associated with CDSSs that automatically prompted users compared with requiring users to activate the system (success in 73 percent of trials vs 47 percent; P = .02) and studies in which the authors also developed the CDSS software compared with studies in which the authors were not the developers (74 percent success vs 28 percent; respectively, P = .001). In conclusion, many CDSSs improve practitioner performance; however, the effects on patient outcomes remain understudied and, when studied, inconsistent.

Improving Clinical Practice Using Clinical Decision Support Systems: A Systematic Review of Trials to Identify Features Critical to Success
Author(s): Kawamoto K, Houlihan CA, Balas EA, Lobach DF
Source: BMJ. 2005 Apr 2;330(7494):765-68Epub 2005 Mar 14.
Summary: This systematic review of randomized controlled trials seeks to identify features of clinical decision support systems critical for improving clinical practice. Seventy studies were assessed for statistically and clinically significant improvement in clinical practice and for the presence of 15 decision support system features whose importance had been repeatedly suggested in the literature. Decision support systems were found to significantly improve clinical practice in 68 percent of trials. Multiple logistic regression analysis identified four features as independent predictors of improved clinical practice: automatic provision of decision support as part of clinician workflow (P < 0.00001), provision of recommendations rather than just assessments (P = 0.0187), provision of decision support at the time and location of decision making (P = 0.0263), and computer-based decision support (P = 0.0294). Of 32 systems possessing all four features, 30 (94 percent) significantly improved clinical practice. Clinicians and other stakeholders should implement clinical decision support systems that incorporate these features whenever feasible and appropriate to improve patient care.

Expert Clinical Decision Support Systems to Enhance Antimicrobial Stewardship Programs: Insights from the Society of Infectious Diseases Pharmacists
Author(s): Pestotnik SL
Source: Pharmacotherapy. 2005 Aug;25(8):1116-25.
Summary: Healthcare-associated infections (HAIs) are a leading cause of in-hospital mortality and adverse events such as antimicrobial resistance. These infections place tremendous burdens on the health care system and create situations for misuse of antimicrobial drugs. Traditionally, antimicrobial stewardship programs have relied on manual methods combined with clinical oversight and intervention to improve the management of HAIs. The advent of modern health care information technology offers the opportunity to expand the breadth and depth of these programs. Expert clinical decision support systems are the most promising of these information technology advances. Infectious disease-specific CDS systems need to be able to adhere to organism and drug name hierarchy lexicons, system functional requirements, and automatically produce location-specific antibiograms that conform to Clinical and Laboratory Standards Institute guidelines. Infectious disease-specific CDS systems are quickly becoming an essential element in the enlarging role of clinicians, both physicians and pharmacists, who specialize in infectious diseases.

Clinical Decision Support Systems for the Practice of Evidence-based Medicine
Author(s): Sim I, Gorman P, Greenes RA, Haynes RB, Kaplan B, Lehmann H, Tang PC
Source: J Am Med Inform Assoc (JAMIA). 2001 Nov-Dec;8(6):527-34.
Summary: The use of clinical decision support (CDS) systems to facilitate the practice of evidence-based medicine (EBM) promises to substantially improve health care quality. This paper, based on the proceedings of the Evidence and Decision Support track at the 2000 AMIA Spring Symposium, describes the research and policy challenges for capturing research and practice-based evidence in machine-interpretable repositories, and presents recommendations for adoption of CDS systems for EBM. The recommendations fall into five broad areas?capture literature-based and practice-based evidence in machine-interpretable knowledge bases; develop maintainable technical and methodological foundations for computer-based decision support; evaluate the clinical effects and costs of CDS systems and the ways they affect and are affected by professional and organizational practices; identify and disseminate best practices for work flow-sensitive implementations of CDS systems; and establish public policies that provide incentives for implementing CDS systems to improve health care quality. Although the promise of CDS system-facilitated EBM is strong, substantial work remains to be done to realize the potential benefits.

A Pragmatic Approach to Implementing Best Practices for Clinical Decision Support Systems in Computerized Provider Order Entry Systems
Author(s): Gross PA, Bates DW
Source: J Am Med Inform Assoc (JAMIA). 2007 Jan-Feb;14(1):25-28 Epub 2006 Oct 26.
Summary: Incorporation of clinical decision support (CDS) capabilities is required to realize the greatest benefits from computerized provider order entry (CPOE) systems. Discussions at a conference on CDS in CPOE held in San Francisco, California, June 21-22, 2005, produced severalpapers in this issue of JAMIA. The first paper reviews CDS for electronic prescribing within CPOE systems; the second describes current controversies regarding creation, maintenance, and uses of CPOE order sets for CDS; and the third presents issues related to certification as a potential means of validating CPOE systems for widespread use. Technical issues for CPOE included reconciling the history of drug allergies electronically, drug-based drug-drug interaction checking, drug ordering, and laboratory test monitoring. Nontechnical issues include continuous refinement of systems, taking responsibility for iterative improvements, and planning and implementation by administration. This manuscript summarizes all of the discussions at the meeting and provides a pragmatically oriented view of how to implement CPOE with CDS.


Areas of Current Investigation

In addition to recommendations for improving the CDS capabilities of various software packages, current research is directed toward the adoption of CDSS, especially adoption in rural and small practice settings. Other areas of CDS investigation include, but are not limited to:

  • How the translation of clinical knowledge into CDS can be routinized in practice and taken to scale to improve the quality of health care delivery.
  • Potential benefits, drawbacks, and unintended consequences of CDS.
  • Evaluating and developing methods for creating, storing, and replicating CDS elements across multiple clinical sites and ambulatory practices.
  • Translating clinical guidelines and outcomes related to preventive health care and treatment of patients with chronic illnesses.

CDS is commonly implemented as an alert, usually in the form of "pop-ups," delivered when the provider accesses the patient's record, such as when ordering tests or medications. The alerts, while generally found to be beneficial, may be overridden because of low specificity or alert "overload" or "fatigue," whereby the provider, after receiving too many alerts, begins to ignore and/or override the alerts.

Receiving too many alerts also can slow the provider down. Alert fatigue is a commonly perceived occurrence with the recent implementation of EMRs and specifically CDS and is the focus of investigation. For example, a study by van der Sijs et al. found that safety alerts were overridden by clinicians 49 to 96 percent percent of the time. A study within the VA Puget Sound Health Care System found that override rates of critical drug-drug and drug-allergy order checks were high. The drug-drug critical alert override rate was 87 percent and the drug-allergy override rate was 81 percent. Shah et al, on the other hand, found that 67 percent of CPOE alerts were accepted and concluded that it is possible to design computerized prescribing decision support with high rates of alert recommendation acceptance by clinicians.


AHRQ Podcasts

In late 2009, AHRQ produced a series of CDS podcasts as a part of its "Healthcare 411" news series. Use the links below to stream, download, or access the transcripts from these podcasts.

Background

Computer-based clinical decision support systems (CDSS) are broadly defined as systems that provide clinicians with clinical knowledge to enhance patient care and patient safety. The workshop "Roadmap for National Action on Clinical Decision Support" describes clinical decision support (CDS) as providing clinicians, staff, patients, or other individuals with knowledge and person-specific information, intelligently filtered or presented at appropriate times, to enhance health and health care. CDSS encompasses a variety of tools and interventions such as computerized alerts and reminders, clinical guidelines, order sets, patient data reports, and dashboards, documentation templates, diagnostic support, and clinical workflow tools. CDSS applications range from electronically available clinical data (e.g., information from a clinical laboratory system or information from a disease registry), electronic full-text journal and textbook access, evidence-based clinical guidelines, and systems that provide patient and situation-specific advice (e.g., EKG interpretation and drug-drug interaction checking).

In the past, many systems were stand-alone and not well-integrated with other clinical systems or into clinical workflow. Research has focused on improving access to CDSS tools by integrating relevant information and evidence-based care at the point of clinical decisionmaking. Much work has been done to incorporate decision support tools into electronic health records (EHRs) by implementing functions such as reminders for appropriate care, drug-allergy alerting during medication order-entry, and evidence-based order sets. Integration of CDSS tools into electronic medical records and point-of-care clinical tools requires standardization of electronic clinical data and medical knowledge and the sharing of information between systems.

Many current clinical system functions, such as computerized provider order entry (CPOE), include mechanisms to present relevant information and evidence-based care recommendations to clinicians at the point of clinical decisionmaking. However, CDSS usually cannot be implemented as off-the-shelf products with no customization. Local expertise to customize rules to fit an organization's population and needs is usually necessary. There is also considerable variability in the decision support features supported by different vendors. For electronic prescribing (e-prescribing), this variability has prompted consensus recommendations for features that e-prescribing systems will need to support.

CDSS are now incorporated as part of the functional criteria into ambulatory EHRs and inpatient EHRs certified by the Certification Commission for Health IT (CCHIT).

CDS "Dashboards" are growing in popularity. CDS Dashboardsinform the end user as to his or her use of decision support and compliance with CDS recommendations and provide feedback to the research team about CDS performance characteristics. They typically provide a summary of the user's performance for key indicators or metrics and comparison of the user's performance with other users or reference benchmarks.

Common barriers to implementation and adoption of CDSS include:

  • Limited implementation of electronic medical records (EMRs), computerized provider order entry (CPOE), personal health records (PHRs), and so on that serve as the basis for CDS.
  • Difficulty developing clinical practice guidelines.
  • Lack of standards.
  • Absence of a central repository or knowledge resource.
  • Poor support for CDS in commercial EHRs.
  • CDS "alert fatigue."
  • Challenges in integrating CDS into the clinical workflow.
  • A limited understanding of organizational and cultural issues relating to clinical decision support.

 

The information on this page is archived and provided for reference purposes only.