CDS
Clinical decision support (CDS) refers broadly to providing clinicians or patients with clinical knowledge, intelligently filtered and presented at appropriate times. [1] Clinical knowledge of interest could range from simple facts and relationships (such as an patient's vital signs, allergies and lab data) to relevant medical knowledge (such as best practices for managing patients with specific disease states, new clinical research, professional organizations' practice guidelines, expert opinion, systematic reviews, and other types of information.
Contents
History
Clinical decision support tools existed prior to development of electronic medical records (EMRs). They include expert consultation, practice guidelines carried in clinicians' pockets, patient cards used by nurses to track a patient's treatments, tables of important medical knowledge, and ICU patient flow sheets. Many of these CDS tools are still relevant, but integration of CDS with current EMRs presents an opportunity for the various types of decision support to be immediately available at the time of the decision-making. CDS can be more relevant, more accurate, and can facilitate and be integrated with clinical workflow.
For more on the history of CDS, see here and here.
CDS components
There are several key components of a good clinical decision support system.
- Documentation tools
- Clinician Checklists
- Calculators
- Reference Links
Documentation forms/templates
As mentioned above, these existed prior to EMRs in the form of structured documentation forms for conducting clinician assessments. Many of these have been supplanted by digital reproductions in EMR of the original paper documentation form.
Examples include:
- nursing intake forms
- physician "History & Physicals"
- ER templates
Other tools that were artifacts of clinician workflow and existed prior to EMR implementation, now have the potential for added functionality when computerized, web-based, or automated. Added functionality includes dispersed access to the tool's information (ability for multiple users from multiple disciplines and geographic locations to share a single set of information), auto-population of accurate and current data from the clinical information system, linkages between tool task lists and CPOE, and improved order fulfillment efficiency.
Examples of these tools include:
- Handoff tools (lists of patients with summations of clinical data used at time of a shift handoff between clinicians)
- Rounding tools (summaries of data on a single patient, clinical task lists
- ICU flowsheets for documenting and charting vital signs and hemodynamic data.
Alerts and reminders
Alerts are an important part of CDS.
Examples include:
- Alert that appropriate cancer screening is due.
- Drug allergy alert
- Drug interaction alert
- Underdose/overdose alerts based on renal or liver function, age, drug level
- Result alerts to follow up with patient if a HBA1c was elevated patient needed to be retested in 3 months. [2]
Relevant data presentation
Examples of this include:
a) Patient specific data such as:
- Display of relevant labs during medication CPOE such as patient's renal and liver function.
- Display of other relevant patient data during CPOE such as patient's age (which may affect side affects and dosing) or conditions.
b) Population-specific data such as:
- Retrospective filtering and aggregate reporting: disease registries and clinic population dashboards.
- Microbiograms: tables of local bacterial flora and their sensitivity and susceptibility to various antibiotics
Order creation facilitators
Examples include: order sets, order menus, tools for complex ordering, and "single-order completers including consequent order."
Order Sets
An order set is a group of related orders which a physician or other licensed clinician can initiate with a few keystrokes or mouse clicks. An order set allows a user to quickly select one or more orders that apply to a specific diagnosis, clinical condition (such as shortness of breath or abdominal pain), treatment event (such as heart surgery), diagnostic test etc. Using order sets is intended to reduce both time spent in entering orders and errors of omission. They serve as a reminder of the tasks which may need to be accomplished in a particular patient in the same sense as a checklist and there is a great deal of overlap between checklists and order sets, both conceptually and in practice. An order set may contain medication orders, orders for diagnostic tests, orders for a clinician to carry out an action, and other types of orders, in any combination and essentially any number. It should be noted that increasing the number of orders in an order set is often counter-productive as this actually slows a clinician and increases cognitive load.
An example order set for a Cardiac MRI would include:
- Order specifying the particular body part or organ to be imaged (in this case, the heart)
- Order for renal function test (blood test) if there is no result for this test in the EMR in the last 6 weeks
- Order to administer a sedative prior to the MRI
- Order to administer contrast through an intravenous line (IV) during the exam
- Order for transportation from hospital room to the MRI suite in the radiology department at time of MRI
Order Menus
An order menu is a group of related orders which are depicted onscreen together via an EMR's GUI so that an ordering clinician visualizes the breath and organization of the orders. An order menu allows CPOE/EMR developers to direct clinicians towards the most common or appropriate orders for a particular topic. Using order sets reduces time spent searching for the desired orders and provides a rudimentary level of knowledge and education. Order sets are commonly made up of medication orders, but non-medication orders may be included.
Examples of order menu content include:
- anti-hypertensive medications arranged by class, by preference, by cost, or other means.
- common pulmonary medications to treat COPD, asthma, embolisms, and chronic cough.
Interaction models
An interaction model is a set of rules for making clinical decisions. The rules are based on a large collection of medical knowledge and an accurate computer representation scheme.
Artificial intelligence
Artificial intelligence is a system that was developed by a team of system engineers and clinicians. The system would take some of the workload from medical teams by assisting the physicians with tasks like diagnosis & Therapy recommendations.
Business Intelligence and Data Warehousing
Validation and Verification of Clinical Decision Support
Sample Decision Support Content
- Diabetes CDS Content
- Drug-Drug Interaction Rules
- Clinical Reminders from Beth Israel/Deaconess Medical Center in Boston
- Symptom Triage Decision Support for Consumers (example: "Chest Pain") [1]
- Weight-based Heparin Dosing Guidelines
- Flowchart-based decision support sample content
- Preventive care reminders
- Mental health clinical decision support
- Computerized clinical decision support systems for chronic disease management
- Probabilistic Case Detection for Disease Surveillance Using Data in Electronic Medical Records
Reviews
- A description and functional taxonomy of rule-based decision support content at a large integrated delivery network.
- Computerized clinical decision support for prescribing: provision does not guarantee uptake
- Computerized clinical decision support systems for chronic disease management
- Expert clinical rules automate steps in delivering evidence-based care in the electronic health record
- Impact of electronic reminders on venous thromboprophylaxis after admissions and transfers
- Drug–drug interactions that should be non-interruptive in order to reduce alert fatigue in electronic health records
- Drug-drug interaction checking assisted by clinical decision support: a return on investment analysis
- Towards Meaningful Medication-Related Clinical Decision Support: Recommendations for an Initial Implementation
- Clinical Decision Support: A tool of the Hospital Trade
- Development and use of active clinical decision support for preemptive pharmacogenomics
- Effect of Clinical Decision-Support Systems: A Systematic Review
- Clinical decision support: progress and opportunities
- A qualitative study of the activities performed by people involved in clinical decision support: recommended practices for success
- Information system support as a critical success factor for chronic disease management: Necessary but not sufficient
- A nursing clinical decision support system and potential predictors of head-of-bed position for patients receiving mechanical ventilation.
- Evaluating Clinical Decision Support Systems:Monitoring CPOE Order Check Override Rates in the Department of Veterans Affairs’ Computerized Patient Record System
- Cost-effectiveness of a shared computerized decision support system for diabetes linked to electronic medical records
- Clinical decision support or genetically guided personalized medicine: a systematic review
- The Effect of Computerized Physician Order Entry with Clinical Decision Support on the Rates of Adverse Drug Events: A Systematic Review
- Effects of Computerized Physician Order Entry and Clinical Decision Support Systems on Medication Safety
- Evaluating the impact of an integrated computer-based decision support with person-centered analytics for the management of asthma in primary care: a randomized controlled trial
- Reducing unnecessary testing in a CPOE system through implementation of a targeted CDS intervention
- Clinical Decision Support Systems (CDSS) for preventive management of COPD patients
- Improving Clinical Practice Using Clinical Decision Support Systems: A Systematic Review of Trials to Identify Features Critical to Success
- Optimization of drug–drug interaction alert rules in a pediatric hospital's electronic health record system using a visual analytics dashboard
- Clinical decision support systems: Potential with pitfalls
- Do computerised clinical decision support systems for prescribing change practice? A systematic review of the literature (1990-2007)
- Adoption of Clinical Decision support in Multimorbidity: A Systematic Review
- A Decision Support Tool for Appropriate Glucose-Lowering Therapy in Patients with Type 2 Diabetes
- Computerized Physician Order Entry - effectiveness and efficiency of electronic medication ordering with decision support systems
- A clinical decision support needs assessment of community-based physicians
- Prospective evaluation of a clinical decision guideline to diagnose spinal epidural abscess in patients who present to the emergency department with spine pain
- Effect of computerized clinical decision support on the use and yield of CT pulmonary angiography in the emergency department
- Developing and evaluating an automated appendicitis risk stratification algorithm for pediatric patients in the emergency department
- Improving red blood cell orders, utilization, and management with point-of-care clinical decision support
- Automated electronic medical record sepsis detection in the emergency department
- Ten Commandments for Effective Clinical Decision Support: Making the Practice of Evidence-based Medicine a Reality
- Physicians' Attitudes Towards the Advice of a Guideline-Based Decision Support System: A Case Study With OncoDoc2 in the Management of Breast Cancer Patients
- Grand challenges in clinical decision support
- Clinical Decision Support Systems for the Practice of Evidence-based Medicine
- Clinical Decision Support: Effectiveness in Improving Quality Processes and Clinical Outcomes and Factors That May Influence Success
CDS Implementation
CDS should be designed to provide the right information to the right person in the right format through the right channel at the right time.
At the stage of planning for implementation of any new health IT system or their components, there are some considerations and steps that should be followed to maximize CDS system success:
- Needs Assessment: ensuring that identified clinical needs and functional requirements
- Assessing Organizational Readiness
i) Understanding prior physician and organizational experience with CDS ii) Assessment of level of physician knowledge, perception, engagement, and willingness to change iii) Aligned leadership with clear objectives
- CDS related factors
i) Deciding whether to purchasing a commercial system or build the system ii) CDS usability: Will CDS increase physician workload? Can the level of intrusiveness of alerts be customized? iii) Adequate planning for encouraging physicians to use CDS iv) Appropriate training on using CDS v) Mechanisms in place to evaluate usage and effectiveness of the CDS
Alerts
Liability
Workflow
Usability
- Evidence based content / Clinical content accuracy
- Changing behavior (limited interaction by users, adherence to protocol)
- Training and communication
- System design limitations
- Choosing the right metrics for reporting (Process / Clinical)
- Potential breaks due to system upgrades
Clinical Decision Support Overview
- National Roadmap for Clinical Decision Support
- General system features associated with improvements in clinical practice
- Support Decisions with Diagnostic Aids
- Clinical Decision Support Liability
- Exploring a Clinically Friendly Web-Based Approach to Clinical Decision Support Linked to the Electronic Health Record A Design Philosophy Prototype Implementation and Framework for Assessment
CDS success measures
To estimate the success of the system we should look at the following points[3]:
- System quality.
- Information quality
- Usage
- User satisfaction (Process Outcome)
- Individual impact (Clinical Outcome)
- Organizational impact (Financial outcome).
Information Resources
- The HIMSS Clinical Decision Support (CDS) Task Force wiki
- Alert placement in clinical workflow
- Initial Selection of What to Alert on...
- Alerts versus on-demand CDS
- Sources of clinical decision support content
- Here is a video of CDS in action within the free EHR drchrono [2].
CDS benefits
Results indicate the potential of CDS to improve the quality of care. These are good reasons for institutions to adopt CDS, but they should do so at their own pace and volition.
Promote use of evidence based recommendations
Better clinical decision-making
- Decision Support in Psychiatry - a comparison between the diagnostic outcomes using a computerized decision support system versus manual diagnosis
- Information system support as a critical success factor for chronic disease management
- Classification models for the prediction of clinicians' information needs
Reduced medication errors
Improved cost-effectiveness
More research is needed to identify the cost-effectiveness of CDS as current research has found conflicting results of increased, decreased, or no change in cost of care. [3] [4]
Increased patient convenience
Improved quality of healthcare delivery
Improved healthcare outcomes for patients and patient populations
Current research has shown various systems associated with improved health outcomes but is still limited and requires more research. However, it has helped improved outcomes for chronic disease management particularly for individuals living with diabetes. [5] Family Health History is a leading predictor of disease risk. Clinical Decision Support can also be used to help healthcare providers fill in the family history gap [3]
Reviews
- Evaluation of Medication Alerts in Electronic Health Records for Compliance with Human Factors Principles
- Evaluation of User Interface and Workflow Design of a Bedside Nursing Clinical Decision Support System
- Clinical Decision Support and Appropriateness of Antimicrobial Prescribing – A Randomized Trail
- Long-term effect of computer-assisted decision support for antibiotic treatment in critically ill patients: a prospective ‘before/after’ cohort study
- Perceived barriers of heart failure nurses and cardiologists in using clinical decision support systems in the treatment of heart failure patients
- Effects of clinical decision-support systems on practitioner performance and patient outcomes: a synthesis of high-quality systematic review findings
- Probabilistic Case Detection for Disease Surveillance Using Data in Electronic Medical Records
- The Reliability of an Epilepsy Treatment Clinical Decision Support System
- Impact of Electronic Health Record Clinical Decision Support on Diabetes Care: A Randomized Trial
- A trial of automated decision support alerts for contraindicated medications using computerized physician order entry
- Cost-effectiveness of a shared computerized decision support system for diabetes linked to electronic medical records
- Development and evaluation of a comprehensive clinical decision support taxonomy: comparison of front-end tools in commercial and internally developed electronic health record systems
- Impact of electronic health record clinical decision support on diabetes care: a randomized trial
- Impact of clinical decision support on head computed tomography use in patients with mild traumatic brain injury in the ED
- Formative evaluation of the accuracy of a clinical decision support system for cervical cancer screening
- Examining clinical decision support integrity: is clinician self-reported data entry accurate?
- Comparison of Computer-based Clinical Decision Support Systems and Content for Diabetes Mellitus.
- Adoption of Clinical Decision support in Multimorbidity: A Systematic Review
- A health record integrated clinical decision support system to support prescriptions of pharmaceutical drugs in patients with reduced renal function: Design, development and proof of concept
- Prospective evaluation of a clinical decision guideline to diagnose spinal epidural abscess in patients who present to the emergency department with spine pain
- Computerized clinical decision support for prescribing: provision does not guarantee uptake
- Improving Hospital Venous Thromboembolism Prophylaxis with Electronic Decision Support
- Real-time use of the iPad by third-year medical students for clinical decision support and learning: a mixed methods study
- Improving red blood cell orders, utilization, and management with point-of-care clinical decision support
- Implementation of multiple-domain covering computerized decision support systems in primary care: a focus group study on perceived barriers
- Computerized clinical decision support improves warfarin management and decreases recurrent venous thromboembolism
- Clinical decision support improves physician guideline adherence for laboratory monitoring of chronic kidney disease: a matched cohort study
- Exposure to and experiences with a computerized decision support intervention in primary care: results from a process evaluation
- Clinical Decision Support Systems for the Practice of Evidence-based Medicine
Related articles
Clinical Decision Support Mechanism (CDSM) Clinical Decision Support to Implement CYP2D6 Drug-Gene Interaction Overrides of clinical decision support alerts in primary care clinics Effect of computerized clinical decision support on the use and yield of CT pulmonary angiography in the emergency department Clinical decision support in small community practice settings: a case study Barriers and facilitators to the uptake of computerized clinical decision support systems in specialty hospitals: protocol for a qualitative cross-sectional study Identifying Best Practices for Clinical Decision Support and Knowledge Management in the Field Development and Implementation of Computerized Clinical Guidelines: Barriers and Solutions Implementation Pearls from a New Guidebook on Improving Medication Use and Outcomes with Clinical Decision Support Clinical decision support systems: A discussion of quality, safety and legal liability issues Clinical decision support in electronic prescribing: recommendations and an action plan: report of the joint clinical decision support workgroup
References
- ↑ Slater, B. Osheroff, JA. Clinical Decision Support, in Electronic Health Records: A Guide for Clinicians and Administrators. American College of Physicians. 2008. http://books.google.com/books?hl=en&lr=&id=KtlUMwaZP98C
- ↑ The Impact of a Decision Support Tool Linked to an Electronic Medical Record on Glycemic Control in People with type 2 Diabetes.http://www-ncbi-nlm-nih-gov.ezproxyhost.library.tmc.edu/pmc/articles/PMC3869133/
- ↑ Formative evaluation of clinician experience with integrated family history-based clinical decision support into clinical practice.http://clinfowiki.org/wiki/index.
- slater 2008
- Franklin, MJ, et al, Modifiable Templates Facilitate Customization of Physician Order Entry, [6]
- Sittig, DF, and Stead, WW, Computer-based Order Entry: The State of the Art, J Am Med Informatics Assoc., 1994;1:108-123. [7]
- Anderson, JG, et al, Physician Utilization of a hospital information system: a computer simulation model. Pric Annu Symp Compu Appl Med Care, IEEE, 1988;12:858-861. [8]
- Southern Ohio Medical Center, [9]
- Clinical Decision Support Systems :State of the Art AHRQ Publication No.09* 0069* EF June 2009
- Grand challenges in Clinical Decision Support Journal of Biomedical Informatics 41(2008) 387* 392
- Determinants of Success of Inpatient Clinical Information Systems: A Literature Review. M J van der Meijden, H J Tange, J Troost, et al. JAMIA 2003 10: 235* 243
- Improving Outcomes with Clinical Decision Support: An Implementer's Guide [Paperback]: Jerry Osheroff, Jonathan Teich, Donald Levick, Luis Saldana, Ferdinand Velasco, Dean Sittig, Kendall Rogers and Robert Jenders