Difference between revisions of "CDS"

Revision as of 17:59, 7 October 2011

Clinical Decision Support (CDS) refers broadly to providing clinicians or patients with clinical knowledge and patient-related information, intelligently filtered or presented at appropriate times, to enhance patient care. Clinical knowledge of interest could range from simple facts and relationships to best practices for managing patients with specific disease states, new medical knowledge from clinical research and other types of information.

Clinical Decision Support overview

• National Roadmap for Clinical Decision Support
• History of decision support
• General system features associated with improvements in clinical practice
• Support Decisions with Diagnostic Aids
• Clinical Decision Support Liability

Overview

For an overview of the process that healthcare organizations can use to begin, or improve, a clinical decision support (CDS) initiative interested parties can follow the guidelines described in Improving Outcomes with Clinical Decision Suppport: An Implementer's Guide to measurably improve key healthcare outcomes such as the quality, safety, and cost-effectiveness of care delivery.

Modes of Interaction

• Interpretation
• Consultation
• Monitoring
• Critiquing
• Teaching

Order Set

An order set is a group of related orders which a physician can place with a few keystrokes or mouse clicks. An order set allows users to issue prepackaged groups of orders that apply to a specified diagnosis or a particular period of time. [1][2] One of the main impetuses for order sets comes from the need to improve user acceptance of computer-based physician order entry, by decreasing the time physicians require to enter orders. Using order sets reduces both time spent entering orders and terminal usage. [3]

Benefits

There are many reported benefits of order sets. Order sets represent a potential solution to the time constraints of busy physicians and may even improve quality and safety. Obstacles to overcome would include physician acceptance, costs of creation and maintenance, and user interface issues. [4]

1. Reduction of transcription errors.
2. Promotion of adherence to consistent standards of care
3. Focus attention upon unique features of a patient.
4. Quicker order entry
5. Reduction in delays due to inconsistent or incomplete orders

Personal order sets

Individuals may create their own personal order sets by a variety of methods, and some are even available on the internet. In addition, some institutions have developed modifiable templates that allow physicians to customize their own order sets. [5] Mostly, however, order sets are developed by a group of physicians or a department with a particular clinical focus. They then come up with a set of diagnostic and treatment options that encompass current best practices. This latter approach results in a more limited number of order sets, and is easier to manage. [6] [7]

• Personal order set
• Functional specifications
• Criteria for creating new order sets
• A Process for Creating and Maintaining Order Sets
• Most commonly used Order Sets in In-patient Setting

Information Resources

• [The HIMSS Clinical Decision Support (CDS) Task Force wiki]
• Alerts and Reminders
• Alert Fatigue?
• Alert placement in clinical workflow
• Initial Selection of What to Alert on...
• Alerts versus on-demand CDS
• Sources of clinical decision support content

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. An AI system could be running within electronic medical record system, and alert a clinician when it detects a contraindication to a planned treatment. It could also alert the clinician when it detected patterns in clinical data that suggested significant changes in a patient’s condition. The definition of artificial intelligence has changed over the years, since 1956 till now. It is mostly found in data rich areas like intensive care settings There are many different types of clinical task to which Artificial intelligence can be applied.

1. Monitoring patients vital signs and then evaluating and administering the right amounts of different drugs needed
2. Planning an adequate nutritional support for maintaining the metabolic needs of newborn infants. Control of the level of pressure support ventilation.
3. Reading of the electrocardiogram (ECG).

There are numerous reasons why more expert systems are not in routine use. Some require the existence of an electronic medical record system to supply their data and most institutions do not yet have all their working data available electronically. Much of the difficulty has been the poor way in which they have fitted into clinical practice, which required additional effort from already busy individuals.

Examples of AI that are still in practice samrtcare/pc ventilator manager, 2004. VIE-PNN Neo-natal parentral nutrition 1993. Examples of decommissioned AI are: N‘eoGaneshVentilator manager, 1992. ACORN Coronary care admission ,1987. By Bassima Hammoud

Business Intelligence and Data Warehousing

• Business Intelligence & Data Warehousing for Healthcare
• Clinical Data Warehousing

Medication-related Clinical Decision Support

Basic Medication-Related Decision Support

• Drug-Allergy Interactions
• Basic Dosing Guidance for medications in CPOE
• Formulary Decision Support
• Duplicate Therapy Checking
• Drug-Drug interaction

Advanced Medication-Related Decision Support

• Advanced Dosing Guidance in CPOE
• Patient Characteristic dosing support
• Drug-Laboratory Interactions
• Advanced Checking of Drug-Disease Interactinos and Contraindications
• Medications to be avoided in the elderly
• Medications requiring dosage adjustments in renal insufficiency
• Medications requiring dosage adjustments in hepatic disease
• Medications to be avoided during pregnancy
• Medications to be avoided while breastfeeding
• Vaccination contraindications
• Common Corollary orders
• Drug-Food Interactions
• Drug-Tobacco Interactions

Adverse Drug Events

• Detection of Adverse Mediation-Related Events

• List of 39 Warning Messages Targeting Prescribing Decisions Designed to Prevent Adverse Drug Events in Long-Term Care

Non-Medication-Based Safety Rules

• Diagnosis-Order Rules

Validation and Verification of Clinical Decision Support

• On Validation and Verification Of Decision Support Protocol Subsystems During Implementation-Optimization: Encapsulating P(X)

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") [8]
• Weight-based Heparin Dosing Guidelines
• Flowchart-based decision support sample content
• Preventive care reminders

References

1. Franklin, MJ, et al, Modifiable Templates Facilitate Customization of Physician Order Entry, [9]
2. Sittig, DF, and Stead, WW, Computer-based Order Entry: The State of the Art, J Am Med Informatics Assoc., 1994;1:108-123. [10]
3. 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. [11]
4. Southern Ohio Medical Center, [12]