Clinical Decision Support Systems

1
Clinical Decision Support Systems
Dimitar Hristovski, Ph.D.E-mail
dimitar.hristovski_at_mf.uni-lj.si Institute of
Biomedical InformaticsMedical FacultyUniversity
of Ljubljana, Slovenia
2
Definition

• A medical decision-support system is any computer
  program designed to help health professionals
  make clinical decisions.
• In a sense, any computer system that deals with
  clinical data or medical knowledge is intended to
  provide decision support.
• Three types of decision-support function, ranging
  from generalized to patient specific.

3
Tools for Information Management

• Examples
• Hospital information systems
• Bibliographic retrieval systems (PubMed)
• Specialized knowledge-management workstations
  (e.g. electronic textbooks, )
• These tools provide the data and knowledge
  needed, but they do not help to apply that
  information to a particular decision task
  (particular patient)

4
Tools for Focusing Attention

• Examples
• Clinical laboratory systems that flag abnormal
  values or that provide lists of possible
  explanations for those abnormalities.
• Pharmacy systems that alert providers to possible
  drug interactions or incorrect drug dosages
• Are designed to remind the physician of diagnoses
  or problems that might be overlooked.

5
Tools for Patient-Specific Consultation

• Provide customized assessments or advice based on
  sets of patient-specific data
• Suggest differential diagnoses
• Advice about additional tests and examinations
• Treatment advice (therapy, surgery, )

6
Alternative (more specific) Definition

• Clinical decision support systems are active
  knowledge systems which use two or more items of
  patient data to generate case-specific advice.
• Main components
• Medical knowledge
• Patient data
• Case-specific advice

7
Characterizing Decision-Support Systems along
Five Dimensions

• System function
• Determining what is true about a patient (e.g.
  correct diagnosis)
• Determining what to do (what test to order, to
  treat or not, what therapy plan )
• The mode for giving advice
• Passive role (physician uses the system when
  advice needed)
• Active role (the system gives advice
  automatically under certain conditions)

8
Passive Systems

• The user has total control
• Requires advice
• Analyses the advice
• Accepts/Rejects the advice
• Domain of use
• Wide domain like internal medicine
• Examples QMR, DXPLAIN
• Narrow domain
• Acute abdominal pain
• Analysis of ECG

9
Passive Systems (cont.)

• Characteristics
• Stand-alone
• Data entry
• System initiative
• User initiative
• Consultation style
• Consulting model
• Critiquing model

10
Active Systems

• The user has partial control
• System gives advice
• User evaluates the advice
• The user accepts/rejects the advice
• Domain of use
• Limited domain
• Drug interactions
• Protocol conformance control
• Laboratory results warnings
• Medical devices control

11
Active Systems (cont.)

• Characteristics
• Built-in/integrated with other system (e.g.
  laboratory information system, or pharmacy
  system)
• Data entry
• By the user
• Related to the main application
• Consultation style
• Critiquing model
• Examples
• HELP (advices and reminders, therapy)
• CARE (reminders)

12

• Consultation style
• The system operates under consulting model
• The system operates under critiquing model
• ATTENDING (anesthesia)
• HELP
• ONCOCIN (oncology, therapy plan)

13
Underlying Decision-Science Methodology

• Problem-specific algorithms
• Pattern recognition
• Statistical methods (Bayesian statistics,
  decision analysis, )
• Artificial intelligence (knowledge-based systems)
• Expert systems (MYCIN therapy selection for
  patients with bacteremia or meningitis)
• Machine learning
• Neural networks
• Knowledge representation formalisms
• Decision trees
• Decision rules

14
Example Decision Tree 1
15
Example Decision Tree 2
16
Example Decision Rule 1
17
System MYCIN a Decision Rule
18
System MYCIN Explanation Example
19
System HELP MLM Example (Medical Logic Module)
20
System ONCOCIN Cancer-Treatment Protocol Example
21

• Human factors
• Logistics
• User interface
• Psychology of human-computer interaction
• Legal and regulatory questions
• Integration
• Stand-alone systems have no future
• Data have to be entered only once
• Advice integrated in the basic information system
  (e.g. electronic medical record)

22
General Architecture of a Knowledge-Based
Clinical Decision Support System
Knowledge base
Data Entry
Inference Mechanism
User
diagnosis
explanations
questions
Patient
Therapy
23

• Characteristics of modern knowledge-based
  decision support systems
• The used medical knowledge (knowledge base)
  separated from the mechanisms using that
  knowledge (inference mechanisms)
• Medical knowledge acquisition
• Experts
• Medical literature
• Automatically from medical data(induction,
  machine learning)

24
Example DXplain

• Can be accessed at http//www.mf.uni-lj.si/cmk

25
(No Transcript)
26
(No Transcript)
27
(No Transcript)
28
(No Transcript)
29
(No Transcript)
30
Disease Information
31
Symptom Information
32
(No Transcript)
33
(No Transcript)
34
(No Transcript)
35
(No Transcript)
36
(No Transcript)