Clinical decision support systems

CDSS-1
CSE
300
Clinical Decision Support Systems
Clinical Decision Support Systems
Mohammed Saleem
Mohammed Saleem
CDSS-2
CSE
300
Overview
Overview

Scope of Clinical Decision Support Systems
Scope of Clinical Decision Support Systems

Issues for success or failure
Issues for success or failure

Evaluation of Clinical Decision Support
Evaluation of Clinical Decision Support
Systems
Systems

Computing techniques used to create DSS
Computing techniques used to create DSS

Design Cycle for the development of DSS
Design Cycle for the development of DSS

Early AI/Decision Support Systems.

Early AI/Decision Support Systems.

Open source Example
Open source Example
CDSS-3
CSE
300
Scope of Clinical Decision Support Systems
Scope of Clinical Decision Support Systems

Definition
Definition

Categories of CDSS
Categories of CDSS

System Architecture
System Architecture

Advantages / Need for CDSS
Advantages / Need for CDSS

Applications Areas
Applications Areas

Disadvantages
Disadvantages
CDSS-4
CSE
300

Definition
Definition

A
A
clinical decision-support system
clinical decision-support system
is any
is any
computer program designed to help health
computer program designed to help health
professionals make clinical decisions.
professionals make clinical decisions.

In a sense,
In a sense,
any
any
computer system that deals
computer system that deals
with clinical data or medical knowledge is
with clinical data or medical knowledge is
intended to provide decision support.
intended to provide decision support.

Three types of decision-support function,
Three types of decision-support function,
ranging from generalized to patient specific.
ranging from generalized to patient specific.
CDSS-5

CSE
300
Categories
Categories

Generating alerts and reminders
Generating alerts and reminders

Diagnostic assistance
Diagnostic assistance

Therapy critiquing and planning
Therapy critiquing and planning

Image recognition and interpretation
Image recognition and interpretation
CDSS-6
CSE
300
Inference Engine
Clinical
Data
Reposit o ry
(CDR)
User
Knowledge Base
Event Monitor
Notifier
Recipient(s)
CDSS-7

CSE
300
Tools for Information Management
Tools for Information Management

Examples:
Examples:

Hospital information systems

Bibliographic retrieval systems (PubMed)

Specialized knowledge-management workstations
(e.g. electronic textbooks, …)

These tools provide the data and knowledge
These tools provide the data and knowledge
needed, but they do not help to
needed, but they do not help to
apply
apply
that
that
information to a particular decision task
information to a particular decision task
(particular patient)
(particular patient)
CDSS-8
CSE
300

Tools for Focusing Attention
Tools for Focusing Attention

Examples:
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
Are designed to remind the physician of
diagnoses or problems that might be
diagnoses or problems that might be
overlooked.
overlooked.
CDSS-9
CSE
300
Tools for Patient-Specific Consultation
Tools for Patient-Specific Consultation

Provide customized assessments or advice
Provide customized assessments or advice
based on sets of patient-specific data:
based on sets of patient-specific data:


Suggest differential diagnoses

Advice about additional tests and examinations

Treatment advice (therapy, surgery, …)
CDSS-10
CSE
300
Alternative (more specific) Definition
Alternative (more specific) Definition

Clinical decision support systems are
Clinical decision support systems are
active
active
knowledge systems
knowledge systems
which use two or more
which use two or more
items of patient data to generate case-specific
items of patient data to generate case-specific
advice.
advice.

Main components:
Main components:

Medical knowledge

Patient data


Case-specific advice
CDSS-11
CSE
300
Characterizing Decision-Support Systems
Characterizing Decision-Support Systems

System
System


function
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
The mode for giving advice

Passive role (physician uses the system when
advice needed)

Active role (the system gives advice
automatically under certain conditions)
CDSS-12

CSE
300
Passive Systems
Passive Systems

The user has total control:
The user has total control:

Requires advice

Analyses the advice

Accepts/Rejects the advice

Domain of use:
Domain of use:

Wide domain like internal medicine

Examples: QMR, DXPLAIN

Narrow domain

Acute abdominal pain

Analysis of ECG
CDSS-13
CSE
300
Passive Systems (cont.)

Passive Systems (cont.)

Characteristics:
Characteristics:

Stand-alone

Data entry:

System initiative

User initiative

Consultation style

Consulting model

Critiquing model
CDSS-14
CSE
300
Active Systems
Active Systems

The user has partial control
The user has partial control

System gives advice

User evaluates the advice


The user accepts/rejects the advice

Domain of use
Domain of use

Limited domain

Drug interactions

Protocol conformance control

Laboratory results warnings

Medical devices control
CDSS-15
CSE
300
Active Systems (cont.)
Active Systems (cont.)

Characteristics
Characteristics

Built-in/integrated with other system (e.g. laboratory
information system, or pharmacy system)

Data entry
Data entry


By the user

Related to the main application

Consultation style
Consultation style

Critiquing model

Examples:
Examples:

HELP (advices and reminders, therapy)

CARE (reminders)
CDSS-16
CSE
300
Need for CDSS
Need for CDSS

Limited resources - increased demand
Limited resources - increased demand
Physicians are overwhelmed.
Physicians are overwhelmed.

Insufficient time available for diagnosis and
treatment.

Need for systems that can improve health care

Need for systems that can improve health care
processes and their outcomes in this scenario
processes and their outcomes in this scenario
CDSS-17
CSE
300
Application Areas
Application Areas
CDSS-18
CSE
300
Possible Disadvantages of CDSS
Possible Disadvantages of CDSS

Changing relation between patient and the
Changing relation between patient and the
physician
physician

Limiting professionals’ possibilities for
Limiting professionals’ possibilities for
independent problem solving
independent problem solving

Legal implications - with whom does the onus
Legal implications - with whom does the onus
of responsibility lie?
of responsibility lie?
CDSS-19
CSE

300
Issues for success or failure
Issues for success or failure

Evaluation of User Needs
Evaluation of User Needs

Top management support
Top management support

Commitment of expert
Commitment of expert

Integration Issues
Integration Issues

Human Computer Interface
Human Computer Interface

Incorporation of domain knowledge
Incorporation of domain knowledge

Consideration of social and organisational
Consideration of social and organisational
context of the CDSS
context of the CDSS
CDSS-20
CSE
300
Evaluation of Clinical Decision Support Systems

Evaluation of Clinical Decision Support Systems

Criteria for success of CDSS
Criteria for success of CDSS

Aspects for consideration during evaluation
Aspects for consideration during evaluation
CDSS-21
CSE
300
Criteria for a clinically useful DSS
Criteria for a clinically useful DSS

Knowledge based on best evidence
Knowledge based on best evidence

Knowledge fully covers problem
Knowledge fully covers problem

Knowledge can be updated
Knowledge can be updated

Data actively used drawn from existing
Data actively used drawn from existing
sources
sources

Performance validated rigorously
Performance validated rigorously
CDSS-22

CSE
300
Criteria for a clinically useful DSS (cont.)
Criteria for a clinically useful DSS (cont.)

System improves clinical practice
System improves clinical practice

Clinician is in control
Clinician is in control

The system is easy to use
The system is easy to use

The decisions made are transparent
The decisions made are transparent
CDSS-23
CSE
300
Aspects for Evaluation of a CDSS
Aspects for Evaluation of a CDSS

The process used to develop the system
The process used to develop the system

The systems essential structure
The systems essential structure

Evidence of accuracy, generality and clinical
Evidence of accuracy, generality and clinical

effectiveness
effectiveness

The impact of the resource on patients and
The impact of the resource on patients and
other aspects of the health care environment
other aspects of the health care environment
CDSS-24
CSE
300
Computing techniques used to create DSS
Computing techniques used to create DSS

Machine Learning and Adaptive Computing
Machine Learning and Adaptive Computing

Inductive Tree Methods

Case Based Reasoning

Artificial Neural Networks

Expert Systems - Knowledge based Methods
Expert Systems - Knowledge based Methods

Rule based Systems
CDSS-25
CSE
300
Design Cycle for the development of a CDSS

Design Cycle for the development of a CDSS

Planning Phase
Planning Phase

Research Phase
Research Phase

System Analysis and conceptual phase
System Analysis and conceptual phase

Design Phase
Design Phase

Construction phase
Construction phase

Further Development phase
Further Development phase

Maintenance, documentation and adaptation
Maintenance, documentation and adaptation