CLINICAL DECISION
SUPPORT SYSTEM (CDSS)
PRESENTED BY,
ROLL N O – 08 AN D 29
M BA (HCA) – 4T H SEM
INTRODUCTION
A clinical decision-support system is a computer program
designed to help health professionals make clinical
decisions.
A working definition has been proposed by Dr. Robert
Hayward of the center for Health Evidence; “clinical
Decision Support System link health observation with
health knowledge to influence health choices by clinicians
for improved health care”.
HISTORY OF CDS
Phase of relationship Duration hallmarks
A long infatuation 1960-1985 Enthusiasm for clinical
decision support, research,
new ideas.
A troubled courtship 1985-1998 Successful implementations,
evaluations showing benefit,
but limited dissemination
Renewed passions 1998-2003 Knowledge explosion, safety
and quality agendas
Building the foundations for a 2003 National agendas, call to
lasting relationship action, roll out of electronic
health records (EHRs),
computer-based provider
order entry (CPOE), electronic
prescribing (eRx), personal
health records (PHRs)
A new party to the relationship 2004 Recognizing knowledge
management as a necessary
infrastructure
Purposes
To assist clinicians To make decisions To assist forces the
1)
3)
2)
at the point of care. for the clinician. clinician to interact
with the CDSS
utilizing both the
clinician’s
knowledge and the
CDSS to make a
better analysis of
the patients data
than either human
or CDSS could
make on their own.
Features of CDSS
•To make data about a •Physicians, a nurse, a
patient easier to assess. laboratory
•More apparent to a human technologist, a
•optimal problem-solving, pharmacist, a patient.
decision-making and action •Computer
by the human. programmer
General
aim Users
Primary
task Result
• To select knowledge • To perform some
that is pertinent. action- usually
• Patient-specific data recommendation.
-> relevance of the
CDS enhanced
Types of
CDSS
Non-
Knowledge-
knowledge
based
based
Knowledge-based systems
This are artificial intelligent tools working in a
narrow domain to provide intelligent decisions with
justification.
The basic advantages offered by such systems are
documentation of knowledge, intelligent decision
support, self learning, reasoning and explanation.
Features of a knowledge-based CDSS
Systems of this type are built on top of a knowledge base in
which every piece of data is structured in the form of if-then
rules.
Example:- if a new order for a blood test is placed and if the
same blood test was made within the past 24 hours, then a
duplication is possible.
The interference engine runs the built-in logic to combine the
evidence-based rules with the patient’s medical history and
data on patient’s current condition.
The results come in the form of alerts, reminders, diagnostic
suggestions, a series of treatment options or ranked lists of
possible solutions while the final word rests with a human
expert.
Non-knowledge based systems
This system do not use knowledge base, it use a form
of artificial intelligence called machine learning,
which allow computers to learn from past
experiences and find pattern in clinical data.
Two types of non-knowledge based systems are :
1. Artificial neural networks (ANN)
2. Genetic algorithms (GA)
1) Artificial neural networks
They use nodes and weighted connections between
them to analyze the patterns found in the patient
data to derive the associations between the
symptoms and a diagnosis.
This eliminates the need for writing rules and for
expert input.
However since the system cannot explain the reason
it uses the data the way it does, most clinicians don’t
use them for reliability and accountability reasons.
2) Genetic algorithms
This are based on simplified evolutionary processes
using direct selection to achieve optimal CDSS
results.
Genetic algorithms reflecting the mechanics of
natural selection described by charles Darwin, just as
species change from generation to generation to
better fit their environment, Gas adapt to a new task,
producing a number of random solutions and then
relatively evaluating and improving them until the
most fitting options is found.
Applicability of CDSS in healthcare
Drug
selection
AUC for
medicare Diagnosti
patients c support
Clinical Cost
manageme containme
nt nt
Advantages and disadvantages of CDSS
Advantages Disadvantages
1. Integrative virtual work environment 1. Costly
2. Easy to use 2. Training
3. Accessibility and availability 3. User resistance
• Portable
• Multiple user view
4. Messaging and alerts 4. Workflow disruptions (i.e, electronic
note entry and documentation)
5. Patient care safety 5. Inadequate results display
• Legibility
• Audit trails
6. Error reduction 6. Technical issues (i.e, network, interface)
• Computerized order entry
• Computerized decision support
7. Information capture and management
• Quality improvement
• Research
Challenges and possible drawbacks
Alert fatigue Integration
issues
Lack of
interoperability Cost of adoption
Role of healthcare administrator in CDSS
1. Aligning to workflow
2. Provide training to employees
3. Figuring out incomplete data
4. Ensuring data quality
5. Daily reports
6. Operations management
7. Management reports
a) Patient load
b) Compliance
c) Quality of care
d) Financial viability
