Clinical Decision support systems Dr Ebtissam Al-Madi
Slide 3
Clinical Decision support systems Clinical Decision Support
Systems are "active knowledge systems which use two or more items
of patient data to generate case-specific advice. Clinical DSSs are
typically designed to integrate a medical knowledge base, patient
data and an inference engine to generate case specific advice.
Slide 4
Functions of CDSS "Administrative: Supporting clinical coding
and documentation, authorization of procedures, and. "Managing
clinical complexity and details: Keeping patients on research and
chemotherapy protocols; tracking orders, referrals follow-up, and
preventive care. "Cost control: Monitoring medication orders;
avoiding duplicate or unnecessary tests. "Decision support:
Supporting clinical diagnosis and treatment plan processes; and
promoting use of best practices, condition-specific guidelines, and
population-based management. "
Slide 5
Examples of early CDSS INTERNIST-I (1974) It uses patient
observations to deduce a list of compatible disease states (based
on a tree-structured database that links diseases with symptoms).
MYCIN (1976) An expert system designed to diagnose and recommend
treatment for certain blood infections and infectious diseases.
Clinical knowledge in MYCIN is represented as a set of IF-THEN
rules with certainty factors attached to diagnoses.
Slide 6
Dxplain: (mid 1980s) Uses a set of clinical findings (signs,
symptoms, laboratory data) to produce a ranked list of diagnoses
which might explain (or be associated with) the clinical
manifestations. DXplain provides justification for why each of
these diseases might be considered, suggests what further clinical
information would be useful to collect for each disease, and lists
what clinical manifestations, if any, would be unusual or atypical
for each of the specific diseases. DXplain includes 2,200 diseases
and 5,000 symptoms in its knowledge base.
Slide 7
Main Benefits of CDSS Improved patient safety e.g. through
reduced medication errors and adverse events and improved
medication and test ordering; Improved quality of care e.g. by
increasing clinicians available time for direct patient care,
increased application of clinical pathways and guidelines,
facilitating the use of up-to-date clinical evidence, improved
clinical documentation and patient satisfaction; Improved
efficiency in health care delivery e.g. by reducing costs through
faster order processing, reductions in test duplication, decreased
adverse events, and changed patterns of drug prescribing favouring
cheaper but equally effective generic brands.
Slide 8
Other benefits Automatic provision of relevant, personalised
expert advice, expertise and recommendations sourced from
up-to-date, best practice knowledge Reduce variation in the quality
of care Can support medical education and training Can help
overcome problems of inefficient coding of data Can be
cost-effective after initial capital costs and update and
maintenance costs Can provide immediate feedback to patients If
integrated with an EMR, can help streamline workflow (history
taking, diagnosis, treatment) and encourage more efficient data
gathering Can provide an audit trail and support research Can
maintain and improve consistency of care Can supply clinical
information anytime, anywhere it's needed.
Slide 9
Drawbacks of CDSS Potential 'deskilling' effect Can be
perceived as a threat to clinical judgment Can be considered too
inflexible (can appear prescriptive, can appear to direct
proceedings; can be difficult to depart from ordered, pre-prepared
paths) Promote over-reliance on software; limit clinicians' freedom
to think ? Difficult to evaluate - lack of accepted evaluation
standards Can be time-consuming to use, possibly lead to longer
clinical encounters and create extra work Uncertain and untested
ethical and legal status Costs: maintenance, support and training
required after initial outlay A clinician's experience and
imagination cannot be duplicated in a computer application.
Slide 10
Factors that will increase use of CDSS Cost Attitude of
targeted users: breadth and depth of commitment Degree of user
acceptance prior to and after installation Ease of use - time
needed to learn to use and to use Type, timing, length of training
to be provided Availablility of support and maintenance
Interoperability: ease/extent of integration with legacy systems
(hardware, other devices) and existing software programs
(integration with patient record and/or any relevant clinical
terminologies would avoid need to re-enter patient data)
Slide 11
Factors that will increase use of CDDS Ease of integration
within organisational context and routine workflow - degee to which
it entails aredesign of clinical processes Legal and ethical issues
User interface: design, structure, number of forms Style, manner of
presentation of advice/ recommendations/ results to user Patients'
attitudes to use Provision of evidence justifying advice and/or
recommendations Involvement of local users during development phase
The quality and reliability of a system and its knowledge base
which should be populated with trusted, up-to-date and maintainable
knowledge
Slide 12
Methodologies of CDSS The basic components of a CDSS include; a
dynamic (medical) knowledge base and an inferencing mechanism
(usually a set of rules derived from the experts and evidence-based
medicine)expertsevidence-based medicine They are implemented
through medical logic modules based on computer languagesmedical
logic modules
Slide 13
Methodologies (cont.) Bayesian Network The Bayesian network is
a knowledge-based graphical representation that shows a set of
variables and their probabilistic relationships between diseases
and symptoms. They are based on conditional probabilities, the
probability of an event given the occurrence of another event, such
as the interpretation of diagnostic tests.Bayesian
networkconditional probabilities Neural Network Artificial Neural
Networks (ANN) is a nonknowledge-based adaptive CDSS that uses a
form of artificial intelligence, also known as machine learning,
that allows the systems to learn from past experiences / examples
and recognizes patterns in clinical information. Artificial Neural
Networks Genetic Algorithms A Genetic Algorithm (GA) is a
nonknowledge-based method. These algorithms rearrange to form
different re- combinations that are better than the previous
solutions. Similar to neural networks, the genetic algorithms
derive their information from patient data.Genetic Algorithm
Rule-Based System A rule-based expert system attempts to capture
knowledge of domain experts into expressions that can be evaluated
known as rules; an example rule might read, "If the patient has
high blood pressure, he or she is at risk for a stroke." Once
enough of these rules have been compiled into a rule base, the
current working knowledge will be evaluated against the rule base
by chaining rules together until a conclusion is reached.expert
system Logical Condition The methodology behind logical condition
is fairly simplistic; given a variable and a bound, check to see if
the variable is within or outside of the bounds and take action
based on the result. An example statement might be "Is the
patient's heart rate less than 50 BPM?" Causal Probabilistic
Network The primary basis behind the causal network methodology is
cause and effect. In a clinical causal probabilistic network, nodes
are used to represent items such as symptoms, patient states or
disease categories. Connections between nodes indicate a cause and
effect relationship.
Slide 14
Examples of CDSS in Dentistry Medical History Dental treatment
plan Endodontics Caries risk Oral Pathology & oral medicine
ect
Slide 15
This weeks assignments Log on to
http://faculty.ksu.edu.sa/ealmadi/182DEN/default.aspx
http://faculty.ksu.edu.sa/ealmadi/182DEN/default.aspx 1.View this
lecture online for review. 2.Article this week: Suggested reading
only. 3.Participate in discussion. 4.Homework: Please answer survey
for your input on course. 5.Quiz: None. ViewReadDiscussHomework
Quiz