Sie sind auf Seite 1von 3

SETH- CLINICAL DECISION SUPPORT SYSTEM DEVELOPMENT VIEW

SETH is a Decision Support System which is to assist the clinicians in their clinical
procedures. This is a non- knowledge based type of decision support system which is
both adaptive (In the sense that it can learn new data) and unsupervised (In the
sense that system can learn from data without any help from knowledge engineer).
How ever at the initial state if the system deployment and in providing for certain
functionalities it will act as a rule based system (knowledge based type).
Below (Figure 1) is the component diagram of the system.

Figure 1

Inference Engine:
Uses the database to extract rules and facts.
The inference engine combines the rules from the knowledge base with the
patients data.
The inference engine is employed during a consultation session, examines the
status of the knowledge base, handles the content of the knowledge base and
determines the order in which inferences are made.
Do pattern matching on data, do data mining. Identify patterns.
Knowledgebase:

The rules and associations of compiled data

The knowledge may be in the form of facts, heuristics (e.g. experiences,


opinions, judgments, predictions, algorithms) and relationships usually
gleaned from the mind of experts through specific knowledge acquisition
methods (e.g. interview) in the relevant domain.
Data acquisition Module:
Controls how the expert and knowledge engineer interact with the program to
incorporate knowledge into the knowledge base
Includes features to assist experts in expressing their knowledge in a form
suitable for reasoning by the computer
External communication management:

Handle communication of the system with external databases, documents and


other electronic devices through which patient data could be fed in to system.

They types of communication, dependencies between components, and type of


relationship between them is displayed in the diagram.
Figure 2 shows the package diagram at an abstract level. It identifies the main
packages under which development should be done, and their communication. Each
package will be composed of several sub packages which will be stated in detail later.

Knowledgebase

Standard User
Communication
Model
Inference Engine

Data Acquisition
Model

External Communication
Management Module
Figure 2

Knowledgebase:
This package will contain the
metadata classes for four types
of data. Production memory,
Working memory, Statistical
data and Performance and
Features data.

Three sub packages to handle


communication with three
types of external systems. With
in each sub package will
contain different packages for
each external system.

The communication mechanism will allow


the system to show the results to the user
as well as have input into the system. It
mainly includes screen displays, a
consultation/advice dialogue and an
explanation component.
Expert knowledge acquisition model
collects information from the experts
providing suitable interface to them to
communicate with the system. The
knowledge engineer data acquisition
model
provides
interfaces
and
communicates with knowledge engineer
(The person trained or experienced in the
design, development, implementation, and
maintenance of the expert system).
Documented knowledge acquisition model
collects data that are in the form of
electronic forms etc.

The first three modules, Comparison


module,
Grammar
interpreter
and
Grammar evaluation model are there to
identify the input data coming from the
user via standard interface module. By
understanding the command system can
process it and find the solution.
The statistical data analysis module and
pattern extraction modules comprise the
data mining subsystem. Pattern identifying
and extracting software mines the
transformed data to identify patterns or fit
models to the data. The module provides
automatic
knowledge
acquisition
(patterns/models) from the data.
The last three modules, performs advanced
checks using special rules that offer a
quality process monitoring and analysis.
When a fault is diagnosed the engine
inferences the fault scenario and proposes
the necessary restoration actions.

Das könnte Ihnen auch gefallen