automated medicare decision support system. by ahmed atyya ali radwa saeed ammar rana samy hammady...
TRANSCRIPT
ByAhmed Atyya Ali
Radwa Saeed Ammar
Rana Samy HammadySalsabeel
MouhamedMeriam Mouhamed
Supervised ByDr. Islam T.El
Kabani
Diagnosis
Dataware- house
The Expert System
First the client send the
symptoms and signs for some patient’s ID to
the Server
The server by its role gets the
history and analysis of the
ID from the database
ID
Information
Needed data
Now the data needed for
diagnosis are ready to be sent
to the Expert System
The Expert System sends
back the Diagnosis to the server
And from the Server back to the client with the Diagnosis
The
Main Server
The
Main Server
client
Diagnosis
The Expert System
ID
Information
Needed data
The
Main Server
The
Main Server
client
Dataware- house
Tools used
DBMS : My SQL to make operational database and data warehouse .
Java for the entry client (GUI represent clients and transactions )
Data, Information, Knowledge
DataFacts without meaning
InformationOrganized data that has meaning and value
KnowledgeIt’s the relation between data and information that use for information deduction.
Operational database
Current value data such as analysis data Can be updated Need normalizationIt’s components Data Hardware Software Users
Data warehouse Collection of data in support of
management’s decision-making
Doesn’t need normalization
Non volatile
Time variant
Subject oriented
Multi-Tiered Architecture
DataWarehouse
ExtractTransformLoadRefresh
Engine
Expert system
Monitor&
IntegratorMetadata
Data Sources Front-End Tools
Serve
Data Marts
Operational DBs
other
sources
Data Storage
Server
Data Warehouse Parts
1-The data warehouse itself, which contains the data and associated software
2-Data acquisition (back-end) software, which extracts data from legacy systems and external sources, consolidates and summarize them, and loads them into the data warehouse
3-Client (front-end) software, which allows users to access and analyze data in the warehouse
Diagnosis
Dataware- house
The Expert System
ID
Information
Needed data
The
Main Server
The
Main Server
client
Diagnosis
ID
Information
Needed data
The
Main Server
The
Main Server
client clientclient client
The traffic organizer
Tool UsedJava
The server is a computer program that provides services to other programs in the same or other computers.
What is the main role of the server in the system?
Multithreading
Is the capability of running multiple tasks concurrently within a program
Thread SynchronizationA shared resource may be corrupted if it is accessed simultaneously by multiple threadsThe synchronized keywordTo avoid race conditions
Why is synchronization important in the Medicare System?
The
Main Server
The
Main Server
client clientclient client
The aggregate means by which the doctors interact with the system
It provides means of input which are the symptoms and the signs of patient
And means of output which is the diagnosis of the patient case
Diagnosis
Dataware- house
The Expert System
ID
Information
Needed data
The
Main Server
The
Main Server
client
An Expert System is a program that behaves like an expert for some problem domain.
It should be capable of explaining its decisions and the underlying reasoning.
Ours posses as a physician advisor
Often an Expert System is expected to be able to deal with uncertain and incomplete information.
They are also called knowledge-based systemsas they should posses knowledge in some form
Some times the diagnosis is uncertain
The set of diseases the expert system deal with
Main structure of an expert system
Knowledge base:Comprises the knowledge that is specific to the domain of the applicationAs simple facts about the domainRules that describe relations or phenomenon in the domainIdeas of solving problems in this domainAn inference engine:Knows how to actively use the knowledge in the baseA user interface:Caters for smooth communication between the user and the system
ModularityEach rule defines a small relatively independent piece of knowledge
IncrementabilityNew rules can be added to the knowledge base relatively independently of other rules
Modifiability (as a consequence of modularity)
Old rules can be changed relatively independently of other rules
Support system transparencyThe system’s ability to explain its decisions and solutions
In backward chaining we start with a hypothesis and work backwards according to the rules in the knowledge base
It searches from goals to data, from diagnosis to findings ,etc.
That’s why we coal it goal driven
Backward chaining
Doesn’t start with the hypothesis, but with some confirmed findings
It starts with what is already known, derives all conclusions that follow from this and adds them to the fact relation
From data to goals, from findings to explanation or diagnoses, etc.
That’s why we call it data drivenAnd that’s why ours is forward chaining
Forward chaining
Introducing uncertainty
The representation assumes problem domains that answers all questions by either true or false, not somewhere between
Information about the problem to be solved can be incomplete or unreliable
Relations in the problem domain can be approximate
As we may not be quite sure that some symptom is present in the patient, or that some measurement data is absolutely correct.This requires probabilistic reasoning.
Decision Making
Process of choosing amongst alternative courses of action for the purpose of attaining a goal or goals.
The four phases of the decision process are
IntelligenceDesignChoiceImplementation
Decision-Making Intelligence Phase
Scan the environment
Analyze organizational goalsCollect dataIdentify problemCategorize problem Programmed and non-programmed Decomposed into smaller parts
Assess ownership and responsibility for problem resolution
Decision Support Systems
Intelligence Phase
AutomaticData MiningExpert systems, CRM, neural networks
ManualOLAPKMS
ReportingRoutine and ad hoc
Design Phase
Generation of alternatives by expert system
Relationship identification used in models through OLAP and data mining
Business process modeling using CRM, RMS, ERP, and SCM
Recognition of the problem through KMS
Choice Phase
Identification of best alternative
Identification of good enough alternative
What-if analysis
Goal-seeking analysis
May use KMS, GSS, CRM, ERP, and SCM systems
Implementation Phase
Improved communications
Collaboration
Training
Supported by KMS, expert systems, EIS, GSS
Database Management System
Extracts data
Manages data and their relationships
Updates (add, delete, edit, change)
Retrieves data (accesses it)
Queries and manipulates data (Query Facility)
Employs data dictionary
Components of DSS
- DSS SubsystemsData management
Managed by DBMSModel management
Managed by MBMSUser interfaceKnowledge Management and organizational knowledge base