Sie sind auf Seite 1von 9

Abstract

The paper provides an overview of the development of medical diagnosis from a machine learning
perspective. The paper is not intended to provide a comprehensive overview but rather describes
some subareas and directions which from our point of view it seem to be important for applying
machine learning in medical diagnosis. The Medical Diagnostic System has been built using expert
system techniques. Expert Systems are useful in capturing rare knowledge from a human expert
into a computer system, thereby allowing a non-expert to be able to use the knowledge captured
into the computer to solve problems from the associated problem domain. In this system a
framework where the knowledge based system approach is applied to assist attend to patients. The
resulting prototype that was designed was evaluated by doctors and system analysts, and found to
be acceptable. They also found the system interface acceptable.
1. Introduction

Increasing computer-based methods improve the quality of medical services. Artificial Intelligence
(AI) is the area of computer science focusing on creating machines that can engage on behaviors
that humans consider intelligent. One of the most important areas of Artificial Intelligence (AI) is
an Expert system. The proposed system for dealing with the problem of diseases diagnosis and
treatment is an expert system. Expert System (ES) is widely used in many areas and it has many
applications. Most important fields area of expert system is the medicine and it use in detection,
diagnosing symptoms and treatment diseases. The user can interact with a computer to solve a
certain problem by expert system. This is because the expert system can store heuristic knowledge.
The reason for Visual prolog program is the flexibility the expandability and low lost. This helps
medical expert (doctor) diagnosis of a patient rightly.
1. 1. Back Ground Of The Study
Computer programs that could in some sense think that is solve problems in a way that would be
considered intelligent if done by a human. Artificial intelligence imitates both the basic problem
solving and learning process of human beings. "In the sixties, AI scientists tried to simulate the
complicated process of thinking by finding general methods for solving broad classes of problems
they used these methods in general purpose programs. However, despite some interesting progress
this strategy produced no breakthroughs. Developing general purpose programs was too difficult
and ultimately fruitless. The problem solving power of a program comes from knowledge it
possesses not just from the formalisms and inference schemes it employs. This realization led to
the development of special purpose computer programs, systems that were expert in some narrow
problem area. These programs were called expert systems. This knowledge can often be accessed
much faster and with greater accuracy in a computer than from the human expert. Within the last
few years, research in the field of artificial intelligence has grown significantly. In the area of
medical diagnosis, have proven successful enough to motivate the investigation of similar expert
systems in others fields of study. One such product related to medical diagnosis, besides equipment
maintenance expert systems in commercial and industrial environments, has recently been put into
service by ANALYTICS.
1.2. Proposed System Description
The proposed system has knowledge base for seven different disease. The user is asked to answer
with Yes or No if a certain symptom appears or not. In the end based on the user’s answers the
name of the disease is posted up on the screen. Disadvantage of this system (and usually of any
other Expert System) is that only the symptoms put in the knowledge base by the programmer are
available. It doesn’t think and doesn’t learn by itself, but the knowledge base can be updated
anytime with new symptoms and new diseases. The knowledge base can be improved with new
diseases and even new symptoms. An important way of improving this Expert System is using
fuzzy techniques. In this case the system would establish the degree that the diagnosis is close to
the reality.
2. Statements Of The Problem
Identifying the disorder afflicting a patient is one of the tasks a doctor faced with in his or her day
to day work. This helps the doctor know what medicine to administer. To practice as a doctor, it
requires some training. Sometimes the doctor may not be available for consultation either for
treatment or training as the case may be, the human expert may be on leave or even absent because
of sickness. Under such circumstances, an intern or non expert can use the proposed expert system
to identify and manage the disorder or as a training tool.

2.1. Existing System Description

Medical expert system a huge figure of expert systems in medicine. The main aim of any medical
expert system is identification and cure of diseases. A medical diagnosis is built up of medical
knowledge base. The information obtained from medical diagnosis is similar to the information
given by proficient in that particular area .Medical Knowledge of specialized doctor is vital for the
growth of medical diagnosis. This knowledge is composed in two phases. In the first phase, the
medical conditions of diseases are recorded during the formation of personal meeting with doctors
and patients. In the second phase, a deposit of rules is formed where each rule contains IF part that
has the symptoms and THEN part that has the disease that should be realized.
2.2. Problem Of The Existing System
The main objective of this phase was to identify, characterize, and define the problems the system
will be expected to solve. The main problems identified include:
 Shortage of specialist
 The other medical staff in the Division needed expert knowledge and guidance
 Problem during diagnosis
3. Objectives
3.1. General Objectives
The main objective of this project was to develop prolog based system for medical diagnosis.
3.2. Specific Objectives
The particular objectives are as follows:

 That can identify a disorder when given the corresponding symptoms.


 That provides a very user friendly interface that is simple and easy to learn and use.
 That makes traditional medicine knowledge more widely available.
 That helps preserve traditional medicinal knowledge.
 Quantify, through the implementation, the amount of information processing necessary to
sufficiently diagnose the symptom of diseases.
 Evaluate the problems encountered in implementation when a rule-based expert system is
chosen as a basis.
 As far as the effectiveness of programming languages is concerned, evaluate the efficiency
and ease of use of PROLOG throughout the implementation. [1]
4. Scope Of The Project
4.1. In Scope
The scope of our system is:
 Medical diagnosis on Ebola, flu, chicken pox, measles, common cold and
mumps.
 Give advice to the patient
4.2. Out Scope
 The out scope or our system excludes the other extra disease
 Do not give any suggestion how to use the prescribed medicine.
5. Significance Of The Project
 The system enable the patient to get good treatment
 The system enable the hospital to minimize human power and cost.
 The system give accurate diagnosis for the patient

6. Beneficiary Of The Project


Our system has different benefit for difference area. Those are:-
For medical employee: the system used to minimize time used during diagnosis
For patient: the system enable the patient to know the disease without any fault, because the
system use the correct symptoms of the disease.
Generally our system used for medical organizations to minimize cost and time consuming to
diagnose the disease.
7. Methodologies
7.1. Method Of Data Collection

We use two type of data collection method

1. Primary data collection method


 Personal communication: we have gathered data through personal communication
with the doctors and other expert.

2. Secondary data collection method

Secondary sources are those which are published or processed materials. I have collected
secondary data from the following sources-
 Various types of official documents
 Some published research report, books, journal and articles.
7.2. Project Development Tool
In order to develop this system we have used various tools such as:-

Software tools

 Prolog software
 Sublime text editor
 Microsoft word 2013
Hardware tools
 Computer
 Flash

7.3. Knowledge Acquisition Method


The knowledge acquisition methods used in this study include: interview schedules, analysis of
documents and Observation. In some instances, during the knowledge acquisition, the doctors were
asked to verbally perform the diagnosis and treatment process loudly, a process known as protocol
or task analysis. Some of the questions asked included
 What is the symptoms?
 What are the symptoms of the different types of disease?
 How are the different types of disease diagnosed?
 How are the different types of disease treated?
 What medical rules or protocols guiding the diagnosis and treatment of disease are in
place?
Knowledge acquisition is a time consuming process in which the knowledge engineer works
alongside the participating expert and extracts, structures and organizes the information to be
represented in the expert system. Knowledge acquisition requires no standard methodology for
extracting knowledge. However, it usually involves a progressive number of personal interviews
of the expert(s) to record information pertinent to the knowledge base. Occasionally, the role of
the knowledge engineer can be significantly reduced if the understanding of the development
processes by the participating experts are substantial and they are willing, able to organize and
express all the necessary information into facts or rules based on their personal heuristics. [2]
8. Knowledge Modeling
Knowledge modeling is a process of creating a computer interpretable model of knowledge or
standard specifications about a kind of process and/or about a kind of facility or product.
9. Knowledge Representation
Knowledge representation and reasoning (KR) is the field of artificial intelligence (AI)
dedicated to representing information about the world in a form that a computer system can utilize
to solve complex tasks such as diagnosing a medical condition or having a dialog in a natural
language. Knowledge representation incorporates findings from psychology about how humans
solve problems and represent knowledge in order to design formalisms that will make complex
systems easier to design and build. Knowledge representation and reasoning also incorporates
findings from logic to automate various kinds of reasoning, such as the application of rules or the
relations of sets and subsets.
After the domain has been identified and knowledge acquired from a participating expert, a model
for representing the knowledge must be developed. Numerous techniques for handling information
in the knowledge base are available; however, most expert systems utilize rule-based approaches.
The knowledge engineer, working with the expert, must try to define the best structure possible.
Other commonly used approaches include decision trees, blackboard systems and object oriented
programming. [3]
10.Project GUI
The user interface is used to gather symptoms and region of residence from the user. It then sends
this information to the inference engine. For its part, the inference engine matches the symptoms
and region of residence provided with those in the knowledge base. If a match is found, the
associated disorder and corresponding treatment advice is given to the user through the user
interface. If a match is not found, it gives appropriate response again through the user interface.
11.Conclusion
Taking into account the fact that we are dealing with a person’s health and we have to put an
approximate diagnosis on a certain disease, this system used in practice implies a great risk. In
reality there are some diseases we have in this system’s knowledge base. Therefore, our knowledge
base is not complete, but we can update and improve it anytime with new symptoms and new
diseases. On the other hand, it is possible that the symptoms already present are not 100% right,
because different experts have different opinions and there are a lot of anomalies in Medicine.

Due to the shortage of specialist and the scarcity of the much needed expert knowledge to guide
the other medical staff. There was therefore a need to come up with a more effective supportive
system for solving this problem characterized by many patients, but few specialists, even if
partially, by creating an expert knowledge sharing tool. The Medical expert system (MES) would
be handy in sharing the much needed expert knowledge in the diagnosis and treatment. Since it
would be used by medical officers, clinical officers and nurses in the absence of specialists.
12. Recommendation
Expert systems development is an area of computing that tries to replace a human expert by having
all the knowledge of a particular area captured in an electronic database. Therefore, some necessary
information might have been omitted in the knowledge base of this project. To come up with an
efficient and user friendly system, it is necessary to have enhanced implementation languages or
tools. Such tools should have capability of adding rules to the knowledge base online and ability
to control memory allocation size among other necessary requirements. Outputting the name of
the identified disorder together with the name and picture of the plant to be used in managing the
disorder will make the user surer of the way forward. The local name could also help those without
knowledge of botanical names know what plants to use without a lot of help. As is clear from this
thesis, a full implementation of our system is quite possible. A better diagnostic expert system
could support a user by graphic enhancements. The location of a component, the necessary steps
to access the component, and some specific procedures to make a measurement could be displayed
to an unexperienced mechanic graphically.
An expert system should be able to explain its reasoning path for teaching and debugging purposes.
We could enhance our expert system with that feature.
References

[1] T. S. A. A., Diagnostic Support System, 2001.

[2] E. ROVENğA, PROLOG EXPERT SYSTEM: medical diagnosis, 2006.

[3] R. Soltan, Diagnosis of Some Diseases in Medicine via computerized Experts, 2013.

Das könnte Ihnen auch gefallen