Abstract: diseases cause morbidity and sudden death. Moreover,

Abstract: Chest diseases are a subgroup of respiratory
system diseases. We gathered Information about fourteen diseases, which attack
the chest, with their symptoms and investigations. In this paper, we present an
Arabic ontology based approach for chest diseases diagnosis. It can be used to
help physicians and other users, determining the chest disease which patient is
suffering from and what are investigations should be applied.Keywords: Semantic Web, Knowledge Representation, Ontology Development, Sparql
IntroductionNo one can ignore the importance of the
respiratory system as one of the most important systems in the human body,
which provides it with oxygen gas. Therefore, any trouble in its function will
lead to death. Several diseases can infect
the respiratory system each of them attacks at least one organ and has a set of
signs and symptoms.  Therefore, the early
detection of any defect in respiratory system functions stands at the top of
doctor’s tasks.However, the diagnostic
process is not an easy process due to the complexity of the human body and
overlapping phenotypes. For that reason, computer science can be helpful to
support physicians in diagnosing’s process. So building an ontology can ease
the process of the chest disease diagnosis. There is no research- to our
knowledge- uses ontologies to serve chest diseases in Arabic. So creating an
ontology will facilitate the diagnosis for doctors, by providing the system with
the patient’s symptoms and signs, which will query the ontology and return the
expected disease. The rest of this paper is organized as the following: Section
2 introduces a medical background about chest diseases. Section 3 gives a
background about ontology development and disease diagnosis. Section 4 presents
the methodology of ontology development. Section 5 contains the implementation.
Section 6 discusses the evaluation of the ontology. The last section, section
7, contains the conclusion and future work. 2.  
BackgroundMainly respiratory system diseases
cause morbidity and sudden death. Moreover, the most high-profile conditions in
world health terms contain diseases such as tuberculosis, pandemic influenza
and pneumonia. In addition, the overall burden of chronic disease in the
community is increased by the prevalence of allergy, asthma and chronic
obstructive pulmonary disease. The initiative to deal with respiratory diseases
embraces the basis of medical science and covers a breadth of pathologies.
Recent advances have improved the lives of many patients with obstructive lung
disease, cystic fibrosis and pulmonary hypertension, but the outlook remains
poor for lung and other respiratory cancers, and for some of the fibro sing
lung conditions 1. 3.  
WorksThere are many works in the
domain of ontology development and disease diagnosis. They are discussed in
this section.In 2 researchers suggest a
system methodology, which
contains three basic modules, namely, the diagnostic module, the staging module
and the treatment recommendation module. In order to detect patient disease,
the patient provides his/her signs and symptoms to the diagnostic module, which
detects what type of cancer the patient is suffering from. Once the type of the
cancer is determined, the staging module finds the current stage of the cancer
based on the cancer type, signs and symptoms that are provided by the patient.
Based on the determined cancer type and cancer stage, the treatment
recommendation module can recommend a specific treatment for the case at hand.In 3 researchers discuss the
problem of knowledge acquisition, which considered as a bottleneck in the
process of developing such systems. The researchers propose an inference method according to the case
at hand. The system was designed to utilize the simplified medical knowledge,
by taking the ontology and the symptoms as input. Then in the first phase, the system returns a set of
diseases. Thus, if the number of these returned diseases is one, then the
process of diagnosing is finished. However, if the number of returning diseases
greater than one, the differential diagnosing process begins, here the system
retrieves similar cases through semantic way depending on a knowledge model.In 4 Cristina Romero Tris proposed a decision
support system, which is built based on knowledge base to help physicians in
the diagnosis process, and to verify the diagnosis
made by the doctor. Therefore, if the doctor inputs a
disease that is not related to the symptoms, the system will notify the doctor
of the inconsistency. Moreover, it will suggest the disease that best fits the
symptoms inputted by the doctor. The proposed system aims to personalize
existing knowledge through the extraction of a partial ontology, which contains
the medical terms that belong to the patient.In 5 Lakshman Jayaratne proposes a decision support system based on
ontology. The proposed system composed of two components genotype component and
phenotype component. The initial input of
the system is genetic sequences of a patient. Firstly, the system identifies
whether the input gene is mutated or not with respect to the reference gene
sequences. Then, according to those mutations, a corresponding common list of
phenotypes are identified and shown to the physician. They are listed down
according to the frequency and probability of phenotypes that might occur. The physician
must first make sure that the phenotypes given by the system are really in the
patient’s body, and can then get the diagnostics report after choosing the
matching phenotype from those listed by the system.In 6 Researchers proposed a framework composed of three phases
wherein the first phase is a text analysis technique would be applied to
medical records. In the second phase, the semantic analysis process is applied
to store the information extracted from the first phase in a knowledge base,
and the last phase involves querying the knowledge base to get the related
medical information. Here, they use medical rules to infer additional medical
facts about the patients and to generate a rich knowledge base of patient facts.In 7 Researchers proposed an approach based on the ontology to
diagnose the disease and suggest appropriate treatment by identifying anomalous
observations on the parts of the tree. The approach consists of three
interrelated modules: knowledge base, reasoning engine and server-side
application. The knowledge base is built using OWL ontology and contains
knowledge related to date palm diseases and insect pests. The reasoning engine
accepts user input queries and responses to data through the I/O interface by analysing the acquired dynamic information
together with the static knowledge stored in the knowledge base. The web
application works as an interface to the system, where the user enters his
queries and gets system feedback and an answer. The system was evaluated by a
human expert in plant diseases by comparing his disease diagnoses to those of
the system, the system showed good accuracy, the results were 83.5% accurate
compared to documented scientific answers. In addition, the ontology was
evaluated using the task based framework and it indicates an accuracy of 100%
and 97.6% when using the precision and recall method. 4.  
DevelopmentIn this section, we present the steps to develop an
ontology for chest disease diagnoses (CDDOnto) using development environment namely protégé.The proposed CDDOnto system will be very important for diagnosing chest
diseases. The ontology content relates to a medical domain and gathered from 8 and from a domain expert who helped to identify
concepts, and relationships between them.There is a wide range of tools available
for creating ontologies such as protégé, SWOOP
and Onto Track. We chose Protégé, because according to 9 it is the most domain-independent
tool.According to 10
building ontology consists of the following steps:·      Determining the Domain of the
OntologyWe cannot build an ontology without any purpose. Defining
ontology domain requires answering some questions:o     What is the domain that the ontology will cover?The domain of the ontology is diagnosing   chest diseases.o     Why to use the ontology?To provide a knowledge base of chest diseases,
symptoms and investigations. It will be used in a system to make diagnoses the
chest diseases and determine the disease.o     What are the questions the ontology should
answer?§  What are the symptoms of a given disease?§  What are the investigations of a given disease?§  What is the disease of giving symptoms?o     Who will use the ontology?The ontology will be
available to the users include patients, physicians and students in the medical field.·      Reusing Existing OntologiesWe have built CDDOnto from scratch since there is not
such ontology.·      Overviewing of the Ontology

We identified fourteen diseases, their symptoms
and investigations and data were needed in the process of diagnosing chest
diseases. Figure 1 illustrates the core classes of the CDDOnto as well as the
relationships among them. It has eight classes, four object properties, and
three data properties.·      Enumerating Terms in
the CDDOntoWe added terms
and properties to the ontology by studying the science of disease diagnosis and
through analysing the structure of disease. The following questions guide our activities
to determine the terms:1)      What are the main
terms that we want to talk about?  The main
terms, we talk about, are disease (???), symptom (???) and investigation (???????).2)     
What are the properties of these terms? What is needed
to be said about those terms?

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now

§  The disease
(???) has the properties has symptom (??_???) and diagnosed by (????_??).§  The symptom
(???) has the property symptom of (???_??).§  The
investigation (???????) has the property diagnoses (????).·     
Defining Class Hierarchy of CDDOntoHere the step starts by defining classes, which are
created in step c. Table 1 shows all classes in the CDDonto in English and
Arabic languages.·     
Defining the Properties of the Classes

There are two types of properties, object
properties and data properties. Object property is used to link object to
object, while data property is used to link an object to XML schema. Once we
defined the classes, we clarified and reflected the internal structure of
classes. Table 2 illustrates the properties of the classes.Figure 2 shows the main
classes in the ontology and the relations (object properties) between them.Figure 3 shows all symptoms and investigation of the
cystic fibrosis disease (i.e. All object properties).We added data properties such as ???, ?????, ??? to the ontology. They are used for giving
a value to an instance of a class. For example, “???” cause of “??????
??????” primary tuberculosis is Mycobacterium tuberculosis “????????? ????????”.The data property is
applicable to each instance of the class. Table 3, illustrate the data
properties of the CDDOnto.·     Defining
the facets of the slotsSlots have different facets that describe the value type, allowed values
and the cardinality of the values slots can take. In our case, all of the slot
values are string using UTF-8 (Arabic). For example, the value type of the “???” property is

1)   Value Type: This
describes the types of values a property can has. The property “???” has the value type string.1)   Allowed values: This
represents values allowed to the properties. The allowed values for the
data property “???” are ???? ???? ???????.2)   Cardinality: this defines how many values a property can
has. The property “???” has multiple cardinality. It allows at least one value.

Figure 4 shows the value type and cardinality of
some of the properties.·     
Create Instances of CDDOntoAdding instances (individuals) of classes in the
ontology. We used an ontology to organize sets of instances. The creation of
individuals allows all the properties of the classes to be recorded. We took
the information of individuals from 8. In CDDOnto, we defined 101
instances that are representing all ontology concepts, including diseases,
symptoms and investigations.·     
Apply Ontology ReasonerAfter creating instances, we
applied an ontology reasoner (e.g. Hermit reasoner). This is necessary to check
that everything is ok and to identify new relations from existing ones. 5.     
CDDONTO Implementation in ProtegeThis section describes the development of CDDOnto in
protégé as an owl ontology. 5.1.  
and SubclassesClasses are the domain concepts and the
building blocks of ontology. In CDDOnto disease (???), symptom (???) and investigation (???????) are subclasses of class Thing. Figure 5
shows the main classes in the ontology, whereas figure 6 shows all.5.2.  
Properties and FacetsIn CDDOnto
Individuals were defined with their data properties. In addition to object
properties between them. Figure 7 shows data taxonomy such as “????????
??????” pulmonary embolism class, which contains three instances.
Pulmonary embolism is a blockage in the pulmonary artery, which supplies the
blood to the lungs.Data Properties are shown in Figure 8 which contains 3
properties, these properties are explained as follows:1- ???
“name”: the ??? refers to the word of circulation of the
disease in the world.2- ???
“Cause”: express an event in the human body, which Cause a disease.3- ???
“Description”: describes either a disease or an investigation.6.   Evaluation of CDDOntoIn this section, we evaluate
the quality of the created ontology in representing all terms, properties, and
relations through disease examples and ontology querying using description
logic query and the SPARQL query.6.1.Quality Evaluation through Disease ExamplesTo evaluate the
quality of the CDDOnto we chose a disease example to check if the ontology
represents terms, properties and relations of a disease sample. See figure 3 we
note that the Cystic fibrosis
(?????? ??????)
is   an individual of inherited (?????) class, which is a subclass of disease (???) class, has
eight symptoms and five investigations. The above example shows that the
ontology represents all needed symptoms and investigations. We can cite many
such examples showing a complete representation of the domain.6.2.Quality Evaluation through Ontology QueryingWe used the Description
Logic Query (DL-Query) that is a standard Protégé plugin to verify and validate
the ontology in accordance to competency questions. We present three querying
examples which answer the main questions that are asked in the development
process of the ontology.Example 1:·      The question: what are the diseases that have the
symptom ‘?????’.·      DL_Query: ???
and ??_??? value ?????.·      Figure 9, shows the result of DL_Query, and
illustrates the individuals of the disease class.Example 2:·     
The question: What are the
symptoms of Cystic
fibrosis disease?·     
DL_Query is: ??? and ???_??
value ??????_?????? Figure 10 shows the result of DL_Query and
illustrates the individuals of symptom class.Example 3:·   The question: what are the investigations of Cystic fibrosis disease?·   DL_Query: ??????? and ???? value ??????_??????

Figure 11 shows the result of
DL_Query, which is a set of investigations should be required by the doctor to
make sure that the disease is Cystic
4:In this
example, we show a SPARQL·      The question: what are the symptoms of Cystic fibrosis disease?·     
Figure 12
shows SPARQL query and the result of the SPARQL query is shown in the figure 13,
which illustrates the symptom’s individuals. That means all these symptoms are
symptoms of the Cystic fibrosis disease. 7. 
ConclusionIn this paper,
we proposed an Arabic ontology-based approach for diagnosing chest diseases. We
focused on the process of building Chest diseases knowledge base. The ontology
content is related to the medical domain and It was gathered from 8 and from
a domain expert. The ontology provides a knowledge base of diseases, symptoms,
and investigations. It will be used in a system to make the diagnoses of the
chest diseases and determine the disease.

In the future, we intend to
build a query engine based on NLP model to enable users writing their queries
using an Arabic natural language since that the target users may do not know
how to write their queries using SPARQL.


I'm William!

Would you like to get a custom essay? How about receiving a customized one?

Check it out