TITLE PAGE

DESIGN OF WEB BASED EXPERT SYSTEM FOR DIAGNOSIS OF CANCER USING

RULE BASE ARCHITECTURE

ALIYU ABUBAKAR USMAN

1MT/18D/2214

BEING A PROJECT SUBMITTED TO THE DEPARTMENT OF

INFORMATION MANAGEMENT TECHNOLOGY, FACULTY OF
SOCIAL AND MANAGEMENT
MODIBBO ADAMA UNIVERSITY YOLA, IN A PARTIAL FULFILMENT
OF THE REQUIREMENTS FOR THE AWARD BACHELOR OF TECHNOLOGY
[Link] DEGREE IN INFORMATION MANAGEMENT
TECHNOLOGY

DEC, 2023

i
 DECLARATION

I, Ailyu Abubakar Usman with registration number IMT/181)/2214 due hereby declare this
final year project was originally writes by me solely under the guidance of my project
supervisor Mrs. Aisha Tukur of the Department of Information Technology, Modibbo Adama
University Yola.

Aliyu Abubakar Usman Date

ii
 APPROVAL PAGE

This project report entitled "DESIGN OF WEB BASED EXPERT SYSTEM FOR
DIAGNOSIS OF CANCER USING RULEBASE ARCHITECTURE" the regulations
governing the award of [Link] degree in information management technology in Modibbo
Adama University Yola, and is approved for its contribution to knowledge and literacy
presentation,

Mrs Aisha Tukur Date

(Project supervisor)

[Link] Saad Date

(Project Coordinator)

[Link] Date
(Head of Department)

iii
 DEDICATION

I, dedicate this project to almighty Allah (S W A) for granting me the power, health, ability
and grace through-out my life and academic pursuit to this stage of the Challenges and
obstacles confront in the University.

iv
 ACKNOWLEDGMENTS

All praise is due to Almighty Allah the creator, sustainer, provider, protector, of one and all
for guidance and protection throughout my study. My profound gratitude goes to my
Supervisor Mrs. Aisha Tukur for her time, guidance, patient and understanding throughout
the period of my research work. I would like to express my sincere appreciation to the
Family of Late Abubakar Usman (Buba Gombe) for their prayers, motivations and financial
assistance especially Zainab Buba (Aunty Lami). I will not forget my lovely girlfriend
Hauwa kulu Hanwa (Ummi) for her patient, understanding, financial assistance, and prayers
throughout the period of my study, finally my appreciations to my friends, especially Engr
Nazif Adamu, Danjuma, RN Usman Abubakar Engr. Sadiq Adamu and course mates and
well-wishers.

v
 ABSTRACT
This project involves the design of expert system for diagnosis of cancer using the methods
of rule base. Expert system is the process of capturing human expertise and store in system as
a knowledge base to imitate human in decisions making. This research consider the methods
used for diagnosis especially cancer diagnosis and found that most of them are clinical test
which is not affordable by common people. Iterative waterfall model is the system
development model used in developing this system. Flowchart, use-case diagram, database
design, and entity relationship diagram were used in designing this system. This system has
proved to be effective in diagnosing tropical diseases, hence should be adopted. This system
was able to achieve its goals as it accurately diagnoses four type of cancer namely Breast
cancer, lung cancer, prostate cancer and colorectal cancer by providing seven symptoms for
each

vi
 CHAPTER ONE
INTRODUCTION
1.0 Background to the Study
Expert Systems (ESs) originated from branch of computer science called Artificial Intelligence
(AI), which has the ability to imitate human being, make judgment and reasoning based on
some facts and rules presented to it (Goth & Kulknrni, 2012). Nowadays expert systems have
been widely used in almost all the fields of man's expertise to assist the users in taking decision;
where human expatriation and multifaceted decision making is required, like medical
diagnosis, expert decision making, policy making, estimating strategies, analysis and so on
(Gath & Kulkarni, 2012).

Medical artificial intelligence is primarily concerned with the development of Artificial

Intelligent programs that perform diagnosis and make therapy recommendations. Medical
Expert Systems (MESs) are more likely to be found in clinical laboratories and educational
settings, for clinical surveillance, or in data rich areas like the intensive care setting. What is
now being realized is that, if they are filling with appropriate rule, intelligent programs do
indeed offer significant benefits (Open-Clinical, 2012).

The use of MESs is in full swing since early 70's designed to diagnose bacteria causing severe
infections (Gath & Kulkarni, 2012). There is a lot medical expert system that was developed
to diagnose lung disease which helps physicians to diagnose the narrowing of coronary vessels
by identifying and isolating coronary vessels by monitoring patients in a Newborn Intensive
Care Unit (NICU) (Giarratano, 2009).

A set of rules can be used to capture a human expert's relevant domain knowledge and can then
be used to reproduce the expert's problem solving in that domain. Probabilistic expert systems
derive from research at the intersection of statistics and artificial intelligent (Russell & Norvig,
2002). In DBMSs are used for storing, retrieving and generally manipulating patient data,
whereas ESS are mainly used for performing diagnoses based on patient data since they can
naturally represent the way experts' reason and provide solution to problem at hand (Mahesh,
2009).
Fortunately, researchers have found that AI is able to detect cancer and other diseases earlier
than possible through standard diagnostic methods, which could be lifesaving for future
patients. This has been proven through studies focused on several different types of cancer,

1
including skin cancer and mesothelioma, which have both been detected using AI with more
than 95% accuracy (Suarez, 2018).

Expert system can help solve defined problem through the use of a keyboard, scanner, etc., and
the computer responds with the answer and explanation based on the facts and the rules that
have been extracted from human and experts and stored in the computer. Medical practitioners
are not capable of effectively handling the large amount of information in both medical
research and patient care. Since the development of the electronic computers, the computer has
risen up from a normal research device to a modern-day human helper as such, have an
important and wide spread influence on our society (Agbogun, 2002).

Although, the use of computer in diagnosis has received increasing attention in recent years,
most of this interest is derived from the general desire to provide tools and techniques to
facilitate the solution of diagnostic problem by the physician. This is because significant parts
of diagnosis consist of sifting out numerous possibilities and developing hypothesis about the
state of the health of the patient. This has been the considerable interest in the application of
automation data processing (Agbogun, 2020).

AI is already being used to predict, model and slow the spread of disease in epidemic situations
around the world, including in resource-poor settings. Dengue fever is a vector-borne disease
that has spread rapidly around the globe in recent years. About half of the world's population
is currently at risk. Researchers have developed a machine learning tool to identify weather
and land-use patterns associated with dengue fever transmission in Manila. The machine
learning algorithm has learnt over much iteration how to fine-tune its model to predict dengue
occurrence with increasing accuracy (Hornyak, 2017).

This research work therefore enumerates the need to implement a computerized system to assist
medical field most especially, the area of diagnosing. It also expatiates on how a computer
system is used to "act" like a medical practitioner in diagnosing a disease and refer the patient
to a medical doctor for the necessary prescription of drugs.

1.1 Statement of the Problems

Cancer is one of the leading causes of death worldwide as new cases and deaths from the
disease keep rising (WHO, 2019). Different methods have been used by researchers in
diagnosing cancer however most of which are clinical tests that are not affordable by common
people. It is observed that only few researchers uses expert system in diagnosing cancer, in
2
2015 Yousuf Qawqzeh and Khalid Abdul Saffar develop an expert system for diagnosing breast
cancer using the method of rule base architecture which is limited to only breast cancer.
Therefore, this research intends in developing an expert system using Rule Base Architecture
Expert System that will cover some common cancers, it will provide physical interaction
between patient user and the system, by input symptoms and query the knowledge base the
result will be obtain. If this is achieved, it will be enable common people to get access to cancer
diagnosis faster and at affordable rate.

1.2 Aim and Objectives of the Study

The aim of this research is to enhance method of cancer diagnosis in human in collaboration
with doctors, nurses Rule Base Architecture Expert System.
i. To examine the patients' personal information that will assist in identifying the cancer
ii. To examine the symptom of cancer and diagnosis then refer patients to a medical doctor.
iii. To develop a web-based system that will aid in the diagnosis of patients.

1.3 Significance of the Study

The use of expert system in medical diagnosis may lead to the solution of the conventional
problems in diagnostic procedures. Expert system for medical diagnosis will contribute to
medical information system in the following areas: It will enhance the performance of medical
doctors, It decreases personnel time spent on diagnosis, It supports intelligent and interactive
scheme for computer aided statistical analysis for medical records, It will help eliminating the
problem of inadequate facilities to support privacy and security of medical records, It improves
customer service and reduces cost, It aids clinical students in learning medical diagnosis.

1.4 Scope of the Study

This project work is complete on its own functionalities and limited to diagnosing cancer in
human and can be used in any hospital. It does not implement control of automatic patient
voice recognition and finger print verification and only cover some common cancers in human.

1.5 Operational Definition of Terms

Artificial Intelligence — is a branch of computer science that develop systems with the
capability to learn and adapt through experience.
Diagnosis — The act of identifying the exact cause of an illness.
Disease — an illness affecting people.

3
Expert System — is an artificial intelligence application that uses a knowledge base of human
expertise for problem solving.
Knowledge-Base — a database of knowledge and rules about a subject used in artificial
intelligence applications.
System — a group of interrelated components interacting to perform a task.
Cancer — In the most basic terms, cancer refers to cells that grow out-of-control and invade
other tissues.

4
 CHAPTER TWO
LITERATURE REVIEW
2.0 Conceptual view
This chapter consists of expert system, cancer, and cancer in Nigeria, common types of cancer,
lung cancer, symptoms of lung cancer, breast cancer, symptoms of breast cancer, prostate
cancer, and symptoms of prostate cancer, colorectal •cancer, and symptoms of colorectal
cancer causes of cancer, theoretical framework, related literature and summary of the related
literature.

2.1 Expert Systems

Expert Systems arc intelligent computer program that uses knowledge and inference
procedures stored in a knowledge base to solve problems that arc difficult enough and require
significant human expertise for their solution (Zixing and Wen, 2017). Normally, such a system
contains a knowledge base containing encapsulated experience and set of rules for applying the
knowledge base to each particular situation. The major features of expert system are user
interface, data representation, inference, explanations etc. Advantages of expert system are
increased reliability, reduced errors, reduced cost, multiple expertise, intelligent database,
reduced danger etc. Disadvantages of expert system are absence of common sense and no
change with changing environment (Mohammed 2011).

2.2 Cancer
In the most basic terms, cancer refers to cells that grow out-of-control and invade other tissues.
Cancer is one of the leading causes of death worldwide as new cases and deaths from the
disease keep rising. Statistics from the WHO showed that in 2012, there were 14 million new
cases and 8.2 million deaths, while in 2018 there were 18.1 million new cases and 9.6 million
deaths (WHO, 2019). Cancer is a major public health problem in the United States and many
other parts of the world. One in 4 deaths in the United States is due to cancer Siegel, 2013.

2.2.1 Cancer in Nigeria

An estimated 116,000 new cases of cancer and 41,000 cancer-related deaths were recorded in
Nigeria in 2018 (WHO, 2019). Nigeria's population is about 20% of the total population of
Africa, and contributed to 15% of the estimated 681,000 new cases of cancer that occurred in
Africa in 2008 (Sylla 2011). More than 100,000 new cancer cases occur yearly in Nigeria with
high case fatality ratio (Sylla 2011)and(Jedy-Agba 2012). There has been a significant increase
in cancer cases in developing countries (Nigeria inclusive) as a result of reduced risk of
5
infectious disease mortalities, high prevalence of smoking, physical inactivity, obesity, dietary
and lifestyle patterns (Jedy-Agba 2012).

2.2.2 Common Types of Cancer

[Link] Lung Cancer
Lung cancer is the second-most-common cancer in thc United States, and it is the deadliest for
both men and women. In 2012, more than 21 Americans wcrc diagnosed with lung cancer, and
in the same year than 150,000 Americans died from lung cancer. Worldwide, lung cancers are
the most common cancers (Charles 2018)

[Link] Symptoms of Lung Cancer

Causes of lung cancer include: Cough that does not go away or gets worse, Coughing up blood
or rust-colored sputum (spit or phlegm), Chest pain that is often worse with deep breathing,
coughing, or laughing., Hoarseness, Weight loss and loss of appetite, Shortness of breath,
Feeling tired or weak.

[Link] Breast Cancer

The term "breast cancer" refers to a malignant tumor that has developed from cells in the breast.
Usually breast cancer either begins in the cells of the lobules, which are the milkproducing
glands, or the ducts, the passages that drain milk from the lobules to the nipple. Less commonly,
breast cancer can begin in the stromal tissues, which include the fatty and fibrous connective
tissues of the breast. The simplest definition of breast cancer is the uncontrolled growth of
breast cells, (Stage, 2009).
[Link] Symptoms of Breast Cancer
Not everyone with breast cancer will have symptoms before they are diagnosed. But, according
to the Centers for Disease Control and Prevention, possible symptoms of the disease include:
A lump in the breast or armpit, A thickening of the breast, swelling of the breast, Dimpling of
the breast, Skin irritation, Red or flaky skin in the nipple area, Nipple discharge other than
breast milk and Breast or nipple pain (Cafasso, 2019)
2.2-2.5 Prostate Cancer
Prostate cancer is the most common cancer found in men. In 2017, more than 177,000
Americans were diagnosed with prostate cancer, and more than 27,000 American men died
from prostate cancer (Charles 2018).

6
2.3.2,1 Symptoms of prostate Cancer
The symptoms of the prostate cancer include: Frequent urination, Weak or interrupted urine
flow or the need to strain to empty the bladder, The urge to urinate frequently at night, Blood
in the urine, Blood in the seminal fluid, New onset of erectile dysfunction, Pain or burning
during urination, which is much less common.
[Link] Colorectal Cancer
Is one of the cancers that can impact both men and women, colorectal cancer is the second
greatest killer in the United States (Charles 2018).
[Link].1 Symptoms of Colorectal Cancer
The symptoms of colorectal cancer include: Change in bowel habits such as diarrhea,
constipation or narrowing of the stool that lasts for more than a few days, A feeling that you
need to have a bowel movement that's not relieved by having one, Rectal bleeding with bright
red blood, Blood in the stool which may make the stool look dark, Cramping or abdominal
(belly) pain, Weakness and fatigue, Unintended weight loss.
[Link] Causes of Cancer
Roughly cancer risk factors are divided into the following groups: Biological or internal
factors, such as age, gender, inherited genetic defects and skin type. Environmental exposure,
for instance to radon and UV radiation, and fine particulate matter. Occupational risk factors,
including carcinogens such as many chemicals, radioactive materials and asbestos, (Joensuuet
2013).
[Link].1 Lifestyle-related factors.
Lifestyle-related factors that because cancer include: Tobacco, alcoholUV radiation in sunlight,
some food-related factors such as (nitrites and poly aromatic hydrocarbons generated by
barbecuing food), (Jocnsuu 2013).
[Link].2 Cancer causing factors related to work and living environments include:
Asbestos fibers, tar and pitch, polynuclear hydrocarbons (e.g. benzopyrene), Some metal
compounds and Some plastic chemicals (e.g. Vinyl chloride), Joensuu 2013
[Link].3 Bacteria and viruses can cause cancer
Helicobacter pylori (H. pylori, which causes gastritis), HBV, I-ICV (hepatitis viruses that cause
hepatitis), HPV (human papilloma virus, papilloma virus, which causes changes eg. Cervical
cells), EBV (Epstein-Barr virus, the herpes virus that causes inflammation of the throat
lymphoid), (Joensuu 2013).
[Link].4 Radiation can cause cancer

7
Ionizing radiation (e.g. X-ray radiation, soil radon), non-ionised radiation (the sun's ultraviolet
radiation), (Joensuu 2013).
[Link].5 Some drugs may increase the risk of cancer
Certain antineoplastic agents, certain hormones, medicines that cause immune deficiency,
(Joensuu 2013).

2.4 Theoretical Framework

According to (Chan 2000) the shell expert system is a complete development environment for
building and maintaining Knowledge-Based Applications and Expert Systems. It provides a
step-by-step methodology for a knowledge engineer that allows the domain experts themselves
to be directly involved in structuring and encoding the knowledge.
 The Proposed Knowledge Base Scheme (Format) The knowledge base represents the
repository of knowledge fòr specific and narrow domain for the knowledge based
system
 User Interface The user interface simulates the communications facilities available to
be used for interaction with the Rule- Case Based shell expert system. This means an
information processing system of one of (vision, speech, hearing, touching, tasting) or
specified protocol many be used to connect the shell expert system to another
computerized system.
 The inference engine was playing the most important role in the construction of
functional model of human system as mentioned in But its implementation depends on
the representation of knowledge in the knowledge basc of the shell expert system.
 Knowledge Base: Knowledge base is a collection of set of fact at the level of experts in
a particular format

2.5 Related Literature

Over the years’ researchers conducted research on cancer using different methods, in which
their merits and pitfalls identified, below are some of the current research, results obtained and
limitation on breast cancer:
According to (Siegel 2019) Lung cancer is the most common cancer affecting both men
and women, accounting for an estimated 228,150 new cases in [Link] cancer also is the
leading cause of cancer death in men and women, accounting for an estimated 142,670 deaths
in 2019, which is approximately 25% of all cancer deaths in the United States.

8
 According to Wang (2018).Microwave Sensors for Breast Cancer Detectionis one of the
current methods use in diagnosing breast cancer, the antenna was fabricated on R04003
substrate and experimental validation was conducted to demonstrate the characteristics include
return loss, gain and radiation pattern. The Comparison study between the proposed antenna
and the conventional bowtie antenna Sensors was also conducted. The experimental results
demonstrated that the new proposed antenna offers a cross-polarization improvement over 120
around the bore sight at frequency range of GHz. The new proposed antenna has the potential
for biomedical application (Wang 2018).
According Pogue (2018), Novel technologies for breast cancer diagnosis was use in
2018;the results showed that the amount of HER2-expression in the metastases was accurately
measured with the new method. In addition, the amount of HER2-expression in the metastases
was frequently found to be different from the primary tumor, leading to a change in therapy in
several patients. The method is limited in: Sufficient pathobiology sampling, hardware and
software optimization.
According to Mello, (2018), Mammographic diagnosis is one of the best methods use in
2018, Final analysis included 2026 women with 6553 screening rounds: 125 screen-detected
cancers wcrc identified of which 13 and 59 were only detected by mammography or MRI,
respectively. In total, 1 12 cancers were seen on MRI and 66 on mammography. Overall, no
significant difference was found between tumor grade of cancers detected by mammography
or MRI, Mammograms are the best breast cancer screening tests we have at this time. But it is
not reliable. According to Sorensen (2016) a novel imaging-based method for defining
appropriateness of breast cancer treatment is as accurate as the current standard-of-care and
could reduce the need for invasive tissue sampling. The results suggest that the method might
lead to more optimal treatment ol' individual patients; thoughit is expensive and required soft
optimization. According to Hopkins (2015) Blood test was use by the researchers where they
took blood samples Crom 1,005 people with one of the eight different cancer types, finding
that Cancer SEEK was able to reliably identiIY the tumors in 70% cases. The success rates
ranged from an impressive 98% in people with ovarian tumors to only 33% in people with
breast tumors. The limitation of this method is that no test can dctcct all cancer, According to
Keating (2014) Screening mammography leads to a 19% overall reduction in breast cancer
mortality, with less benefit for women in their 40s (15%) and more benefit for women in their
60s (32%). As a result, screening mammography is recommended by the American Cancer
Society beginning at age 45, or sooner depending on individual preference. Limited added

9
value in terms of cancer detection when breast MRI is available for Women of all ages who
are at increased risk.

2.6 Summary of the Literature (Synthesis)

Cancer is a deadly disease that affects both Men and women worldwide, in Nigeria,
efforts have been made by the health care management in diagnosing cancer but some cases
remains unchecked due to some weaknesses in the methods used and cost of diagnosis to a
common people. This research observed that most of the methods use are clinical tests very
few researchers uses expert system in diagnosing cancer. (Yousuf 2015) uses the method of
rule base reasoning architecture and develops expert system but limited in diagnosing only
breast cancer. For this reason this research consider carrying out the study on some common
cancer to identify the limitations in the technology used for detecting cancer in other to fill
some existing gaps to enhance cancer diagnosis. Current methods has been reviewed which
include Microwave for breast cancer detection which is limited in low dielectric property
contrasts between the healthy and the malignant tissues, working frequency selection,
development of a high sensitivity microwave sensor, and limited image resolution. Moreover,
novel technology is also used but the method is expensive, more so, mammograms diagnosis
is also used yet this method has its limitations, as it is not reliable in detecting the presence of
cancer. Therefore, as this research observes that most of the methods used in diagnosing breast
cancer are clinical test and are not affordable by a common people. To address this issue this
research intends to develop an expert system using Rule Base Architecture Expert System
which will act as intelligent human in detecting presence of cancer in human. If this challenge
is addressed properly, it will be easier for medical doctors to diagnose some common cancer.

10
 CHAPTER THREE
RESEARCH METHODOLOGY
3.0 Overview
This chapter consist of method of data collection, analysis of existing system, problems
of existing system, proposed system, system design, database design, entity relationship
diagram, use case diagram, activity diagram, flowchart, development framework, software
development methodology and system requirement.

3.1 Methods of Data Collection

The method of data collection used by this research is Secondary source, different web pages
and peer reviewed journals was consulted to extract related data.

3.2 Analysis of Existing System

Cancer has been a major public health challenges worldwide. Effort has been made by
the health management worldwide in diagnosing breast cancer, different methods have been
used most of which are associated with some pitfalls. According to Siegel, (2013) Incidence
and mortality data was use from the National Center for Health Statistics analysis but this
method is prone to error in reporting. The method of screening mammography leads to a 19%
overall reduction in breast cancer mortality yet is associated with limited added value in terms
of cancer detection when breast cancer is available for women of all ages who are at increased
risk (Keating, 2014). A novel imaging-based method for defining appropriateness of breast
cancer treatment is accurate, though the method is expensive (Sorensen 2016). Mammographic
diagnosis is one of the best methods use in 2018, but is not reliable as it is not accurate (Mello,
(2018). In 2015 the rule base architecture was used in developing expert system for cancer
detection but only limited to breast cancer (Yousuf 2015). Therefore, according to the analysis
most of the methods used are clinical test; they are associated with limitations and are not
affordable by a common people. This research intends to address these issues by developing
expert system using Rule Base Architecture Expert System.

3.3 Problems of Existing System

Most of the existing systems for detecting cancer are clinical tests that are not reliable
as they are not accurate in detecting cancer, more over they are expensive and are not affordable
by common people, and therefore these problems can be addressed by developing expert
system using Rule Base Architecture Expert System.
3.4 Proposed System
11
Due to the inability of the existing system to accurately diagnosc breast cancer, this research
proposed the expert system for diagnosing some common cancer using the method of using
Rule Base Expert Systcm., set of rules will be stored as fact in the data base based
on the related symptoms of the some common cancer. The result will be obtained by queries
based on symptoms Of cancer.
3.5 System Design
3.5.1 Database
Database design is the blueprint for creation of physical database that will serve as the backend,
which will store customer data. Table designs are normalized before they are implemented.
Table 1: Admin
S/no Name Type Length Key Extra
1 Username ALPHANUMERIC 50 PRIMARY AUTO INCREMENT
2 Password ALPHANUMERIC 50 - -
Table 2: Users Bio data
S/no Name Type Length Key Extra
1 User id INTEGER 11 PRIMARY AUTO INCREMENT
2 F name TEXT 50 - -
3 S name TEXT 50 - -
4 Sex TEXT 6 - -
5 Age TEXT 6 - -
6 Username ALPHANUMERIC 50 - -
7 Address ALPHANUMERIC 150 - -
8 Phone ALPHANUMERIC 50 - -
9 Email ALPHANUMERIC 50 - -
Table 3: Diagnosis
S/no Name Type Length Key Extra
1 Diag. Id INTEGER 11 PRIMARY AUTO INCREMENT
2 disease name TEXT 50 - -
3 Symptom 1 TEXT 100 - -
4 Symptom2 TEXT 100 - -
5 Symptom3 TEXT 100 - -
6 Symptom4 TEXT 100 - -
7 Symptom5 TEXT 100 - -

12
 8 Symptom6 TEXT 100 - -
9 Symptom7 TEXT 100 - -

Table 4: Comments
S/no Name Type Length Key Extra
1 Comment Id INTEGER 11 PRIMARY AUTO INCREMENT
2 Comment TEXT 10 - -
3 User id INT 11 FOREIGN -
4 Date DATE - -

3.5.2 Entity-Relationship Diagram

An entity relationship diagram (ERD) shows the relationships of entity sets stored in a database.
An entity in this context is a component of data. In other words, ER diagrams illustrate the
logical structure of databases. An ER diagram is a means of visualizing how the information a
system produces is related

Figure 2. Entity-Relationship Diagram

13
3.5.3 Use case
A use case diagram is a dynamic or behaviour diagram in UML. Use case diagrams model the
functionality of a system using actors and use cases.

Figure

3.5.4 Activity Diagram

Activity diagram is another important diagram in UML to describe the dynamic aspects of the
system. Activity diagram is basically a flowchart to represent the flow from one activity to
another activity. The activity can be described as an operation of the system. The control flow
is drawn from one operation to another.

14
Fig: 4: Activity Diagram

15
3.5.5 Flowchart
A flowchart shows the step-by-step sequence of computer operations necessary in solving
problems.
Figure 3.1 below is a schematic representation of the proposed system flowchart

3.5.6 Framework

16
Fig 6: Dcvelopmcnt Framework

3.6 System Development Tool

Tools for system development include:
Local Server: Local server is use for hosting website locally,
HTML: Hypertext makeup language is use for designing interface.
Web browser: web browser is use Cor displaying web pages.
PHI): Hypertext pre-processor id use for liking database and user interface.
MySQL: Structured query language is an application for developing database.
JQuery: is a cross-platform JavaScript library designed to simplify the client-side scripting of
HTML.
JavaScript: is most commonly used as a client side scripting language. This means that
JavaScript code is written into an HTML page. When a user requests an

3.7 Waterfall Methodology

Waterfall Methodology is a system development methodology that proceeds sequentially from
the requirements stage to the implementation stage, by strengthening the completion of each

17
phase before proceeding to another phase without revising any finished phase. It is like a
waterfall, once it goes down a hill it cannot go back up again.

Figure 7: Schematic Representation of Waterfall Model

Advantages of the Waterfall Model

The following are the advantages of the waterfall model
i. The waterfall model strengthens the completion of each phase before continue to the next
phase. This will the management to the software and will reduce the costly iterations
among phases.
ii. In each phrase, this model will provide quality gates. The quality gate is a checkpoint to
determine the quality of each phase. The next phase will not proceed unless quality of
each phase is achieved. By doing this, the finished product will have a better quality.
iii. This model is also simple and easy to follow.
iv. Lower problems risk for well-understood system by using familiar technology.

Disadvantages of the Waterfall Model

The following are the disadvantage of the waterfall model
i. In each phrase, the programmers must follow the freezing requirements in the earlier
phrase.
18
 ii. Due to the freezing requirements, this waterfall model doc not allow programmers to
make any changes for previous phrases.

3.8 System Requirements

The following are the minimum hardware and software requirements of the proposed system.
3.8.1 Hardware Requirements
The requirements of this system include Hard disk capacity of 120GB, 4GB RAM, Keyboard,
Mouse, Stable Power Supply,
3.8.2 Software Requirements
Local Server, Web browser and MySQL

19
 CHAPTER FOUR
IMPLEMENTATION AND RESULTS
4.1 OVERVIEW
This chapter consist of Result of' the Implementation, Result of the Implementation I- Login
Form, Result of' the Implementation Il- Registration Form, Result of the
Implementation Ill- Add Disease Form, Result of the Implementation IVDiagnosis Form,
Result of the Implementation VI- Comment Form, Discussion of the Result of
Implementation, Implementation and Testing Results and Discussion of result

4.2 Result of the Implementation

4.2.1 Result of the Implementation I- Login Form

Fig l: Login Form

4.2.2 Result of the Implementation Ill- Registration Form

20
4.2.2 Result of the Implementation Ill- Registration Form

Fig. 3: Registration Form

4.2.3 Result of the Implementation IV – Add Disease Form
Fig. 4: Add Disease Form
4.2.3 Result of the Implementation IV – Diagnosis Form

21
Fig. 5: Diagnoses Form
4.2.4 Result of the Implementation VI – Comment Form

Fig. 5: Comment Form

4.3 Discussion of the Result of Implementation
This system was designed in such a way that only the admin can login, register patient, add
disease/symptoms and diagnose patient while user can only post a comment for admin to view.
For admin to login he should provide the username and password and press on login. To register
patient admin should enter all patients' necessary information such as name address phone
number; email date of birth etc.; to add new diseaseadmin should provide disease name and
seven (7) symptoms. For admin to diagnose a particular patient must be registered first after
that the admin click on diagnose then the list of patient displays and click on the

4.3 Implementation and Testing Results

This system is implemented and tested using symptoms of four different types of cancers the
first type of cancer tested vvas Breast cancer, the second was the Lung Cancer, the third was
Prostate Cancer and the fourth was Colorectal Cancer using seven different symptoms each.
After testing the system meet the requirement as it provides accurate result.

4.4 Discussion of Results

Figure: 1
is the login interface of the new system. It is powered by user authentication which allows only
admin to login.
Figure: 2
is the registration page which allows admin to register user with their necessary information
22
Figure: 3
is the disease registration page which allows the admin to register new disease by providing
symptoms.
Figure: 4
is the patient's diagnosis page which allows the admin to perform diagnosis based on the
symptoms.

23
 CHAPTER FIVE
SUMMARY, CONCLUSION AND RECOMMENDATIONS
5.0 SUMMARY
This research covers cancer diagnosis, chapter one covers overview of expert system, statement
of the problem, scope/limitation and definition of terms.
Chapter two covers overview of cancer, theoretical framework, related literature and summary.
Chapter three consists of methods of data collection, analysis of the existing system, problems
of the existing system design: database design, entity relationship diagram, and flowchart, use
case diagram development methodology and system requirement. Chapter four consist of result
implementation and discussion of result and chapter five summary conclusion and
recommendation.

5.1 CONCLUSION
Cancer is a deadly disease that affects both Men and Women especially in under developed
countries where the modern technology for diagnosing cancer are
limited. There is a need for diagnosis tool that will be affordable by lower level
individuals, this research provide expert system for common cancer diagnosis that cover only
four cancer namely breast cancer, lung cancer, prostate cancer and
colorectal cancer. This research provide room for other researchers to carry out
research as it is limited to only four types of cancer with seven symptoms each, they can also
provide automatic fingerprint authentication and voice recognition.

5.2 RECOMMENDATIONS
Based on the findings ol' this research, the following recommendations are made:
i. The health care management should design policies that encourage doctors to
use medical expert systems for the diagnosis of diseases especially cancer.
ii. The ministry of health should organize training sessions for doctors on how to
use medical expert systems.
iii. Future researchers should try and develop expert systems that will cover all kind
of cancer.

24
 REFERENCES
Adewole, K.S, Hambali, M. A & .limoh M. K (2015). Rule Based Expert System
for Diseases Dignosis. Book of Proceedings, International Science, Technology,
Engineering, Arts, Management and social Sciences (iSTREAMS) Multidisciplinary
Conference. Longe, O, B., Jimoh R. G. and Ebem D. U. (Eds), 7,
Anna Suarez(2018) The Impact of Artificial Intelligence on Cancer
Research and Detection 10th July 2018
Brian Krans and Jacquelyn Cal'asso(2017) What Are the Warning Signs of Breast
Cancer'? August 23, 2017 btgps://[Link]/health/brcast-
cancer/warningsigns (Retrieved 3/1 1/2018 )
Ganesh N. Sharma, Rahul l), Jyotsana S,Piush S, ond Sharma K. K,
(2010) Journal of Advanced Pharmaceutical Technology & Research arc
provided here courtesy of Woltcrs Kluwcr-- Mcdknow Publications 2010 Apr-Jun; I
109-126.
Gath, S. J. and Kulkarni, R. V. (20 12). A Review: Expert System for Diagnosis of
Myocardial' Infarction. International Journal of Computer Science and Technologies
(IJCSIT), 3 (6)
WHO (2019 )February 4, 2019 Agency Report, Cancer killed 41,000 people in
Nigeria in 2018- WHO (Retrieved 11/May, 2019)
Joensuu, Heikki; Jyrkkiö, Sirkku; Kellokumpu-Lehtinen, Pirkko-Liisa; Kouri,
Mauri; Roberts, Peter J. & Teppo, Lyly (toim.) (2013), Facts about cancer Living with
cancer Treatment and rehabilitation Advice services Peer support and discussion
(Retrieved, 11 May, 2019)
Kalluri R, Zeisberg M, (2006) Fibroblasts in cancer. Nature reviews Cancer 2006,

Mahesh, V., Kandaswamy, A, and Venkatesa, R. (2009).Telecardiology for Rural Health Care.
international Journal of Recent Trends in Engineering, 2(3).
Mohammed Abbas Kadhim, M. Afshar Alam, Harleen Kaur, "Design(2011)
Implementation of Fuzzy expert, System:of Back Pain Diagnosis", International Journal
of Innovative technology & Creative Engineering, vol. 1, no. 9, PPI 6-22, September
2011.
Motz GT, Coukos G, (2011) The parallel lives of ångiogenesis and immunosuppression: cancer
and other tales. Nat Rev Immunol 2011 ,

25
Open-Clinical (2012). Retrieved 31 December, 20 18 from: [Link]
[Link]/[Link]
Rebecca S, Deepa N, and Ahmedin J,(2013) cancer statistic volume 63 number
1 _ January/February 2013
Rena Goldman, (2017) History of breast cancer March 15, 2017
[Link]
Russell, S. and Norvig, P. (2002). Artificial Intelligence: A Modern Approach, Second
Edition, Prentice Hall.
Sarah Brechon, (2014) Brief History of Cancer, Maurer foundation breast health
education[Link]
Stage IA. (2017), Breast cancer [Link] committee on cancer. 7th
edition.
Siegel RL, Miller KD, Jemal A, (2018): Cancer statistics, 201B. CA: a cancer journal for
clinicians 2018, 68(1):7-30

26