Design and Implementation of An Expert System in Diagnosis and Treatment of Breast Cancer
Design and Implementation of An Expert System in Diagnosis and Treatment of Breast Cancer
Design and Implementation of An Expert System in Diagnosis and Treatment of Breast Cancer
BY
------------------
------------
-------------
OCTOBER, -------
APPROVAL PAGE
1
This is to certify that this project was carried out by -------- and has been
read and approved as meeting the requirement of Computer Science
Department, ------------------
…………………………..
……………………..
---------------------------------------- DATE
(SUPERVISOR)
………………………….`
……………………
--------------------------------------- DATE
(H.O.D)
………………………..
…………………………
EXTERNAL EXAMINER DATE
DEDICATION
2
This research work is dedicated to my heavenly father “God almighty”
and his only begotten Son Jesus Christ, for his great inspiration and
ACKNOWLEDGEMENT
3
I thank the Almighty God, for his guidance and protection throughout the
Ijeoma Emeagi for her guidance and contribution throughout the research.
and the Dean of student affairs, Pastor ----------------- for all their great support
throughout the period the work lasted. I also want to acknowledge other
lecturers in my department Mr. --------, Mr. ----------, Mr. -------, Mrs. ---------,
Mrs. -----------, Mr. ----------, etc for all their encouragement throughout the
my uncles Mr. --------, and my mentor Mr. ------- for their special support
TABLE OF CONTENTS
Dedication -------------------------------------------------------------------------------iii
Acknowledgement.- ---------------------------------------------------------------------iv
Abstract ---------------------------------------------------------------------------viii
---------------------------------------------------------------------------2
------------------------------------------------------------------------------3
---------------------------------------------------------------------------3
-----------------------------------------------------------------------------------4
-----------------------------------------------------------------------------4
-------------------------------------------------------------------------4
5
2.1.1 Types of breast cancer ------------------------------------------------------5-6
–---------------------------------------------------------------6-7
-----------------------------------------------------------------------------8-9
--------------------------------------------------------------------------------9
-------------------------------------------------------------------------------10
---------------------------------------------------------11-12
----------------------------------------------------------------------12
---------------------------------------------------------12-14
2.2.2 Success factors of CDS systems
-------------------------------------------------------------15-18
---------------------------------------------------------------19-21
--------------------------------------------------21-23
6
3.0 Preamble
-----------------------------------------------------------------------------------------24-25
------------------------------------------------------------------------25
------------------------------------------------------------------25-26
-------------------------------------------------------------27
-------------------------------------------------------------------28
–-------------------------------28-30
----------------------------------------------------------------30
--------------------------------------------------------------------------------31-32
---------------------------------------------------------------------------------------32
-----------------------------------------------------------------------------------------33
7
4.3 Database design
--------------------------------------------------------------------------------33-34
---------------------------------------------------------------------------------34-35
4.5 System
flowchart------------------------------------------------------------------------------------
36
---------------------------------------------------------------37
-------------------------------------------------------------------------------38
---------------------------------------------------------------------------39-40
--------------------------------------------------------------------------------40-41
RECOMMENDATIONS
5.0 Summary
--------------------------------------------------------------------------------------------
----42
5.1Conclusion
--------------------------------------------------------------------------------------------
8
---43
5.2Recommendations
--------------------------------------------------------------------------------------43
REFERENCES
------------------------------------------------------------------------
-------------44
APPENDIX 1: Program flow chart
-------------------------------------------------------------45
APPENDIX 11: Source code
-----------------------------------------------------------------46-57
APPEMDIX III: Program output
------------------------------------------------------------58-60
ABSTRACT
“Expert system on breast cancer diagnosis “is a software doctor aimed at
designing a package that can act as expert doctor assist in the absence of one. A
database of the procedures of this diagnosis of breast cancer will be created, this
will enable the retrieval of the data collected and stored, for feature use. This
package is simple, easy and reliable it makes an individual with computer
knowledge have vast range of knowledge for diagnosing breast cancer and
prescribing treatments, after inputting systems. Hospitals, research centers,
laboratories and government will benefit from this project when properly
9
implemented, especially in rural areas where experts system are almost not
available. In carrying out this project the methodology used are interview,
questionnaire and examination of records. Due to the problem of the old
system which are lots of time being wasted by patients while in queue, since
their reference or retrieval of information from old patients case is often a
problem, sluggish rate releasing diagnosis report, patients past record are
subjected to fear of rodents and termites attack. The new system will be capable
of designing a medical expert system on breast cancer that will provide
complimentary assistant to a patient without first going to the doctor for a
diagnosis and be able to provide a system which is very effective, efficient,
secured and reliable. This design expects gave the structure for the new system.
Visual basic (V.B) programming language 6.0 version was used.
CHAPTER ONE
1.0 INTRODUCTION
Over the year the leading cause of death in woman aged between 35-54 years is
breast cancer and second to cardio vascular disease in order woman (Logan
1975).
Breast cancer is a malignant tumor (a collection of cancer cells) arising from the
Mortality and incidence rate vary throughout the world, with England and
Wales making first and U.S fourteen developing countries like Nigeria not left,
in fact the two leading cancer sites are breast and lung accounting for about
25% of all cancer such as common disease in woman and 1 to 12% woman is
affected in the U.S and 1% Nigeria. However its not surprising that there exist
and long list of potential risk factor aging factor , age of first birth being breast
10
disorder decrease parity, unopposed ovarian cycling menstrual experience,
two most important risk factor majority of woman now coming for medical
The high incidence for breast cancer is not unique in middle east . study reveals
that in USA , most of the women have breast cancer as a common aliment,
which has further focused more to educated the woman about early detection
1.1BACKGROUND OF STUDY
Nowadays with the evolution of science and technology, medical field become
more efficient. There are many applications on expert system that has been used
disease diagnosing.
There are many types of diagnose that had used this expert system such as to
diagnose chest pain, breast cancer, skin disease, hypertension, diabetes and
e.t.c. this kind of diagnosis expert system is known as medical expert system.
integrated system.
11
According to Luger (1989), medical expert systems have evolved to provide
knowledge for diagnosing and prescribing treatment for diseases with both
All the parameters that have been used in this system are based on easy to
without first going to the doctor for diagnosis and be able to provide a system
1.2STATEMENT OF THE PROBLEM
Disease(breast cancer)
diagnosis and treatment constitute the major work of physicians.Some of
the time, diagnosis is wrongly done leading to error in prescripting
treatment and further
complications in the patient’s health. It has also been noticed that much
time is spent in physical examination and interview of patients before treatment
commences.
The clinical decision support system (CDSS) shall address these
problems by effectively
12
providing quality diagnosis in real-time.
1.3 OBJECTIVE OF THE STUDY
The aim of the project is to design software that can be used to diagnose breast
Aid health care providers responsible for large patient, the expert system
can answer basic or general questions, leaving more time for individuals to
Aiding the nurses and other staff in federal medical centre (FMC) to
know what to do in the case of emergency if the human expert is not present at
1.4 SIGNIFICANCE OF STUDY
Advances in the areas of computer science and artificial intelligence have
allowed for development of computer systems that support clinical diagnostic or
therapeutic
medical
13
centre (FMC),the clinical decision support (CDS) systems aim to codify
and strategically
practice using mathematical
modeling tools, medical data processing techniques and artificial intelligen
ce
(A.I.) methods.
1.5 SCOPE OF THE STUDY
1.6 LIMITATIONS OF THE STUDY
In the course of this study, a major constraint experienced was th
at of time
factor and insufficient finance.Others include the inevitability of human error
and bias
as some information were obtained via interpersonal
interactions,interviews and research,
14
Great pains were however taken to ensure that these limitations are at their very
minimum
1.7DEFINITION OF RELATED TERMS
Here, the researcher shall try as much as possible to explain certain technical
terms used
during the course of his study.
Prognosis: This is a medical opinion as to the likely outcome of a disease
Etiology: This is the branch of medicine that investigates the causes and origin
of diseases.
Diagnostic Criteria: This term designates the specific combination of sign
s, symptoms,
and test results that the clinician uses to attempt to determine the
correct diagnosis.
Therapy critiquing and consulting: This function of a clinician implies
assessing of the
therapy looking for inconsistencies, errors, cross-references for
drug interactions and
prevents prescribing of allergenic drugs.
Allergen: A substance that causes an allergy.
Epidemiology: The scientific and medical study of the causes and transmission
of disease
15
within a population
16
CHAPTER TWO
LITERATURE SURVEY/REVIEW
Breast cancer is on the rise. Big countries have the most cases but not always the
highest incidences and rates in the developing world may be even higher than the
The simplest definition of breast cancer is the uncontrolled growth of breast cells. It
is found that one out of every seven Women will be diagnosed with breast cancer if
all live to their full life span in a well-developed country like USA alone.
Ongoing focused research for breast cancer causes and cure is offering new hope for
effective treatments that attack the tumor without destroying the surrounding tissue.
2.1.1 TYPES OF BREAST CANCER
Breastcancer can be subdivided into various classes based on the cells that
are affected, the origin of the
malignancy and the size and spread of the cancer. The different types
of breast cancers can be listed as follows:
cancer
17
in which only the duct walls are affected. This type of cancer does not spread
through the
walls of the duct to the outer tissue and hence is the most curable type of breast
cancer.
2. Lobular carcinoma in situ (LCIS):
contained within
the lobules and does not spread to the outer tissue.
3. Invasive ductal carcinoma (IDC): The most common
form of breast cancer in
the tissue from where it can
4. Invasive lobular carcinoma (ILC): In this type the
malignancy originates in the lobules
or milk glands and further invades the wall to spread to the rest of the body.
5. Inflammatory breast cancer (IBC): This is a very
uncommon type of invasive breast
thick
red inflammatory look which is actually caused by
cancer cells blocking lymph vessels
18
in the skin. Instead, inflammatory breast cancer (IBC) makes the skin of the breast
look red and
feel warm and gives the skin a thick, pitted
appearance that looks a lot like an orange peel. Pathologic
changes such as cancer cells in the lymph ducts in the skin(dermal lymphatic)
are characteristics of inflammatory breast cancer.
2.1.2 DIAGNOSIS OF BREAST CANCER
Cancer of any type is usually asymptotic and does not show significant
symptoms until it is
well advanced.
Hence the need to perform a routine screening test is vital in diagnosing
cancer at an early
stage. Breast cancer if diagnosed well
within an early period of time offers high chances
carried out for screening
and diagnosis of breast cancer.
The screen procedures include:
1. Mammogram: It is a type of imaging technique that uses allow dose x-ray sy
stem
mammography
makes use of solid state detectors that convert x-rays into electrical signals.
19
These electrical signals are then converted to digital images by interfacing them
with a
computer.
Different software is then used to quantify and detect abnormal areas of density
mass or
calcification as pointers for presence of malignant conditions .
Mammograms can detect changes in the breast up to nearly
two years before a physician or the
four views of
caudal
view and lateral view are the two separate views used to derive four images.
2. Clinical Breast Exam (CBE): A clinical breast
examination is a physical examination
of the breasts by a certified health professional. These examinations are used
in conjunction
with Mammograms to detect the presence of
lumps and also to check for other breast
abnormalities such as mastitis or fibro adenoma .
20
3. Breast Self-Exam (BSE): In this test the individual is asked to self-
examine the breast
for changes in texture, appearance, weight and volume.
full magnets that act in
conjunction with radio waves to produce computer images showing differences
in the number
The radioactive dye is picked up faster
by cancerous tissue than normal or benign ones.
This test is used in conjunction with a mammogram for a full body
screen for a complete
diagnosis .
5. Genetic Test: In case of patients with a strong background
history of ovarian and breast
cancer a gene test is carried out in which the mutations if any on genes BRCA1 and
BRCA2
6. Positron-Emission Tomography (PET): PET is similar to X-
rays where instead of cell
Structure the cell activity is shown.
Cancer cells use up sugar faster than normal cells
do. PET is highly accurate at diagnosing
whether a tumor is cancerous.
21
2.1.3 BREAST CANCER STAGING
Breast cancer staging or grading is based on size of the tumor,
whether lymph nodes are involved,
whether cancer has spread
beyond the breast and whether the cancer is invasive or non-invasive.
The cancer stage is determined in order to best
understand the prognosis and guide the
treatment decisions and tailor the treatment according to the individual patient’s
case
requirements.
There are four defined stages of breast cancer each with further subcategories
1. Stage 0: Used to describe non-invasive breast cancers such as
DCIS (Ductal Carcinoma In Situ) and LCIS
(Lobular Carcinoma In Situ). In stage 0 there is
of the breast
invades the adjacent tissue in which:
a) The tumor measures up to 2 centimeters
b) No lymph nodes are involved.
3. Stage 11: This stage is divided into subcategories as IIA
and IIB. II A describes invasive
22
breast cancer in which:
a) No tumor seen in breast but seen in auxiliary lymph nodes
b) Tumor measures 2cms or less and has spread to the auxiliary lymph nodes.
c) Tumor larger than 2cms but smaller than 5cms and has not
spread to the auxiliary lymph nodes.
IIB describes invasive breast cancer in which:
a) The tumor is larger than 2cms but not larger than 5cms and has spread to the
auxiliary lymph nodes.
b) Tumor is larger than 5cms but has not spread to the
auxiliary lymph nodes.
4. Stage 111: This stage is subdivided into three categories
IIIA, IIIB and IIIC. IIIA describes
Invasive breast cancer in which:
a) No tumor is found in the breast but found in auxiliary lymph
nodes that are clumped together
Or sticking to other structures.
IIIB describes invasive breast cancer which:
a) The tumor may be of any size and has spread to chest wall
and/or skin of the breast AND
may have spread to auxiliary lymph nodes that are clumped together.
Or it may have
23
affected lymph nodes near the breastbone.
b) Inflammatory breast cancer is considered at least stage IIIB.
IIIC describes invasive breast cancer in which:
a) The tumor may not be in the breast or it may be of
any size and has spread to chest wall
or skin AND
b) The cancer has spread to lymph nodes above or
below the collarbone AND
c) Cancer may have spread to auxiliary lymph nodes or
to lymph nodes near the breastbone.
5. Stage IV: Describes invasive breast cancer in which:
The cancer has spread to other parts of the body like lungs, liver bone or brain.
2.1.4 TNM STAGING SYSTEM
The TNM staging system is used by physicians to accurately
define the spread of the cancer.
The TNM is determined as follows:
a) T: Size of the tumor is indexed by this variable.
b) N: Lymph node involvement is defined by value of N.
c) M: whether the cancer has metastasized is denoted by M.
2.1.5 BREAST CANCER BIOPSY
24
A final diagnosis for presence or absence of breast cancer
cannot be made until a biopsy
is performed and the
pathologist looks at the biopsy tissue under the microscope.
Only the pathologist is qualified to make the final diagnosis.
The information gleaned from the
gross pathology is the size,
location and the character of the specimen tissue as a whole,
and the size, location and character of the cancer, if present contained within it .
There are two types of biopsy procedures involved.
Needle biopsy, also called stereotactic biopsy and involves far less
tissue. This is further subdivided as Fine Needle Aspiration
(FNA) and a core needle
biopsy technique.
Cytopathologists perform FNA procedure which has the
advantage that it is the quickest
way to demonstrate the
presence of cancer. Positive diagnosis of FNA resolves the issue
FNA is carried out with a small Syringe and needle which are used to aspirate
some cells
A core needle biopsy is performed if the lump is palpable.
While the FNA procedure
25
Obtains only cells a core needle
obtains a thin sample of the tissue itself and views all the cells
in their proper architectural relation to other cells in the tissue.
Thus it gives more information than FNA. The second type is
the open biopsy which consists
of a surgical incision directly
above the area to be removed and removal of some or
biopsy or lumpectomy
and incisional biopsy.
2.1.6 TREATMENT OPTIONS FOR BREAST CANCER
stage or kind of cancer.
The kind of surgery depends on the size of the tumor, the spread of the cancer,
the age and sex
of the patient. In case the tumor is under
2cms and the cancer is not determined as aggressive,
lumpectomy.
26
In this kind of surgery only the tumor and affected nodes are removed whereas
the
breast mass is kept intact.
which
involves complete removal of the breast.
2. Chemotherapy: Chemotherapy is the process of
administering drugs through the
eliminate the
fast growing cancer cells. Unfortunately
therapy is more targeted and localized
In internal
amount of
4. Hormonal Therapy: Hormonal therapy also involves
the whole body and it involves
27
Menopausal stages.
5. Targeted Therapies: These are highly focused treatments
in which the protein that enables
cells in comparison to chemotherapy. These drugs modify
the properties of cancerous
Complementary and Holistic Medicine: Even though this
2.2.1 CLINICAL DIAGNOSTIC SUPPORT SYSTEMS
Advances in the areas of computer science and artificial intelligence have
allowed for the
decisions
28
based on individualized patient data(Berner and Bell, 1998; Shortliffe, Penna
Wiederhold,
encyclopedia are interactive
computer programs designed to assist healthcare professionals with decision making
tasks.
Bankman, 2000, elucidates further by asserting that Clinical Decision Support(CDS)
systems aim
to codify and strategically manage biomedical knowledge to
handle challenges in clinical
practice using mathematical modeling tools,medical data processing techniques
and Artificial Intelligence(AI) methods.
In other words, CDSS are active knowledge systems which use two or more items
of patient
data to generate case-specific advice (Wyatt and Spiegelhalter, 1991).
This kind of software uses relevant knowledge rules within a knowledge base
and relevant
patient and clinical data to improve clinical decision making on
topics like preventive,
acute and chronic care, diagnostics, specific test ordering, prescribing practices.
Clinicians, health-care staff or patients can manually enter patient characters into
the computer
29
system; alternatively, electronic medical records can be queried for retrieval
of patient
characteristics.
However, Delaney, Fitzmaurice et al. 1991; Pearson, Moxey et al. 2009) warns
that ―regardless
of how we choose to define CDS systems, we have to accept
that the field of CDSS is rapidly
advancing and unregulated. ―it has a potential
for harm if systems are poorly designed and
inadequately evaluated, as well as a
huge potential to benefit , especially in health care
provider performance,quality of care and patient outcomes.CDS system is one of the
areas
addressed by the clinical information systems(CIS). Clinical information systems pro
vide a
clinical data repository that stores
clinical data such as the patient’s history of illness, diagnosis
There are some principal categories to take into account while striving for
excellent decision making as outlined by Shortliffe and Cimono 2006.:
a. Accurate data
b. Applicable knowledge
c. Appropriate problem solving skills.
30
Patient data must be adequate to make a valid decision. The problem arises
when the
clinician is met with an overwhelming amount of specific and
unspecific data, which
he/she cannot satisfactorily process. Therefore, it is
important to access when additional
facts will confuse rather than clarify the
patient’s case. For example, a usual setting for such
a problem is intensive-care
units where practitioners must absorb large amounts of data
from various
monitors, be aware of the clinical status, patient history, accompanying chronic
illness, patient’s medication and adverse drug interactions, etc – and on top of
that make an
appropriate decision about the course of action.
The quality of available data is of equal importance.
Measuring instruments and monitors serious adverse effect on patient-
care decisions.
Knowledge used in decision making process must be accurate and current. It is
a major
importance that the deciding clinician has a broad spectrum of medical
knowledge and access to
31
information resources, where it is possible to
constantly revise and validate that knowledge.
For a patient to receive
appropriate care, the clinician must be aware of the latest evidence
based
guidelines and development in the area of the case in question. It is in the
clinician’s hands to bring proven therapists from research papers to the fore.
CDSS analogously needs an extensive well structured and current source of
knowledge to
appropriately serve the clinician.ood problem solving skills are needed to utilize
available
data and knowledge.
Above all, good problem solving skills are needed to utilize available data and
knowledge
deciding clinicians must set appropriate goals for each task, know
how to reason about each
goal and taste in to account the trade-offs between costs and benefits of therapy and
diagnostics.
By incorporating patient specific
data and evidence based guidelines or applicable
knowledge base, the CDSS
can improve quality of care with enhancing the clinical
decision making process, (General Practice Electronic Decision Support 2000).
In order to be able to construct applicable CDS systems, it is imperative to have
a broader-based
32
understanding of medical decision making as it occurs in the natural setting.
Designing CDSS without understanding the cognitive processes
underlying medical reasoning
and decision analysis is pliable for ineffectiveness
and failure for implementation into
clinical workflow (Patel, Kaufman et al.2002).
2.2.2 SUCCESS FACTORS OF CDS SYSTEMS
Despite the fact that the computerized CDS systems were continuously in
development
since the 1970s, their impact on routine clinical practice has not
been as strong as expected.
The potential benefits of using electronic decision
support systems in clinical practice fall
into three broad categories (Coiera 2003):
1. Improved patient safety (reduced medication errors and unwanted adverse
events,
refined ordering of medication and tests);
2. Improved quality of care (increasing clinicians’ time allocated directly to
patient care, increased application of clinical pathways and guidelines,
33
accelerate and encourage the use of latest clinical findings, improved clinical
documentation
and patient satisfaction);
3. Improved efficiency of health-care (reducing costs through faster order
processing,
reductions in test duplication, decreased adverse events, and
changed patterns of drug
prescribing, favoring cheaper but equally effective generic brands).
Developing CDSSs is a challenging process, which may lead to a failure despite
our theoretical knowledge about the topic.
Understanding the underlying causes,which lead either to success or either to fai
lure,
may help to improve the
efficiency of CDSS development and deployment in
day-to-day practice.
Failures can originate from various developmental and implementation phases:
failure to technically complete an appropriate system, failure to get the system
accepted by the
users and failure to integrate the system in the organizational or user environment
(Brender, Ammenwerth et al. 2006).
34
There is an estimation that 45% of computerized medical information systems
fail because of
user resistance,even though these systems are technologically
coherent. Some reasons for such a high percentage of failure may derive from
insufficient computer ability, diminished professional autonomy, lack of
awareness of long-term benefits of CDSS-use and lack of desire to change the
daily workflow
(Zheng, Padman et al. 2005).
There is also clear evidence that
CDSS services are not always used when available,
since too numerous systems’ alerts are being overridden
or ignored by physicians (Moxey,
Robertson et al. 2010).
Despite the problems and failures that might accompany CDSSs, these systems
have still been
proven to improve drug selection and dosing suggestions, reduce
serious medication errors by
flagging potential drug reactions, drug allergies and identifying duplication
of therapy,
to recommended care standards.
Recent studies suggest that there are some CDSS features crucial to success of
these systems
(Kawamoto, Houlihan et al. 2005; Shortliffe and Cimino 2006;
Pearson, Moxey et al. 2009; Moxey, Robertson et al. 2010):
35
CDSS should provide decision support automatically as part of clinicians’
workflow, since systems where clinicians were required to seek out advice
manually have not been proven as successful.
Decision support should be delivered at the time and location of decision-
making. If the clinician has to interrupt the normal pattern of patient care to
move to a separate workstation or to follow complex, time-consuming
startup procedures it is not likely that such system will be good accepted.
Systems that were provided as an integrated component of charting or
ordering systems were significantly more likely to succeed than alone
standing systems.
Generally speaking, the decision-support element should be incorporated
into a larger computer system that is already part of the users’ professional
routine, thus making decision support a byproduct of practitioners’ ordinary
work practices.
Computerized systems have been reported to be advantageous over paper-
based systems.
Systems should provide recommendation rather than just state a patient
assessment. For instance, system recommends that the clinician prescribes
diuretics for a patient rather just identifying patient being cardiologically
decompensated.
CDSS should request the clinician to record a reason for not following the
36
systems’ advice (the clinician is asked to justify the decision with a reason,
e.g. ―The patient refused―).
It should promote clinicians’ action rather than inaction.
No need for additional clinical data entry. Due to clinicians’ effort required
for entering new patient data, they tend to avoid this process, which is
essential for new decision support. Systems should rather acquire new data
automatically (e.g. data retrieval from EMR).
The system should be easy to navigate and use, e.g. with quick access and
minimal mouse clicks for desired information.
Timing and frequency of prompts are of great importance. For instance if
there are too many messages, this might only lead to ignoring all of them and
consequently to missing important information.
The timing is as well of great importance - the alerts shouldn’t appear
at inappropriate times and interrupt the workflow.
The presentation of data or information on CDSSs shouldn’t be too dense or
the text to small. Researchers also suggest the use of blinking icons for
important tasks or the arrangement of interactions according to their
urgency.
Decision support results should be provided to both clinicians and patients.
Studies have shown beneficial effect of such actions, because they stimulate
the clinicians to discuss treatment options with patients, and consequently
make the latter feel more involved in their medical treatment.
Periodic feedback about clinician’s compliance with system decision-
37
making.
What these features have in common is that they all make it easier for clinicians
to implement the CDSS into their workflow, thus making it easier to use. An
effective CDSS must minimize the effort to receive and act on system
recommendations. Clinicians found it also very practical if the CDSS would
back up its decision-making with linking it to other knowledge resources across
the intranet or Internet. In their opinion the safety and drug interaction alerts
were the most helpful feature. Above all the organizational factors, such as
computer availability at the point of care and technical perfection of CDSS
hardware and software are crucial to implementation (Moxey, Robertson et al.
2010).
Kawamoto 2005 suggests that the effectiveness of CDSS remains mainly
unchanged when system recommendations are stated more strongly and when
the evidence supporting these prompts is expanded and includes institution-
specific data.
2.3 EXAMPLES OF CDSS IN PRACTICE
There have been multiple attempts through history to construct a computer or
program, which would assist clinicians with their decisions concerning
diagnosis and therapy. Ledley and Lusted published the first article evolving
around this idea in 1959. The first really functional CDSS didn’t appear until
the 1970s.
Some of them are reviewed below:
Leeds abdominal pain,
38
MYCIN,
HELP and
Internist-1.
Leeds abdominal pain
F. T. de Dombal and his co-workers at University of Leeds developed Leeds
abdominal pain. It used Bayesian reasoning on basis of surgical and
pathological diagnoses. These pieces of information were gathered from
thousands of patients and put into systems’ database. The Leeds abdominal pain
system used sensitivity, specificity and disease prevalence data for various
signs, symptoms and test results. With help of Bayes’ theorem it calculated the
probability of seven possible diagnoses resulting in acute abdominal pain:
pancreatitis, and nonspecific abdominal pain. The system assumed
that each patient with abdominal pain had one of these seven conditions, thus
selected the most likely diagnose on the basis of recorded observations.
Evaluation of the system was done by de Dombal et al. in 1972.
It showed that the clinicians’ diagnoses were correct in only 65 to 80 percent of the 304 cases
whereas the program’s diagnoses were correct in 91.8 percent of cases.
Surprisingly, the system has never achieved similar results of diagnostic
39
accuracy in practice outside the Leeds University. The most likely reason for
that is the variation of data that clinicians entered into the system for acquiring
correct diagnoses (de Dombal, Leaper et al. 1972).
MYCIN
This was a consultation system that emphasized appropriate management of
patients who had infections rather than just finding their diagnosis. Th
developers of this system formed production rules (IF-THEN rules), on basis of
current knowledge about infectious diseases. The MYCIN program determined
which rules to use and how to chain them together in order to make decisions
about a specific case. System developers could update the system's knowledge
structure rapidly by removing, altering, or adding rules, without reprogramming
or restructuring other parts of the system (Shortliffe 1976).
The HELP System
The HELP system is actually an integrated hospital information system with the
ability to generate alerts when data abnormalities in the patient record are noted.
It can output data either automatically, in form of printed reports, or it can
display specific information, if so requested. Furthermore, the system has an
event-driven mechanism for generation of specialized warnings, alerts and
reports (Burke, Classen et al. 1991).
Internist-I
40
This was an experimental CDSS designed by Pople and Myers at the University
of Pittsburg in 1974. It was a rule-based expert system capable of making
multiple, complex diagnoses in internal medicine based on patient observations.
The Internist-I was using a tree-structured database that linked symptoms with
diseases. The evaluation of the system revealed that it was not sufficiently
reliable for clinical application. Nevertheless, the most valuable product of the
system was its medical knowledge base. This was used as a basis for successor
systems including CADUCEUS and Quick Medical Reference (QMR), a
commercialized diagnostic CDSS for internists (Miller, Pople et al. 1982).
2.4 SELECTED CONTEMPORARY EXAMPLES OF CDSS
ATHENA
The Athena decision support system was deployed in 2002 as a tool to
implement guidelines for hypertension. It encourages blood pressure control and
issues recommendations about a suitable choice of therapy, concordant with
latest guidelines. It also considers co-morbidities of the specific patient in
question. ATHENA DSS has an easily changeable knowledge base that
specifies criteria for eligibility, risk stratification, set blood pressure margins, it
includes relevant co-morbid states and guideline-recommendation, specific for
patients with present co-morbidities. The knowledge base also comprises of
preferences for certain drugs within antihypertensive drug groups according to
the latest evidence.
New pieces of evidence are constantly changing protocols of best hypertension
management;
41
ATHENA is thus designed to be accessible to clinicians for
knowledge base-customization and to custom local interpretations of guidelines
according to the local population structure and other factors.
The system was designed to be independently integrated into a variety of EMR-
systems, and is thus interchangeable and adaptable for various health
success of implementation has been researched and
reviewed on many occasions (Goldstein, Coleman et al. 2004; Lai,
Goldstein et al. 2004).
42
ISABEL
Isabel is a web-based diagnosis decision support system that was created i
n 2001 by physicians. It offers diagnosis decision support at the point of care.
The system is eligible for all aged patients, from neonates
to geriatrics. Its databasecovers major specialties like Internal
Medicine, Surgery,
Gynecology & obstetrics, Pediatrics, Geriatrics, Oncology, Toxicology and
Bioterrorism.Isabel produces an instant list of likely diagnoses for a
given set of clinical
features (symptoms, signs, results of tests and investigations etc),
followed by suggesting the administration of suitable drugs. This is executed
by reconciling (i.e. pattern-
matching technology) patient data sets with data sets as described in
established medical literature. The system allows clinicians to follow their
assumptions about differential diagnoses; it hence restricts searches to specific
body systems, relatively to diagnoses in question. The system is interfaced with
EMR, which allows it to extract existing diagnoses and other patient-specific
data.
Furthermore it contains a feature to help Isabel has been extensively validated
and been shown to enhance clinician’s cognitive skills and thereby improve
s
43
patient safety and the quality of patient care (Ramnarayan, Tomlinson et al.
2004; OpenClinical 2006).
LISA
LISA is a CDSS that consists of two main components. The first is a centralized
Oracle database, holding all patient information about drug schedules, blood
and toxicity results, doses prescribed etc. The database is accessible by health
professionals from different sectors and locations. The second component
represents a web-based decision support module, which is using the PROforma
guideline development technology to provide advice about dose adjustments in
treatment of acute childhood lymphoblastic leukemia. Bury, Hurt et
from textbooks and journals.
44
CHAPTER THREE
METHODOLOGY AND SYSTEM ANALYSIS
3.0 PREAMBLE
Procedures used in data collection and information gathering are here, outli
ned
and analyzed. Data was carefully collated and objectively evaluated in order to
define as well as ultimately provide solutions to the problems for which t
he
research work is based.
During the research work, data collection was carried out in many places. In
gathering and collecting necessary data and information needed for system
analysis, two major fact-finding techniques were used in this work and they are:
a. Primary source
b. Secondary source
Primary source:
Primary source refers to the sources of collecting original data in which t
he
researcher made use of empirical approach such as personal interview and
questionnaires.
This involved series of orally conducted interviews with select clinicians i
public and private healthcare practice on the diagnostic procedures they adopt.
45
Also, some patients were interviewed with a view to getting information about
their opinion on how medical diagnoses affected them.
Secondary Source:
Perusals through online journals and e-books as well as visits to relevant
websites, medical dictionaries and other research materials increased
my
knowledge and aided my comprehension of diagnostic processes.
3.1 METHODS OF DATA COLLECTION
Oral Interview
This was done between the researcher and the doctors in the hospital used fo
the studies, and the lab attendance was interviewed. Reliable facts we
re got
based on the questions posed to the staff by the researcher.
Study of Manuals
Manuals and report based used by lab attendance were studied and a
lot of
information concerning the system in question was obtained.
46
Evaluation of Forms
Some forms that are necessary and available were assed. Thes
e include
admission card, lab form, test result, bill card Etc. These forms help
in the
design of the new system.
3.2 ANALYSIS OF EXISTING SYSTEM
This aims at objectively evaluating the existing system of diagnostics
and
treatment in the hospital with a view to highlighting its limitations. It also se
eks
o proffer solutions by offering a knowledgeable expert system which would
aid
clinicians in diagnostic procedures.
The existing system of medical diagnosis and drug prescription i
n
most
hospitals involves manual activities. A proper diagnosis is the first step towards
47
proper medical care. This was the consensus opinion reached by all respond
ents
interviewed. An investigation into how diagnosis is carried out reveale
d that
anytime patients visit the hospital, they are subjected to long waiting hours j
ust
to undergo the regular card verification and clearance.
Patients queue accordingly for several hours on a first come first serve (FCF
S)
basis. A new patient usually registers into the hospital by filling the patient f
orm
which signifies that the person is now registered with that hospital.
It also,
gives the person access to own a hospital folder which is used to record basi
information about the diagnoses and drug prescriptions to the patient.
He/she is then referred to a doctor for examination and testing.
This
examination helps the doctor to determine exactly what a patient may
be
suffering from. Testing is a great way to find out a medical conditio
n
However it was the widespread practice that in attending to registered patie
nts
48
the attending staff usually retrieved his hospital folder using the patient’s fo
rm.
This form is then sent to the doctor who peruses it, before examining the pat
ient
and carrying out the appropriate therapy. The patient is either referred t
o the
laboratory unit for a test (if the need be) or to the pharmacy unit to obtain th
prescribed drugs (if the matter is not too complex).
Any treatment proffered to the patient by the doctor must be recorded in
the
patient’s folder to aid future diagnostic references.
This procedure is usually a long and tedious one with attendant bottlenecks.
49
3.3 BLOCK DIAGRAM OF EXISTING SYSTEM
The diagram below graphically illustrates the process of service delivery to
patients in the hospitals visited.
Patient verifies or obtains
From the Waiting room
card from the hospital
Clerk/receptionist
desk
Patient uses the card to
see a doctor in the
consultation room
Doctor examines the
patient and refers patient
for x-ray, ultrasound etc
Pharmacy
50
3.4 LIMITATIONS OF EXISTING SYSTEM
Some shortcomings were noticed in the existing system after thorough
analysis. They include:
a. Manual documentation of patients’ records
It was noticed in the course of investigation that the existing system was
heavily dependent on manual methods of entering, storing and retrieval of
patients’ data. This implied patients had to wait for quite long before
being referred for diagnosis.
b. Error in diagnosis:
It was discovered that in some cases, wrong diagnosis was given for
ailments because they (the ailment) were relatively new and the physician
had limited knowledge about it. The situation was even made worse
because at the point of medical examination, the physician could not
access a wider knowledge base for guidance.
c. Stalling of treatment due to doctor’s absence:
Another discovery was that patients had to wait indefinitely in the event
of a doctor’s prolonged absence and sometimes, end up not accessing
treatment. This has led to a further deterioration of their health conditions
and in some cases resulted in death of patient.
3.5 INPUT, PROCESS AND OUTPUT ANALYSIS OF PROPOSED
SOLUTION
The proposed system is built with the benefit of an object-oriented approach.
The system seeks to build a computational model of some problem domain and
therefore tends to be exploratory in nature.
51
The flow of data in the proposed system is in such a way that when a particular
disease is highlighted from the disease menu, it will display an interactive
submenu that includes the symptoms. The central concepts of the object-
oriented paradigm are introduced namely: encapsulation, inheritance and
polymorphism.
INPUT ANALYSIS
This deals with the process used to feed data to the system for processing. Here,
data could be manually fed in with the help of a keyboard or sourced for
electronically by consulting the electronic medical records (EMR) database. The
data supplied to the system includes:
a) Patient’s name
b) Home address
c) Sex
d) Age
e) Disease symptoms
f) Date visited
PROCESS ANALYSIS
After the inputs are collected, the system analyzes the data and queries its
knowledge base for the actual or related medical condition. Data mining may be
conducted to examine the patient’s medical history in conjunction with relevant
clinical research. Such analysis can help predict events, which can range from
drug interactions to disease symptoms.
52
OUTPUT ANALYSIS
The CDS system with the aid of its knowledge base, applies rules to patient data
using an inference engine and displays the results to the end user(clinician) via
his monitor screen. The output here can be
Clinician diagnosis
Preventive and control mechanisms
Drug prescription
3.6 JUSTIFICATION FOR THE NEW SYSTEM
It is expected that with the introduction of the new system, a lot of positive changes
will be noticed. In the design of the diagnostic system, conscientious
effort is made to create an effective knowledge based system which would be
successfully implemented into the workflow, providing the clinician with the
necessary support in their decision making abilities.
The system will also significantly improve health workers’ performance and
improve patient outcome thus affecting the gross quality of health care delivery.
53
CHAPTER FOUR
DESIGN, TESTING AND IMPLEMENTATION OF THE NEW SYSTEM
4.0 DESIGN STANDARD
The major objective of this design is to achieve a new system that is more
diagnosis and treatment prescription based on the accurate cancer symptoms as
provided by the patient in the course of examination and the expert system’s
inference.
Here the doctor accesses the application on the computer system and keys in the
symptoms of the patient’s ailment. Once this is done, the software will diagnose
the patient based on the symptoms entered. The result of the diagnosis will be
recommended treatment for the disease.
The software design process of the proposed system after a detailed analysis of
the current system is carried out using a particular design methodology.
Top down approach has been the best approach in most engineering designers.
This involves the disintegration of the project topic itemed as system into
subsets called the subsystem.
54
In the proposed system, the system is divided into different modules and
subsystems. These subsystems perform a particular task. At the end of which
the whole system is integrated together in line with stated objectives.
The terminals at different locations are connected to the medical knowledge
base management system of the expert system. All the files, user forms,
diagnostic forms and associated programs will be connected.
The design will
also provide necessary control both manual and automated to help maintain the
integrity of the data base files.
4.1 OUTPUT DESIGN
The output form is designed to generate printable reports from the database. The
output is place on a database grid and contains information on patient’s records.
The output produced can be printed on a hard copy or viewed on the screen.
The output generated by the expert system includes:
1. Disease diagnosis report
2. Patients Report
3. Disease treatment report.
55
symptom options.
The input form desig
4.2 INPUT DESIGN
Patients Name
Sex
Age
Address
Symptoms
56
4.3 DATABASE DESIGN
In any good database design, effort should be made to remove completely or at
best reduce redundancy. The database design in the software is achieved using
Microsoft Access Database. Below is the structure of the database.
57
PATIENTS DIEASES SYMPTOMS TABLE
4.4 THE MAIN MENU
Main Menu
menu
MODULES FUNCTION:
Login: Login menu allow the user to enter his/her username and password in
Logout: The logout menu takes you out of the software environment.
Search for patient: This menu allows the user to view, edit, delete and search
for registered patient and their diagnosis cases and prescribed treatment.
Detect cancer type: This menu allows users to determine the cancer type he/she
is suffering from based on his/her selected symptom, rom the symptoms options.
Diagnose : Diagnose menu allow the user to select his/her cancer type, in other
to view more related symptoms , definition, causes and treatment concerning the
Input data
CPU
The new system was implemented using Microsoft Visual Basic programming
language. This is because the programming language has the advantage of easy
development and flexibility. It also has the ability of providing the
developer/programmer with possible hints and equally produces a graphical
user interface.
Visual Basic is an event driven, graphical user interfaced object oriented
programming environment. Structured programming allows the program to be
developed in presented module, either by using a top-down or bottom-up
method.
The hierarchy of object is in visual basic and it runs the objects, (such as
controls) which are placed in frames (another object which group other objects
virtually together), and can be placed on the form (windows which open up to
display information, or receive input from the user). These forms are linked
together by code modules to create a finished visual basic application.
Forms being objects have their own properties and methods attached to them as
well, amongst which are caption (which displays text centered at the top of the
form, the control box, (which allows one to minimize, maximize, remove,
resize, restore or close the form) and the desktop. There exist also two boxes
which allow the desktop to change the colour of the form. The toolbox which
allows one to design the screen by choosing various options from it such as
label text, checkbox and command button is also present.
Considering all these features and much more, the most preferred choice to use
was the Visual Basic for window environment, which was quite rewarding.
4.7 SYSTEM REQUIREMENTS
The computer system is made up of units that are put together to work as one in
order to achieve a common goal. The requirements for the implementation of
the new system are:
The Hardware
The Software
Software Requirement
For the effective implementation of the new system, the following software has
to be installed on the computer system.
Windows XP operating system or later
Microsoft Access Database 2010 or earlier
Visual basic 6.0
Hardware Requirement
Pentium VI and Above
1GB Ram and above
40 GB HD
Printer
4.8 CHANGE OVER PROCESS
This is the process of changing from the manual system to computerized
system. When the entire procedure obtained in an organization is converted to
automatic electronic mode. There are many methods of change over whic
include:
Direct Changeover
In this method the old system is completely replaced by the new system in one
move. This may be avoidable where the two systems are substantially different,
where the new system is a real time system, or when an extra staff to oversee its
parallel running is unobtainable. This method is comparatively cheap but i
risky. Program corrections are difficult while the system has to rem
ain
operational. The new system should be introduced during stack periods and in
large systems. It may be introduced, as an application, allowing several months
between each stage to ensure all problems are cleared up before the whol
system becomes operational.
Parallel Changeover
In this method , both the manual and computerized system are operated
users are satisfied .The old system is discontinued when discrepancies are seen
to have seized arising. It has the advantage of having an old system to fall back
on, in case the new system fails. The disadvantage is the cost of running two
systems side by side, both of which will achieve similar result.
Phase Changeover
Here, the changeover starts with a department or branch. The effect of the new
system in the sample department or branch is observed before some other
department or branch which may be more sensitive can adapt to the new system.
Pilot Changeover
In this case, some transactions that are very complex are operated using parallel
changeover and in other remaining existing system in application, dir
ect
changeover is used. The researcher recommends the ―parallel changeover‖
to
avoid drastic problems that may arise due to failure of a newly develope
system.
4.9 SOFTWARE TESTING
This defines the test requirement, which the software should meet and it
is
progressively integrated into complete package.The process of test plan is
concerned with providing that a package produces correct and expected result
for all possible input data.
For this software testing, we have three basic testing that should be adopted viz:
a. Module Testing
b. Integrated testing and
c. System testing
Module Testing
In this design we have many modules which when triggered up at certain events
perform a specific function. So, module testing involves testing of each of the
modules in software to verify that they meet their respective objective module
testing were carried out to ensure that information properly flows into and out
of the program module under test.
The Integration Test
So far, the various modules have been tested and each proved efficiency as an
entity(i.e. module). Though sometimes, the modules can perform their
respective functions but when put together, they can function together. So this
test therefore checks that when the modules are integrated they can combine to
perform their respective functions. Hence, integration testing was done to entire
program structure to uncover errors associated with interfacing. These errors
were debugged to produce desired results. The essence of integration testing is
to ascertain that these modules do not lose their efficiency and reliability. The
Integration involved the main form which serves as coordinator and driver for
other module.
System Testing
Before bringing and data processing system into use, it is of vital importance
that the system is both comprehensive within its intended limits and fully
correct. So, each routine must have been written according to specification and
tested to complete satisfaction. Also bags must have been removed completely
and the program run produced exactly what is required of it.
CHAPTER FIVE
SUMMARY, CONCLUSION AND RECOMMENDATIONS
5.0 SUMMARY
The primary goal of the breast cancer clinical decision
support systems development,
as for any
branch of biomedical research, is to improve the overall health of t
he
population. CDSSs may contribute to this by improving the quality
of
healthcare services, as well as by controlling the cost-effectiveness of medical
examinations and treatment.
The ultimate acceptance of CDS systems will depend not only on t
he
performance of the computerized method alone, but also on how well the
human performs the task when the computer output is used as an aid and on the
ability to integrate the computerized analysis method into routine clinical
practice (Hunt, Haynes, Hanna & Smith, 1998).
Issues, such as a friendly user-interface, a short system response time and low
cost, are critical for the daily routine use of CDS systems. Obviously, the
development of CDS systems requires close collaboration of two scientific
areas: medicine and computer science. This collaboration aims to cod
ify
knowledge and define the logical procedures used by the physician to reach a
conclusion.
As a result, the engineer must ―extract‖ knowledge from the physician an
d
reproduce it appropriately. This is particularly difficult because the physician’s
decisions are the result of a complex procedure combining special knowledge
and experience.
5.1 CONCLUSION
The coupling of CDSS technology with evidence-based medicine brin
gs
together two potentially powerful methods for improving health care quality. To
realize the potentials of this synergy, literature-based and practice-
based
evidence must be captured into computable knowledge bases, technical an
methodological foundations for evidence-adaptive CDSSs must be
developed
and maintained, and public policies must be established to finance t
he
implementation of electronic medical records and CDSSs and to reward health
care quality improvement.
5.2 RECOMMENDATIONS
Based on the remarkable successes recorded by clinical decision support
systems in robust health care delivery, this research work is therefor
e
recommended to approved health institutions such as: hospitals, primary health
centers, medical laboratories etc.
to further enhance diagnostic processes by
clinicians hereby guaranteeing efficiency in drug or therapy prescription a
nd
ultimately ensuring effective treatment.
Quoting Delaney, Fitzmaurice, Riaz & Hobbs, 1999, future trends an
challenges in the area of CDS systems include the creation of links to patient
electronic medical records and a universally-agreed upon medical vocabulary,
so that the entries in the medical records can have well-defined meanings. In
addition to this, studies that evaluate the performance of CDS systems in
clinical practice, in conjunction with demonstrations of cost-effectiveness, are a
critical stage in further developing CDS systems. Users should be responsible
for carefully monitoring the introduction of any new system carefully
REFERENCES
Bankman, E. S. (2000). Clinical decision support systems: Theory and Practice.
New York: Springer Inc.
Burke, J. P., & Classen, D. C. (1991). "The HELP system and its application to
infection control." J Hosp Infect 18 Suppl A: 424-431.
Bury, J., C. Hurt, et al. (2004). "A quantitative and qualitative evaluation of
LISA, a decision support system for chemotherapy dosing in childhood
acute lymphoblastic leukaemia." Stud Health Technol Inform 107(Pt 1):
197-201.
Coiera, E. (2003). Guide to health informatics. London : Oxford University
Press.
Dombal, F. T., & Leaper, D. J. (1972). "Computer-aided diagnosis of acute
abdominal pain." Br Med J 2(5804): 9-13.
Goldstein, M. K., & Coleman, R. W. (2004). "Translating research into practice
organizational issues in implementing automated decision support for
hypertension in three medical centers." J Am Med Inform Assoc 11(
5):
368-376.
http://www.cancer.org/acs/groups/content/@nho/document/acspc-024113.pdf.
http://www.medicinenet.com/breast_cancer_factsstages/article.htm.
edition
APPENDIX I
Start
Main menu
1. Patients
2. Diseases
3. Report
4. Exit
NoNo
Yes
No Yes
No
Yes
Select menu option Call
Call
Call
patient
diseases
Report
Option
Stop
Option 1?
2? Yes Yes
Option3?
4? module
diagnosis
module module