Nothing Special   »   [go: up one dir, main page]

Design and Implementation of An Expert System in Diagnosis and Treatment of Breast Cancer

Download as doc, pdf, or txt
Download as doc, pdf, or txt
You are on page 1of 74

DESIGN AND IMPLEMENTATION OF AN EXPERT SYSTEM IN

DIAGNOSIS AND TREATMENT OF BREAST CANCER


(A Case Study of Federal Medical Centre Owerri)

BY

------------------
------------

A RESEARCH PROJECT PRESENTED TO THE DEPARTMENT OF


COMPUTER SCIENCE SCHOOL OF -----------

-------------

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

steadfastness during the research.

ACKNOWLEDGEMENT

3
I thank the Almighty God, for his guidance and protection throughout the

process of writing this project.

I also want to appreciate my distinguished supervisor, Mrs. Nneoma

Ijeoma Emeagi for her guidance and contribution throughout the research.

My gratitude goes to my head of department (H.O.D.) Mrs. ---------------

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

process the work lasted.

My special appreciation also goes to my parents Mr. And Mrs. ---------,

my uncles Mr. --------, and my mentor Mr. ------- for their special support

throughout my education and I also want to appreciate my siblings who have

contribute in one way or the other.

TABLE OF CONTENTS

Title page -------------------------------------------------------------------------------i


4
Approval page --------------------------------------------------------------------------ii

Dedication -------------------------------------------------------------------------------iii

Acknowledgement.- ---------------------------------------------------------------------iv

Table of contents --------------------------------------------------------------------v-vii

Abstract ---------------------------------------------------------------------------viii

CHAPTER ONE: INTRODUCTION

1.1 Introduction -----------------------------------------------------------------------1

1.2 Background of the study ---------------------------------------------------2

1.3 Statement of the problem

---------------------------------------------------------------------------2

1.4 Objective of the study

------------------------------------------------------------------------------3

1.5 Significance of the study

---------------------------------------------------------------------------3

1.6 Scope of the study

-----------------------------------------------------------------------------------4

1.7 Limitations of the study

-----------------------------------------------------------------------------4

1.8 Definition of related terms

-------------------------------------------------------------------------4

CHAPTER TWO: LITERATURE SURVEY/REVIEW

2.1 Overview of breast cancer ------------------------------------------------------5

5
2.1.1 Types of breast cancer ------------------------------------------------------5-6

2.1.2 Diagnosis of breast cancer

–---------------------------------------------------------------6-7

2.1.3 Breast cancer staging

-----------------------------------------------------------------------------8-9

2.1.4 TNM staging system

--------------------------------------------------------------------------------9

2.1.5 Breast cancer biopsy

-------------------------------------------------------------------------------10

2.1.6 Treatment options for breast cancer

---------------------------------------------------------11-12

2.2 Review of related literatures

----------------------------------------------------------------------12

2.2.1 Clinical diagnostic support systems

---------------------------------------------------------12-14

2.2.2 Success factors of CDS systems

-------------------------------------------------------------15-18

2.3 Examples of CDSS in practice

---------------------------------------------------------------19-21

2.4 Selected contemporary example of CDSS

--------------------------------------------------21-23

CHAPTER THREE: METHODOLOGY AND SYSTEM ANALYSIS

6
3.0 Preamble

-----------------------------------------------------------------------------------------24-25

3.1 Methods of data collection

------------------------------------------------------------------------25

3.2 Analysis of existing system

------------------------------------------------------------------25-26

3.3 Block diagram of existing system

-------------------------------------------------------------27

3.4 Limitations of existing system

-------------------------------------------------------------------28

3.5 Input Process and output analysis of propose solution

–-------------------------------28-30

3.6 Justifications for the new system

----------------------------------------------------------------30

CHAPTER FOUR: DESIGN, TESTING AND IMPLEMENTATION

4.0 Design standard

--------------------------------------------------------------------------------31-32

4.1 Output design

---------------------------------------------------------------------------------------32

4.2 Input design

-----------------------------------------------------------------------------------------33

7
4.3 Database design

--------------------------------------------------------------------------------33-34

4.4 The main menu

---------------------------------------------------------------------------------34-35

4.5 System

flowchart------------------------------------------------------------------------------------

36

4.6 Choice of programming language

---------------------------------------------------------------37

4.7 System requirements

-------------------------------------------------------------------------------38

4.8 Change over process

---------------------------------------------------------------------------39-40

4.9 Software testing

--------------------------------------------------------------------------------40-41

CHAPTER FIVE: SUMMARY, CONCLUSION AND

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

cell of the breast. Although breast cancer predominantly occurs in women, it

can also affect men.

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,

lactation experience , viral hypothesis.

However hereditary and family history of breast cancer is now considered to be

two most important risk factor majority of woman now coming for medical

attention in developing countries.

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

and prevention; so as to minimizes the death rate cause of breast cancer.

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

in medical field. As an example, an expert system has been implemented for

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.

This diagnosing expert system is develop either as a standalone system or

integrated system.

11
According to Luger (1989), medical expert systems have evolved to provide

physicians and individual with computer knowledge to have a vast range of

knowledge for diagnosing and prescribing treatment for diseases with both

structured questions and structured responds within medical domains of

specialized knowledge or experience. Therefore this breast cancer diagnosis and

treatment expert system consists of both structured questions and structured

responses within medical domains.

All the parameters that have been used in this system are based on easy to

understand medical terminologies. Therefore this system can assist medical

practitioners or even individuals (patient) to diagnose the breast, give result

without first going to the doctor for diagnosis and be able to provide a system

which is very efficient, secured and reliable.

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

cancer and prescribe treatment. The objective could be summarized as follows:

 Offer prescription of medication

 Aid health care providers responsible for large patient, the expert system

can answer basic or general questions, leaving more time for individuals to

patience with peculiar situations.

 Offering prompt feedback and self evaluation.

 Providing potentially infinite array of information of the steps to take in

the eventuality of a particular occurrence.

 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

that point in time.

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 

decisions based on individualized  patient  data. Based on my case study federal

medical

13
centre (FMC),the 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  intelligen

ce

(A.I.) methods.

1.5 SCOPE OF THE STUDY

This research work expert system on breast disease diagnosis system

concentrates only on the diagnosis of some breast diseases will be concerned in

registering patients and saving their records to the database.

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, 

 making some inconsistet with  existing  realities or outrightly incorrect.

14
Great pains were however taken to ensure that these limitations are at their very

minimum 

and less impactful on the outcome of the work.

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

2.1 OVERVIEW OF BREAST CANCER

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

official data suggest.

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.

International journal of health care association. Fight against cancer (011-002)

Volume 111- No2 April 2000.

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:

1. Ductal  carcinoma  in  situ  (DCIS):  Most common type of non-invasive breast

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):  

 The   glands   are affected in this particular type of cancer but the  cancer  is

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

 which the malignancy starts in the duct  and  further  invades

the  tissue  from  where  it  can

  be spread to the distal parts  of  the body.

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 

Cancer in which there is no defined lump in the breast.  Instead the breast skin has a

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 

of Survival for the patient. 

There are numerous diagnostic procedures and screen tests currently

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 

to examine the breast  tissue. Digital mammography, also called full field

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

patient can be aware about them. Screening mammograms comprise of a total of

four views of

the breast. Standard views are taken of the right breast and two of the left. Cardio-

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.

4. Magnetic Resonance Imaging (MRI): MRI comprises of power

full magnets  that act in

conjunction with  radio waves to  produce  computer  images  showing differences

in the number 

of blood  vessels  in various types of the tissues in the body. 

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 

are studied to predict the risk factor for malignancy.

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 

evidence of cancer cells or non-cancerous abnormal cells breaking out of the part

of  the breast 

in which they originated or of invading normal neighboring tissue.

2.   Stage   1:  Describes invasive breast cancer which

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 

of presence of cancer, whereas a negative FNA gives no meaningful information. 

FNA  is  carried  out  with  a  small Syringe and needle which are used to aspirate

some cells

from the lump for an examination under the microscope.

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 

all involved  tissue. This  is  further  subdivided  into excisional

biopsy or lumpectomy 

and incisional biopsy.

2.1.6   TREATMENT OPTIONS FOR BREAST CANCER

1.   Surgery:  Surgery  is  usually  the  first  treatment  option for any

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,

then a more  conservative approach for  surgery  is approached called as

lumpectomy.   

26
In this kind of surgery  only  the  tumor  and  affected  nodes are removed whereas

the

breast mass is kept intact.

In case of aggressive cancers usually  a mastectomy  is recommended by physicians,

which

involves complete removal of the breast.

2.   Chemotherapy:  Chemotherapy is the process of

administering drugs through the 

Blood stream and affects the entire system. The treatment is used to target and

eliminate the

fast growing cancer  cells. Unfortunately

since these drugs cannot differentiate between healthy and cancer cells but eliminate

only fast dividing cells it also causes considerable damage to healthy cells. For

example the cells which are responsible for hair growth or nails.

3.   Radiation Therapy: Unlike chemotherapy radiation

therapy is more targeted and localized 

only to affected areas. The radiation treatment can be either external or internal.

In internal 

radiation catheters are used to administer the drugs at the specific area. The type and

amount of

 radiation is usually determined by the time of the surgery performed.

4.   Hormonal   Therapy: Hormonal therapy also involves

the whole body and it involves

medicine which is used to lower the risk of hormone receptor positive breast cancer. 

The hormonal treatment is based on the age of the woman and her menstruation and

27
Menopausal stages.

5.   Targeted Therapies: These are highly focused treatments

in which the protein that enables

the rapid growth of the cancer cell is inhibited. This is less harmful to healthy

cells in  comparison to chemotherapy. These drugs modify

the properties of cancerous

cells and  try and contain  the growth.

Complementary and Holistic Medicine: Even though this

stream is not considered to be an integral part of medical sciences, it

still is an effective option for breast cancer treatment.

This treatment is used in complement with surgical Procedures or chemotherapy and

radiation procedures. Complementary medicine involves a wide range from yoga

and meditation to  nutrition science and herbal medicines.

International journal of health care association. Fight against cancer (011-002)

Volume 111- No2 April 2000.

2.2 REVIEW OF RELATED LITERATURES

2.2.1 CLINICAL DIAGNOSTIC SUPPORT SYSTEMS

Advances in the areas of computer science and artificial intelligence have

allowed for the

development of computer   systems   that   support   clinical diagnostic or therapeutic

decisions

28
 based on individualized patient data(Berner and  Bell,  1998;  Shortliffe, Penna

Wiederhold, 

 and  Fagan,  1990). Medical diagnostic systems to Wikipedia—the online

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. 

These  kinds  of decision-support systems  allow the clinicians to spot  and  

choose the  most appropriate treatment.

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   

proferred,treatment as well as interactions with cares providers.

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, 

they enhance the delivery  of preventive care services and improve adherence 

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:

appendicitis,diverticulitis,perforated ulcer,cholecystitis, small-bowel obstruction,

 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

information-systems. The effectiveness, accuracy and

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

al (2004). Clinicians  answer  their questions with up to date knowledge 

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

early before  it deteriorates.

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

Obtain drugs from

Pharmacy

Fig 3.1 Block diagram of the existing system (clinical decision support system) service path

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

reliable and robust than the existing system in terms of rapid cancer prognosis,

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

displayed on the screen showin the kind can of cancer the patient is suffering from and the

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

Diagnosis Save Clear Close

Fig 4.1 Diagram of input form design of the expert diagnosis system.

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

S/N FIELD FIELD TYPE FIELD SIZE


1 No Text 15
2 Patients Name Text 20
3 Address Text 30
4 Age Integer 2
6 Sex Text 6
7 Symptoms Memo 1000
8 Diagnosis Text 100
9 Date Date/time 8
10 Treatment Text 100

Fig 4.2 Diagram of the disease symptoms table.

4.4 THE MAIN MENU

Main Menu

Login /Log out Registration Search Detect Diagnose About


for patient cancer type

Fig 4.3: Diagram of the expert system main

menu
MODULES FUNCTION:

Login: Login menu allow the user to enter his/her username and password in

order to access the software.

Logout: The logout menu takes you out of the software environment.

Registration: it shows the interface that allow new patient to enter

their information and stored the information on the database.

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

cancer type selected.


4.5 SYSTEM FLOWCHART

Input data

Input from the


keyboard Report

CPU

Disk storage Output

Fig 4.4: The diagram of the sytem flow chart


4.6 CHOICE OF PROGRAMMING LANGUAGE

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

concurrently for sufficiently long period and their outputs compared


periodically and possible discrepancies reconciled on the new system until  all

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.

Stage1A, 2009, Breast cancer staging. American joint committee on cancer. 7 th

edition
APPENDIX I

PROGRAME FLOW CHART

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

You might also like