A Mobile-Based Fuzzy Expert System for Breast Cancer Growth Prognosis

487

A Mobile-Based Fuzzy Expert System for Breast Cancer Growth Prognosis

CHAPTER ONE

INTRODUCTION

1.1 Background to the Study

Information and Communication Technology (ICT), specifically mobile health (mHealth), can play a key role in enhancing and enabling health care systems, when linked to specific needs. The initiation of various types of mobile portable computer devices – smartphones, private digitally powered assistants, and tablet systems has influenced an appreciated positive impact in many works of life which includes the health sector. This has been influenced by the increasing excellence and availability of application software in the health sector, (Aungst, 2013). These softwares are set of instructions that have been written in a particular programming language to run on a moveable portable aid or on a computer system to achieve a particular purpose, (Wallace, Clark & White, 2012). In recent development faster processors and improved memory in the analysis of complex data in the health sector have paved the way for diverse medical mobile expert systems. These systems are either individualised or used by medical expert (Ozdalga, Ozdalga & Ahuja, 2012). These portable application systems are designed to supplement the experts work in order to deliver a resource that will advance the results for private health monitoring and at the point of care (Aungst, 2013). There are existing medical expert system models and health calculators which include Breast Cancer Surveillance Consortium (BCSC) Risk Calculator (for breast cancer risk calculation), the Breast Cancer Risk Assessment Tool (the Gail model) often used by health care providers to estimate risk, MedCalc. These models did not explore detail risk factors for breast cancer growth, and detail fuzzy rules were not explored as well. Most of the mobile health calculators for breast cancer prognosis are not user friendly. They are not readily available for personal use and are majorly used by the medical professionals in the the health care sectors.

World Health Organisation (WHO) in 2012 described cancer as a leading cause global deaths. In, 2008 cancer accounted for about 13% (7.6 million) deaths (WHO, 2017). There are divergent views on the exact cause of breast cancer. Though, knowing an individual risk factors and preventing the growth of the malignant (breast cancer) could be a preferred approach to tackling this disease because most research works that have developed models for prognosis and diagnosis have not actually reduced the death rate (Global Cancer Facts & Figures, 2015). This is because reviewed literatures have shown that the existing systems focused on diagnosing/prognosing the survivability and recurrence of the disease. By the time patients report at the hospital for diagnosis, the tumour has grown to the metastatic stage where survival is almost impossible.

Majority of the models applied in medical field are naturally unclear. As a result of the unclear (fuzzy) nature of medical data and models as well as the relationships that exist in the models, fuzzy logic technique is suitable for medical applications. Fuzzy logic (an aspect of soft computing) proposes approaches of result production that have the capability of estimated representation of decisions. As a result of the difficulty in medical exercise, the old-style numerical study methods are not satisfactory and may not be suitable. The utmost causes of ambiguity are as follows:

Incomplete data about an individual: either from patient or family members.

Often time, the patient’s state of health account is provided by the individual, or by the family member. These data to a large extent are subjective and ambiguous.

The well being check-up: Often time, medical practitioners get impartial facts.

Laboratory test and prognosis results may also be subject to various mistakes.

The delinquency of patient’s preceding health status check-up can also cause error in the test report.

Symptoms might be faked or overstated more/fewer than they truly appear.

Patients are likely to neglect some of the symptoms.

Some symptoms might be indescribable by patients.

Hence, fuzzy logic a soft computing methodology has the capability to reduce uncertainty in decision making in medical field.

1.2 Statement of the Problem

The most recurrent and second leading cause of death in women is breast cancer. The inadequacies of the existing methods, such as Mammography, Magnetic Resonance Imaging (MRI), Self-examination and others, account for the breast cancer high mortality. The shortcomings of the existing models include:

Late discovery of the cancerous germs – these methods only detect breast cancer at the metastatic stage. (the tumour has grown and spread to other parts of the body);

Existing models cause patients pains and related inconvenience which dissuade women from voluntary screening. Thus, most people do not report cases of breast cancer until it has got to the third stage and stack the odd of survival against the patient.

Imprecise diagnosis because it involves several layers of uncertainty. These shortcomings make the traditional approaches inappropriate.

Thousands of people fall victim to breast cancer every year due to limitation of medical services and the inability to use the existing services effectively. Late presentation of cases at advanced stages when little or no benefit can be derived from any form of therapy is the hallmark of breast cancer among Nigerian women. The available breast cancer calculators are only focused on survivability and re-occurrence and also not safe because individuals do not know where their personal data is being saved. To curtail the worsening incidence of breast cancer deaths, a Mobile-based Fuzzy Expert System (MFES) for breast cancer pre-growth prognosis that would obviate the inadequacies of the existing models, encourage voluntary personal screening and more importantly, detect the risk of developing breast cancer is designed. Pre growth prognosis of a disease like breast cancer is very crucial to a successful reduction of death rate caused by the disease. This research weaved its solution/prognosis intervention around a nature motivated method that is biologically inspired. This method would be able to detect the risk of early developments and proffered likely solutions thereby reducing the consequence of ignorance which may lead to death.

1.3 Objective of the Study

The general objective of this study work is to design and implement a Mobile-based Fuzzy Expert System (MFES) for breast cancer pre-growth prognosis. The fuzzy expert system would be capable of capturing ambiguous and imprecise information prevalent in breast cancer prognosis. The specific objectives are to:

determine the range values for the Membership Function (BreastCancerRisk factors) using experts rating for the indicators for fuzzification;

formulate the membership functions using information in (1);

design a MFES for breast cancer pre-growth prognosis and implement and carry out performance evaluation of the developed mobile based fuzzy expert system using in comparison existing fuzzy logic models.

1.4 Methodology

In order to achieve the stated objectives, the following approaches were considered:

1. Upper and lower values were determined from the values (facts) collected from the domain experts to determine the membership functions.

2. Membership functions for all the risk factors were formulated, using the values in (1).

3. The rules for all the risk factors were formulated.

4. Java expert system shell (JESS) was used to develop the MFES, using the informations in (1), (2) and (3) and this runs on Android systems.

5. The MFES performance evaluation was carried out using data from healthy people and those already diagnosed with the disease and also in comparison with existing fuzzy logic models.

Get Full Work


Disclaimer:
Using this Service/Resources:
You are allowed to use the original model papers you will receive in the following ways:
1. As a source for additional understanding of the subject.
2. As a source for ideas for your own research work (if properly referenced).
3. For PROPER paraphrasing (see your university definition of plagiarism and acceptable paraphrase)
4. Direct citing (if referenced properly)
Thank you so much for your respect to the authors copyright.