ABSTRACT

Studies show that fuzzy logic has different approaches for enhancing personal health care delivery in the health care sector. Currently, breast cancer rated as the second leading cause of death among women, according to the World Health Organisation. Previous studies relating to breast cancer prognosis using fuzzy logic approach were directed at reoccurrence of the disease as well as the survivability of individual. However, there is need for early identification of the predisposing risk factors to breast cancer growth and its elimination. Consequently, this study focuses on developing an efficient Mobile-based Fuzzy Expert System (MFES) for initial breast cancer growth prognosis that can predict the individual risk level and thus, reduce the high incidence rate.

Facts relating to the predisposing factors of breast cancer were elicited from four domain experts through direct contact; this was used to generate the appropriate fuzzy rules. The fuzzy inference approach was employed to formulate the membership functions and fuzzy rules to design the MFES. Mamdani approach was used for the fuzzification of input and de-fuzzification of the output. The system accommodates imprecision tolerance and uncertainty to achieve tractability, robustness and least solution cost.  Java expert system shell running on Android operating system was used to achieve the mobile technology aspect of the system. For the purpose of system evaluation, 2500 data were collected from two health care centers in Nigeria using random sampling technique. The data were stratified into twenty-five different strata. Each stratum contained 100 dataset and four individual data were selected at random.

The result indicated that the fact elicited from the experts serves as range values for the 12 risk factors used for the fuzzification of the input and thus, 36 rules were generated. The rules were used as basis for the development of the MFES. The developed MFES for breast cancer growth prognosis recorded 96% accuracy for all dataset picked from the 25 different strata. The system showed that with higher number of fuzzy rules focusing on pre-tumour growth and detailed predisposing risk factors; the prediction of risk level was reliable.

This work provided the resource for an individual to personally examine the breast cancer risk level, showing that the predisposing risk factors can be reduced by personal health monitoring. Though, MFES employed higher number of fuzzy rules unlike the existing systems with less number of rules; it supports pre-tumor growth instead of post-tumor growth which was incapable of handling the high incidence rate. It is therefore recommended that MFES be used to detect predisposing breast cancer  risk levels early enough. The main contribution of this work is the reduction of the incidence rate in contrast to the existing methods currently applied in the diagnosis of breast cancer.

Keywords: Soft Computing, Fuzzy Set, Breast Cancer, Risk Factors, Membership Functions

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.