Expert system based on fuzzy rules for diagnosing breast cancer

Present problem of every country nowadays is not to defeat other countries in a war and protect its citizens, rather to defeat the deadly diseases in their own country, which are paralyzing the strength of the countries by their adverse effects. One of the major threatening diseases among them is cancer. According to latest reports given by WHO, nearly 2.3 million women were diagnosed by breast cancer in year 2020 which resulted in 685,000 deaths worldwide and this graph was highly ascended till the end of 2020 which reported 7.8 million women (alive) tested positive with breast cancer in the past 5 years which made the Breast cancer as the most prevalent cancer among all other cancers. Cancer is the result of changes in genes known as mutations, which are responsible for the growth of cells. Breast cancer cells typically form a tumor that can be diagnosed by either of these i.e., mammography, ultrasound, MRI, biopsy or by all which are dreadful and expensive procedures. Many expert systems are designed to help the oncologists in diagnosing the disease so as to save their time and efficiency, which can be utilized in treating the patients after diagnosis and gifting them back the crown of their life from which they were almost deprived off. Still there are some problems due to which these expert systems are not fully utilized for which they are meant. First problem is that these expert systems are limited to cities because of which villagers are deprived of this facility. As we know, even after 75 years of independence, women of village area are not given importance and so is their health. Second and most prevalent problem seen is the complicated and dreadful diagnosis procedure, which threatens women the most. To solve first problem, we have taken the decision to implement this system in villages after increasing its accuracy more, which will be convenient and easy for villagers. For making diagnosis phase comfortable for women, this research has opted the way which will not frighten the women, that is just to have a blood analysis by giving blood sample which can be easily undertaken without any panic, adding up a feather of novelty to our research. This work is surely going to help the oncologist, as the work has been done under the guidance of oncologist and rules of fuzzy logic are designed as per the information shared by oncologist. This paper intends to talk about the expert system that diagnosis the breast cancer using the values of nine parameters taken from Coimbra breast cancer dataset of UCI machine learning repository such as age, BMI, glucose, insulin, Homa-IR, leptin, adiponectin, Mcp-1 and resistin and gives the output as benign or malignant. This expert system is based on fuzzy logic rules which use mamdani interface system having fuzzifier for fuzzyfying the data values of parameters received from simple blood analysis, memory is used to store rules which predict the output and defuzzifier gives the output as benign or malignant with promising accuracy, sensitivity and specificity as 90.3%, 87.3% and 95% respectively. To our knowledge till now no such expert system is designed with all these attributes giving such high accuracy. It is easy to go process of diagnosing the disease with promising accuracy which will attract the women with symptoms to get it diagnosed at early stages thus help in reducing the mortality rates to a large fag end.