A Retrospective Data Analysis on the Breast Cancer Patients Epidemiology and Awareness in the Eastern Regions of Saudi Arabia

According to the Ministry of Health (MoH), breast cancer is the leading cause of death for women in Saudi Arabia. Unfortunately, there is a lack of statistical evidence-based data mining on the population data to help establish clinical centers and programs for breast cancer, especially in the isolated and deserted regions of Saudi Arabia. The main objective of the study is to address this issue and the research gap. In this regard, we have made three major contributions in the current study. First, we illustrate the latest developments in data mining techniques applied to screening data relevant to the region and applicable to patients facing similar socio-economic and socio-cultural challenges. In this case, Naïve Bayes and J48 classifiers were investigated along with K-means clustering. Second, we conducted a retrospective analysis of 10 years of clinical hospital data collected between June 2010 and June 2020 from the breast cancer data repository. Third, we conducted a self-awareness survey in which 1,731 participants responded on various critical reasons for better understanding. Several conclusions were drawn for instance, awareness among the men was significantly low compared to ladies and people are not having a habit of regular checkups. Our contributions aim to provide a sustainable solution to the healthcare section and encourage researchers to develop more sustainable and innovative approaches apart from the techniques used in the study.