Treffer: DEVELOPMENT OF WEB-BASED FUZZY EXPERT SYSTEM FOR BREAST CANCER RISK PREDICTION.

Research indicates that fuzzy logic offers various approaches to improve the delivery of personal healthcare within the healthcare sector. Presently, breast cancer ranks as the second leading cause of death among women, as reported by the World Health Organization. Previous studies that applied fuzzy logic to breast cancer risk focused on disease recurrence and individual survivability. However, there is a growing necessity to identify the risk factors predisposed to breast cancer growth and mitigate these risks at an earlier stage. Therefore, this study concentrates on the development of an efficient web-based Fuzzy Expert System (WFES) for breast cancer risk prediction. This system aims to predict an individual's risk level, ultimately reducing the high incidence rate of breast cancer. To obtain information regarding the factors that predispose individuals to breast cancer, data were collected from four domain experts through direct contact. This data was then used to formulate relevant fuzzy rules. The fuzzy inference engine was applied to establish membership functions and fuzzy rules, which served as the foundation for designing the WFES. The Mamdani approach was employed for input fuzzification and output de-fuzzification. This system accommodates imprecision, tolerance, and uncertainty to ensure tractability, robustness, and minimal solution cost. Python was utilized for modelling, and JavaScript was used for system implementation. The study's results indicated that the information obtained from experts defined the range values for six risk factors used in input fuzzification, resulting in the generation of fifty rules. These rules formed the basis for the development of the WFES. This work empowers individuals to assess their breast cancer risk level, emphasizing the potential to reduce predisposing risk factors through personal health monitoring. [ABSTRACT FROM AUTHOR]

Copyright of Science World Journal is the property of Science World Journal and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)