Using Dynamic Bayesian Networks for management of breast cancer treatment

نوع: Type: thesis

مقطع: Segment: masters

عنوان: Title: Using Dynamic Bayesian Networks for management of breast cancer treatment

ارائه دهنده: Provider: Nahid Najafi Birgani

اساتید راهنما: Supervisors: Dr. Vahid Khodakarami

اساتید مشاور: Advisory Professors:

اساتید ممتحن یا داور: Examining professors or referees: Dr. Javad Behnamian,Dr. Nafise Soleimani

زمان و تاریخ ارائه: Time and date of presentation: 2024

مکان ارائه: Place of presentation: 61

چکیده: Abstract: Breast cancer is one of the most common diseases among women and has been identified as one of the major causes of death for women in Iran, leading to significant personal, familial, and social damages. One of the current challenges faced by patients is the lack of proper understanding of the importance of early diagnosis and the management of cancer treatment. Various tools have been used for the early detection of breast cancer; however, it appears that this disease, in addition to early detection, requires monitoring, evaluation, and decision-making throughout different treatment phases. In this study, we aim to use the concept of dynamics to demonstrate how changes in factors affecting the disease level can alter the patient's condition during each treatment phase. Due to the presence of uncertainties and complexities, a Bayesian network approach was employed in this research. By considering the identified risk factors through literature review and expert opinions, a process for developing an integrated model was proposed, and modeling was conducted based on this process. The model's performance was validated using various scenarios. A case study evaluating the status of four patients at different stages of diagnosis and treatment was assessed based on the final model. The innovative aspects of the model include considering factors such as side effects and costs of various treatments during treatment phases, as well as identifying different treatment factors in each phase and determining their significance at different stages. This model allows for the evaluation and measurement of the impact of factors affecting the target node. Our results and evaluations can predict various patterns according to the patients' conditions. Physicians and patients can use the obtained results in their decision-making processes

فایل: ّFile: Download فایل