University of Twente Student Theses


Bayesian-Network updating using novel clinical data

Huh, Jeongyeon (2023) Bayesian-Network updating using novel clinical data.

[img] PDF
Abstract:Endometrial cancer is one of the most common cancers affecting women worldwide and exhibits a complex nature with varying patient responses to treatment. The current growing interest in using advanced computational techniques offers promising opportunities to improve prognostic predictions in these complex cases. This study aims to investigate the relationship between endometrial cancer and various biomarkers, analyze possible treatment options, and determine patient-specific probabilities for treatment outcomes by looking into the presence of lymph node metastasis and survival rates. The study utilizes Bayesian networks which can potentially contribute to the development of more accurate and clinically relevant prognostic tools for endometrial cancer patients, improving clinical management and treatment outcomes. The performance of a Bayesian network model by leveraging score-based structure learning and local parameter learning was demonstrated. In the model-building process, the insignificant biomarkers were removed, and new variables were added to more accurately represent endometrial cancer prognosis. The results demonstrate the potential of Bayesian networks to provide personalized prognostic predictions, ultimately enabling clinicians to make better-informed decisions and improve patient outcomes in endometrial cancer treatment.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page