Loading...

Machine Learning for Optimizing Drug Dosing in Anti-Angiogenic Cancer Therapy

Darabi, Atyeh | 2025

0 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 57946 (02)
  4. University: Sharif University of Technology
  5. Department: Mathematical Sciences
  6. Advisor(s): Moghadasi, Reza
  7. Abstract:
  8. Optimal drug dosing is one of the fundamental challenges in treating complex diseases such as cancer. Cancer, characterized by the rapid growth of tumors and the stimulation of angiogenesis to form new blood vessels for providing nutrients and oxygen, is one of the most significant public health threats. Angiogenesis is influenced by factors that guide the migration and aggregation of endothelial cells toward the tumor. In this study, the Anderson-Chaplain mathematical model was utilized to simulate the dynamics of angiogenesis and analyze the effects of relevant biological parameters.To better understand this process, topological data analysis and clustering methods were applied to the simulated vascular structures. These analyses enabled the extraction of morphological patterns of vascular networks and explained the role of key factors (such as chemotaxis and haptotaxis) in shaping these networks.To optimize treatment, pharmacokinetic and pharmacodynamic (PK/PD) models, which are scientific disciplines focused on mathematical modeling in drug development, were employed alongside a deep reinforcement learning approach. These models simulate patient responses to anti-angiogenic drugs and propose a policy for optimal dosing. The primary goal of this research is to inhibit angiogenesis and reduce endothelial cell density in tumor vascular networks while minimizing side effects such as hypertension and proteinuria. By integrating mathematical methods and machine learning, this study provides an effective approach for managing cancer treatment and personalizing drug dosing
  9. Keywords:
  10. Anti-Angiogenic Drug ; Machine Learning ; Deep Reinforcement Learning ; Tumor Angiogenesis ; Optimal Drug Dosing

 Digital Object List

 Bookmark

...see more