Title:
Statistical inference for system and disease dynamics
Statistical inference for system and disease dynamics
Author(s)
Sun, Yan
Advisor(s)
Yang, Shihao
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
This thesis will focus on the application of machine learning methods in multiple research areas, including the analysis of dynamic system and healthcare analysis. On the analysis of a dynamic system, commonly modeled through ordinary differential equations (ODEs) or partial differential equations (PDEs), this work presents a methodology that infers unknown parameters from perturbed observations without numerically solving the equation, thus achieving enhanced computation efficiency. This thesis also discusses a methodology of monitoring the inherit change of a dynamic system, often presented through abrupt changes of key parameters, proposing an online algorithm that detects the change of key parameters through the flow of system observations, while keeping the statistically principled under a change-point detection diagram. In the last part, this thesis discusses the application of statistical learning in healthcare analysis, where the author utilizes causal learning methods to uncover the potential adverse effects of certain treatments, such as immunotherapy for lung cancer patients.
Sponsor
Date Issued
2024-07-22
Extent
Resource Type
Text
Resource Subtype
Dissertation