University of Illinois Urbana-Champaign

Pathophysiological model for early detection of sepsis

Chen, Zikun

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/107270

Description

Title
Pathophysiological model for early detection of sepsis
Author(s)
Chen, Zikun
Contributor(s)
Lui, Sha
Issue Date
2020-05
Keyword(s)
  • medical guidance system
  • preventable medical error
  • pediatric sepsis
  • pathophysiology model
  • data-driven early warning system
Abstract
Pathophysiology Centric Early Detection and Treatment Guidance System is a cyber medical early warning system which assists the early detection of the onset of serious adverse events by guiding medical staff to take preemptive interventions. This guidance system is a pathophysiologic model-based and data-driven early warning system: it keeps track of multiple pathophysiological processes, their interactions, and updates the patient state based on the requested information obtained in real time. The objective of this thesis is to examine a Bayesian method to achieve a reliable prediction by transforming a Boolean decision tree that is commonly used for diagnosis to a trustable and interpretable probability based graph that can be used for early detection of pediatric sepsis and visualization for medical practitioners. This thesis compares the current diagnosis methods of sepsis, shares the results of Bayesian implementation, and proposes possible avenues for future early detection tools that can be used in a medical guidance system. The approach used in this thesis is to transform the decision tree used for Systemic Inflammatory Response Syndrome (SIRS) into a simple Bayesian model. Further improvements of the model are needed and will be discussed in this thesis.
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/107270

Owning Collections

Senior Theses - Electrical and Computer Engineering PRIMARY
The best of ECE undergraduate research