Off-campus WSU users: To download campus access dissertations, please use the following link to log into our proxy server with your WSU access ID and password, then click the "Off-campus Download" button below.
Non-WSU users: Please talk to your librarian about requesting this thesis through interlibrary loan.
Access Type
WSU Access
Date of Award
January 2017
Degree Type
Thesis
Degree Name
M.S.
Department
Industrial and Manufacturing Engineering
First Advisor
Ratna B. Chinnam
Abstract
Many of the patients’ journeys begin in the Emergency Department. ED overcrowding as a major barrier to receiving timely emergency care jeopardizes the reliability of the emergency care systems. Within the ED system, the triage nurse will evaluate the patient’s condition and
record the information as a triage note. The “fast track” system then filters the minor cases of illness to be treated by nurse practitioners and determines the patients that need to be treated by physicians. A Medical Decision Support (MDS) system can speed up this process.
The goal of this study is to compare the performance of graphical models such as a Bayesian network against popular machine learning models such as a support vector machine for predicting disease conditions at the end of ED triage using the free text note from the triage nurse. We also demonstrate the advantage of relying on the Unified Medical Language System (UMLS) for preprocessing the triage note text for improved classification.
Recommended Citation
Marashi, Sheida, "Predictive Models For Disease Diagnosis Using Triage Data" (2017). Wayne State University Theses. 629.
https://digitalcommons.wayne.edu/oa_theses/629