Date of Award

Spring 5-18-2020

Document Type

Thesis

Degree Name

B.B.A. with honors

Honors Designation

yes

Program of Study

Computer Information Systems - Data Analytics

Language

English

First Advisor

Arturo Castellanos

Second Advisor

Kevin Craig

Third Advisor

Zeda Li

Abstract

The healthcare industry is primed for a massive transformation in the coming decades due to emerging technologies such as Artificial Intelligence (AI) and Machine Learning. With a practical application to the UNOS (United Network of Organ Sharing) database, this Thesis seeks to investigate how Machine Learning and analytic methods may be used to predict one-year heart transplantation outcomes. This study also sought to improve on predictive performances from prior studies by analyzing both Donor and Recipient data. Models built with algorithms such as Stacking and Tree Boosting gave the highest performance, with AUC’s of 0.6810 and 0.6804, respectively. In this work, a roadmap was created that justifies the need for these technologies in healthcare. In application, the data was prepared, models were built using advanced algorithms, and important variables were selected. These steps were continuously done with validation from experienced clinicians. To yield greater insights in this study, the dataset was split row-wise by factors such as LVAD Support, Donor/Recipient Gender Combinations, and Time Period; this rendered 8 new datasets for analysis. This work explores the trade-off between interpretability and performance in applying analytic methods in a real-world problem in this domain. Finally, forward looking industry implications are discussed.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.