Document Type

Dissertation

Date of Award

8-31-2021

Degree Name

Doctor of Philosophy in Business Data Science - (Ph.D.)

Department

Data Science

First Advisor

Michael A. Ehrlich

Second Advisor

Yi Chen

Third Advisor

Dantong Yu

Fourth Advisor

Jorge Eduardo Fresneda Fernandez

Fifth Advisor

Zhi Wei

Abstract

According to the National Academy of Medicine (NAM) (formerly called the Institute of Medicine), a quality health care system embodies six attributes: timeliness, equity, safety, efficiency, effectiveness, and patient-centeredness. Timeliness is to avoid unnecessary delays in care delivery for patients and caregivers; equity is to ensure that the quality of care that patients receive does not vary based on their personal characteristics; safety is to ensure that the care that is intended to help patients does not harm them; efficiency is to avoid waste and optimize resource allocation to improve care delivery; effective care is one that relies on sound scientific knowledge and delivers the most benefit to the patient; and patient-centeredness concerns the contributions of patients, their family members, and care givers to the patient's health. Thus, to make progress in quality care improvement, every aspect of the health care system as related to these six items must be improved.

Recent efforts targeted at improving quality of care in urgent care settings have included benchmarking and performance measurement, financial incentivisation, public reporting of performance data, adoption and use of health information technology, and other quality improvement initiatives. With the advent of artificial intelligence (AI), many believe there is potential for transformation of the health care industry through adoption of AI technologies.

Through a series of essays, this dissertation contributes to the literature on timeliness, equity, and efficiency in the emergency department. The first essay assesses recent trends in emergency department throughput in the United States. The second assesses current trends and sources of inequities in emergency department wait time across racial and ethnic groups. In the third, a model aimed at improving efficiency in the emergency department is developed ? an explainable machine learning model that leverages text data to predict patient disposition during triage is developed.

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.