Data-Driven Quality of Service Improvements in Hospitals
Public Deposited- Last Modified
- March 20, 2019
- Creator
-
Yu, Dongqing
- Affiliation: College of Arts and Sciences, Department of Statistics and Operations Research
- Abstract
- In recent years, there has been an increasing interest in developing novel methods for effective and efficient healthcare service delivery and data analytics has widely been recognized as being essential for decision-making at various healthcare service settings. This dissertation consists of three research projects each aiming to improve decisions at three different healthcare settings with one being related to critical care delivery and the other two being related to inpatient patient flow management. Each project combines statistical analysis of hospital data with techniques and methodologies from operations research. The first project concerns care delivery in the cardiac intensive care unit (CICU). We analyze a prospective study to describe admissions and care practices within the CICU of the UNC Hospital, and also evaluate the influence of an open versus closed model of care on patient outcomes and resource consumption. The second and third projects study management of patient flow from emergency department (ED) to hospital internal wards (IWs). Both projects develop effective inpatient flow management policies with the objective of reducing ED boarding time, which is defined as the time between the decision for admission for an ED patient and the time the patient is physically admitted to an IW. Delayed admission to IWs has been identified as a key factor for ED overcrowding and is a big challenge for many hospitals. We approach the problem from two different angles: early discharging patients to free up beds in IWs, and early requesting beds for ED patients based on early prediction of need for IW beds. In both projects, we develop relevant statistical models for analyzing the detailed hospital patient flow data and build mathematical decision models to develop new methods. We also build simulation models and use these models to investigate the benefits of the proposed methods. Simulation studies suggest significant potential improvements in various performance measures of interest.
- Date of publication
- December 2016
- Keyword
- DOI
- Resource type
- Rights statement
- In Copyright
- Advisor
- Ziya, Serhan
- Ji, Chuanshu
- Katz, Jason
- Shen, Haipeng
- Argon, Nilay
- Degree
- Doctor of Philosophy
- Degree granting institution
- University of North Carolina at Chapel Hill Graduate School
- Graduation year
- 2016
- Language
Relations
- Parents:
This work has no parents.
Items
| Thumbnail | Title | Date Uploaded | Visibility | Actions |
|---|---|---|---|---|
|
|
Yu_unc_0153D_16603.pdf | 2019-04-12 | Public | Download |