|
" Experimental Investigation of Concrete Breakout Strength of Anchors in Shear within Fiber Reinforced Concrete "
Khanfar, Mohammad A.
Azzawi, Raad
| Document Type
|
:
|
Latin Dissertation
|
| Language of Document
|
:
|
English
|
| Record Number
|
:
|
1054723
|
| Doc. No
|
:
|
TL53840
|
| Main Entry
|
:
|
Mahyoub, Mohammed A.
|
| Title & Author
|
:
|
Improving Health Referral Processing Using Machine-Learning-Guided Simulation: A Care Management Setting Case Study\ Mahyoub, Mohammed A.Khasawneh, Mohammad T.
|
| College
|
:
|
State University of New York at Binghamton
|
| Date
|
:
|
2020
|
| Degree
|
:
|
M.S.
|
| student score
|
:
|
2020
|
| Note
|
:
|
115 p.
|
| Abstract
|
:
|
Health referrals are very important as a way of containing the health conditions of chronically ill and elderly patients, especially patients admitted to the emergency department. Therefore, processing health referrals has been adopted as an essential part of the care management paradigm. In this thesis, a machine-learning-guided discrete event simulation framework to improve health referrals processing is proposed. The modeled system in this study is complex in the sense that it is composed of several affiliated hospitals (e.g., H1, H2, and H3) and a referral creation unit (RCU) of the care management organization. The proposed process improvement framework is centered around incorporating a prediction module to predict patient discharge date and referral type to allow for early demand estimation. The latter can be used for early planning, processing, and prioritization. Integrating machine learning and discrete event simulation approaches provides the advantage of testing the proposed approach. To illustrate, the machine learning part of the model aims at predicting the demand of RCU (i.e., health referral requests from affiliated hospitals). The discrete event simulation part models the referral request journey from the inpatient hospital to the RCU. Given the fact that health referrals should be created before patient discharge to ensure a smooth transition, this research aims to improve the process of creating health referrals on time. The prediction models performed well across all affiliated hospitals. By incorporating a prediction module for the referral processing system to plan and prioritize referrals, the overall performance was enhanced in terms of reducing the average referral creation delay time by about 50% compared to the baseline model of the current system configuration. This research will emphasize the role of post-discharge care management in improving health quality and reducing associated costs. Considering the fact that there is a shortage of research in using machine learning and/or simulation modeling in care management settings, this thesis will guide care management organizations to start using these powerful methods in their process improvement initiatives. Generally, the current study will demonstrate how to use integrated systems engineering methods for process improvement of complex healthcare systems.
|
| Descriptor
|
:
|
Artificial intelligence
|
|
|
:
|
Biomedical engineering
|
|
|
:
|
Industrial engineering
|
|
|
:
|
Public health
|
| Added Entry
|
:
|
Khasawneh, Mohammad T.
|
| Added Entry
|
:
|
State University of New York at Binghamton
|
| |