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.
Date of Award
Industrial and Manufacturing Engineering
Celestine C. Aguwa
Leslie F. Monplaisir
Currently, organizations have adopted and implemented a variety of innovative quality management philosophies, approaches, and techniques to stay competitive in an ever-changing global economy. Benchmarking is one of such techniques deployed by organizations to stay competitive. The motivation for this research stems from a real-world problem being faced by hospitals in the healthcare industry who have amassed a ton of data and want to embark on benchmarking project to assess the performance of the emergency departments due to challenges faced with poor management of operations which has led to high patient boarding rates, high patient wait-times, poor quality service, low patient satisfaction, and increased waste in clinical resources.
This study utilizes a unique structured and systematic benchmarking model which integrates machine learning tools such as data envelopment analysis and back-propagation neural network algorithms in analyzing and providing insights into the performance data collected from four selected emergency departments within a one-year period is presented. Data envelopment analysis (DEA) is a nonparametric approach in operations research for the estimation of production frontiers. Back-propagation neural network (BPNN) is an algorithm for supervised learning of artificial neural networks using gradient descent. The results obtained from the analysis shows that the integration of BP-DEA as a sophisticated performance prediction tool for analysis supersedes the utilization of simple statistical tools generally adopted by authors for benchmarking studies. Our analysis further presents the efficient and inefficient departments and areas for improvement in the inefficient departments are investigated. Recommendations are suggested based on the findings which when implemented leads to increased efficiency in operations, reduction in boarding rates and increased quality of healthcare services provided in the emergency department.
Etu, Egbe-Etu Emmanuel, "The Impact Of Machine Learning Algorithms On Benchmarking Process In Healthcare Service Delivery" (2018). Wayne State University Theses. 616.