Publicação
Predicting Emergency Attendance at a Tertiary Hospital: An Emergency Department Data Warehouse Project
| Resumo: | The overcrowding of emergency departments (ED) has been a well-known problem worldwide. Over the years, many solutions have been proposed, demonstrating that improving task processes and management through business intelligence (BI) applications results in better outcomes. C.H.U.L.N. is the largest Portuguese hospital, providing third-level services, and its unique characteristics present a management challenge. Consequently, the excessive influx of patients to the emergency room is a more pronounced issue compared to other institutions. Therefore, the purpose of this thesis is to create a data warehouse for the C.H.U.L.N.'s Emergency department. This will facilitate the future development of a patient influx prediction algorithm, ultimately improving departmental management. To determine which information should be included in the data warehouse for the future algorithm, it was necessary to understand, based on existing projects and algorithms, what relevant information should be considered. As a result of the Data Warehouse Project, a constellation schema composed of two star schemas was designed. The relevant patient information identified in the literature includes the patient's age, gender, date and time of admission to the ED, diagnosis, Manchester Triage System (MTS) priority color, patient checkout condition, and other selected information. These factors were considered in the Data Warehouse. The project focuses on two main fact tables - Emergency Assistance and Outpatients - which enable access to selected information about ED patients. This information can be compared with the selected information about patients receiving treatment in service wards and during medical appointments. Analyzing the C.H.U.L.N.’s ED flowchart from the moment the patient enters the department, it seemed important to consider other factors such as waiting times in minutes. This thesis intends to serve as an intermediary step, creating a suitable data warehouse that permits the future development of a influx prediction algorithm, along with other potential projects. The application of BI is an important step in the development, improvement and sustainability of healthcare, which is the primary focus of this entire thesis. |
|---|---|
| Autores principais: | Gonçalves, Catarina Sousa |
| Assunto: | Business Intelligence Healthcare Sustentability Data Warehouse SDG 3 - Good health and well-being SDG 9 - Industry, innovation and infrastructure SDG 12 - Responsible production and consumption |
| Ano: | 2023 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| Resumo: | The overcrowding of emergency departments (ED) has been a well-known problem worldwide. Over the years, many solutions have been proposed, demonstrating that improving task processes and management through business intelligence (BI) applications results in better outcomes. C.H.U.L.N. is the largest Portuguese hospital, providing third-level services, and its unique characteristics present a management challenge. Consequently, the excessive influx of patients to the emergency room is a more pronounced issue compared to other institutions. Therefore, the purpose of this thesis is to create a data warehouse for the C.H.U.L.N.'s Emergency department. This will facilitate the future development of a patient influx prediction algorithm, ultimately improving departmental management. To determine which information should be included in the data warehouse for the future algorithm, it was necessary to understand, based on existing projects and algorithms, what relevant information should be considered. As a result of the Data Warehouse Project, a constellation schema composed of two star schemas was designed. The relevant patient information identified in the literature includes the patient's age, gender, date and time of admission to the ED, diagnosis, Manchester Triage System (MTS) priority color, patient checkout condition, and other selected information. These factors were considered in the Data Warehouse. The project focuses on two main fact tables - Emergency Assistance and Outpatients - which enable access to selected information about ED patients. This information can be compared with the selected information about patients receiving treatment in service wards and during medical appointments. Analyzing the C.H.U.L.N.’s ED flowchart from the moment the patient enters the department, it seemed important to consider other factors such as waiting times in minutes. This thesis intends to serve as an intermediary step, creating a suitable data warehouse that permits the future development of a influx prediction algorithm, along with other potential projects. The application of BI is an important step in the development, improvement and sustainability of healthcare, which is the primary focus of this entire thesis. |
|---|