Description
The investigation of healthcare environments in China is rapidly developing to establish evidence-based design (EBD) databases tailored to local conditions. These databases aim to enhance the quality of healthcare environments. However, current global EBD studies lack credible evidence due to challenges in conducting comparative research on patients in real healthcare settings. Existing evidence focuses on individual environmental parameters rather than considering the integrated influence of multiple parameters. This disparity between research findings and real-world conditions hinders the practical application of EBD in design. Drawing from previous experiences, this research employs a data-driven analysis model to explore the integrated influence of multiple environmental parameters on occupants in real-world healthcare environments. By utilizing this model, substantial progress can be made in evidence-based healthcare environment studies, acquiring highly credible and realistic design evidence for improved practical application.To achieve this research objective, a comprehensive multi-strategy approach, integrating desktop research and field investigations, was employed. The desktop research involved a thorough review of environmental interventions and analysis of underlying mechanisms influencing thermal sensation. Field investigations encompassed data collection in actual hospital wards to develop a personal thermal sensation prediction model for patients using artificial neural network (ANN) technology. Additionally, the model's practical applicability is explored through follow-up interviews with potential end-users, including designers, HVAC engineers, and hospital managers.
The data-driven multi-factorial analysis model serves as a valuable tool for designers, engineers, and researchers, providing reliable and credible design evidence to support decision-making processes. It aids spatial design by identifying optimal placements for elements such as doors, windows, air conditioning outlets, furniture, and inpatient beds. Furthermore, the model contributes to patient-centered healthcare environment design by balancing energy conservation and occupants' environmental preferences. It assists medical staff in allocating inpatient beds and appropriate wards based on patients' thermal preferences. Moreover, the multi-factorial analysis model helps researchers practically study healthcare environments, enabling the gathering of reliable evidence to improve overall quality.
Period | 1 Sept 2019 → 22 Mar 2024 |
---|---|
Examinee | |
Examination held at | |
Degree of Recognition | International |
Keywords
- Evidence-based design
- Healthcare environments
- Artificial Neural Network
Documents & Links
Related content
-
Research output
-
An Artificial Neural Network-based model that can predict inpatients’ personal thermal sensation in rehabilitation wards
Research output: Contribution to journal › Article › peer-review
-
Indoor Thermal Comfort Prediction Model for Patients in Rehabilitation Wards
Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review
-
Investigating spatial impact on indoor personal thermal comfort
Research output: Contribution to journal › Article › peer-review
-
Projects
-
BIM-based Design Strategies for Improving the Overall Quality of Healthcare Environment
Project: Internal Research Project