Huichao Dong
Department of Architecture, University of Pennsylvania, Philadelphia, PA, USA

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Data-Informed UI Decision Cards for Emergency Department Renovation: Linking Patient-Flow Simulation to Configurable Spatial Scenarios Huichao Dong; Xiaoming Xiao; Sarah Li
International Journal of Graphic Design Vol. 3 No. 2 (2025): October| IJGD: International Journal of Graphic Design
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/ijgd.v3i2.4014

Abstract

Emergency department renovation requires designers to connect operational indicators with spatial planning choices through a clear visual interface. This study developed and analytically demonstrated a data-informed UI decision-card prototype linking patient-flow analysis to configurable wayfinding, nurse-station, and staff-support scenarios. The analysis used public CSV files from the 2024 Synthetic Dataset of Emergency Healthcare Services, with the California Emergency Department Volume and Capacity dataset providing facility-level context. Dataset-derived variables included waiting time, queue count, resource utilization, length of stay (LOS), and satisfaction; wayfinding friction, walking load, visibility, collaboration, station count, and respite-room count were prespecified scenario inputs. Composite indices represented ED pressure and operational staff-support review. The outpatient analysis set contained 236 records. Mean total waiting time was 36.42 minutes, mean LOS was 50.79 minutes, mean simulated satisfaction was 82.84%, and mean ED Pressure Index was 0.298. Gradient boosting achieved a mean five-fold RMSE of 4.119 and an R² of 0.944 on the synthetic data; its output served as a secondary-priority cue for congestion and provider-load cards. CheckPatientType had the highest mean wait, and Triage the highest mean provider utilization. Under the prespecified scenario inputs and base-case weights, Scenario C received the highest support score (66.95) and highest collaboration risk. Evidence labels indicate whether each card is based on dataset variables, model outputs, or configured scenario inputs, making the basis of each renovation trade-off explicit.