An architectural workflow database for generating evidence-based healthcare facilities' design via transfer learning

Paper i proceeding, 2026

Evidence-based design principles can help overcome legislative shortcomings and long-standing challenges in designing healthcare units. Leveraging these principles through transfer learning can utilize pre-trained knowledge to generate optimal spatial arrangements, yet the dataset-formulating factors remain scarcely investigated. Therefore, we employ mixed-methods research (including workflow analysis and behavioral mapping in an emergency care unit) to generate a highly contextual evidence-based database. Using four actor flow scenarios, we identified dead zones, nodes, collision points, approximate nursing distances, and zone mapping as key contextual factors. This study contributes to informing design considerations and the contextual training of transfer learning in generative healthcare architecture.