Red Flagging of Patient Data in the Emergency Room: a User-Centered Design

Emergency departments (EDs) are high-pressure environments where factors like rapid decision-making, overcrowding and resource constraints can lead to errors and reduction in the quality of provided care. At the Aarhus University Hospital (AUH) in Denmark, patient data such as medical history is collected on a large scale and made available digitally through an Electronic Patient Journal (EPJ) to enhance overall patient care. However, the volume of data poses challenges for the medical staff in the ED, necessitating efficient ways to filter critical information. In this context, this paper describes the design of an application for 'red flagging', which will later be developed using Artificial Intelligence (AI). Its goal is to identify critical patient information and highlight potential risks that might otherwise be overlooked by the ED's medical staff. This research examines the topic from the user's perspective, exploring different methods to incorporate a red flagging system into existing healthcare workflows. The primary focus is on investigating the potential design and visualization of the red flagging functionality to ensure that the information delivered by the AI will benefit the ED staff. In this context, a user-centered design process was implemented, resulting in the creation and evaluation of a design prototype. This prototype serves as a practical exploration of how such an application can be tailored to meet the needs and requirements of its users while aligning with existing systems. It also gives an outlook on the potential of integrating such systems, as well as the concerns and requirements that must be addressed to implement AI-based software into clinical practice.