RadStream: An interactive visual display of radiology workflow for delay detection in the clinical imaging process

Given the high caseload most radiology departments face on a daily basis, workflow streaming becomes a necessity. In addition, workflow optimization can significantly reduce cost and increase efficiency and productivity. In this paper, we present RadStream: a web-based retrospective, exploratory, interactive data visualization tool that provides a comprehensive overview of the radiology department's daily activities. We worked closely with radiology staff to analyze the department workflow and classify the analytical tasks required by domain experts in order to inform the design of the tool, and together we abstracted the steps and factors involved in the clinical imaging process. The visual representation emphasizes the time interval between the different steps and uses color-coding to denote the status of a process (on-time, acceptably late, late) in compliance with standard radiology turnaround times (TATs). RadStream is an ongoing research project. Its main focus is on monitoring performance with special attention to duration, delays, and compliance with standard TATs. RadStream is currently undergoing evaluation by radiology staff using hospital data and real scenarios to evaluate its effectiveness, and the initial feedback received is very promising. Working with domain experts, we seek to provide a tool that helps monitor and improve the radiology department's activities. And based on a few review sessions with staff radiologists, we sensed a general excitement about RadStream as a quality assurance tool. We have also collected some constructive feedback we can build upon for future releases.