Varying Annotations in the Steps of the Visual Analysis
This work addresses the problem of integrating annotations in visual analytics for clinical data analysis, but it appears incremental as it focuses on domain-specific design without broad methodological innovation.
The paper tackled the challenge of designing suitable annotations for different steps in visual analysis by identifying step-specific annotations and outlining their properties for heterogeneous clinical data, and demonstrated its applicability in an ophthalmic domain tool with expert interviews showing usefulness for analyzing patients with different medications.
Annotations in Visual Analytics (VA) have become a common means to support the analysis by integrating additional information into the VA system. That additional information often depends on the current process step in the visual analysis. For example, the data preprocessing step has data structuring operations while the data exploration step focuses on user interaction and input. Describing suitable annotations to meet the goals of the different steps is challenging. To tackle this issue, we identify individual annotations for each step and outline their gathering and design properties for the visual analysis of heterogeneous clinical data. We integrate our annotation design into a visual analysis tool to show its applicability to data from the ophthalmic domain. In interviews and application sessions with experts we asses its usefulness for the analysis of patients with different medications.