Combining Visual Cleansing and Exploration for Clinical Data

Clinical data have their own peculiarities, as they evolve over time, may be incomplete, and are highly heterogeneous. These characteristics turn a thorough analysis into a challenging task, especially since domain experts are aware of the data flaws, which may impact their trust in the data. As we obtained anonymized clinical data from more than 3,500 patients with retinal diseases, we have to address these challenges. We define a workflow that integrates data cleansing and exploration in an iterative process, so that users are able to easily find anomalies and patterns in the data at any point in their analysis. We implement our workflow in a user-centered visual analytics tool with dedicated visualization and interaction techniques. In collaboration with experts, we apply our tool to examine the interdependency between patients' visual acuity developments and treatment patterns. We find, that real-life data often have unforeseen incidents which can strongly influence the overall visual acuity development. This differs to study results, which are usually conducted under restrictive conditions and have shown visual acuity improvement with on-schedule treatment.