Dementia Patient Segmentation Using EMR Data Visualization: A Design Study

Abstract

(1) BACKGROUND: The Electronic Medical Record system, which is a digital medical record management architecture, is critical for reliable medical research. It facilitates the investigation of disease patterns and efficient treatment via collaboration with data scientists. (2) METHODS: In this study, we present multidimensional visual tools for the analysis of multidimensional datasets via a combination of 3-dimensional radial coordinate visualization (3D RadVis) and many-objective optimization (e.g., Parallel Coordinates). Also, we propose a user-driven research design to facilitate visualization. We followed a design process to (1) understand the demands of domain experts, (2) define the problems based on relevant works, (3) design visualization, (4) implement visualization, and (5) enable qualitative evaluation by domain experts. (3) RESULTS: This study provides clinical insight into dementia based on EMR data via visual analysis. Results of a case study based on questionnaires surveying daily living activities indicated that daily behaviors influenced the progression of dementia. (4) CONCLUSIONS: This study provides a visual analytical tool to support cluster segmentation. Using this tool, we segmented dementia patients into clusters and interpreted the behavioral patterns of each group. This study contributes to biomedical data interpretation based on a visual approach.