Visual Analytics in Delirium Management

Background: Delirium is a patient safety issue that often occurs within the population of elderly people. As delirium may be characterized by fluctuating progress, the aim of this work is to find methods to visualize the occurrence of delirium over time in different patient stays in gerontopsychatric settings. Methods: We analyzed current data mining visualization techniques for clinical research using a delirium data set collected in a gerontopsychatric setting. Results: We identified heatmaps and dendrograms resulting from hierarchical clustering as a suitable visualization method. Conclusion: Heat maps with hierarchical clustering are a suitable data mining tool or visualization technique to study delirium cases in the time course of patient stays.