Visualizing Aggregations of Patient Cohorts
Electronic Health Records are being collected by leading health organizations. This project aims to visualize patient records by focusing on similarities within clusters of records. The following important questions arise: 1) How to compute intermediate values summarizing groups of multiple records? 2) How to cluster the records into groups and what similarity measure to use? 3) How to visualize intermediate results? Therefore, we developed MedCommix, a visualization tool for efficient exploration of similarities in patient health records, to approach these problems.
Krist Wongsuphasawat, Cody Dunne and Andreea Olea
Department of Computer Science, University of Maryland