Searching Categorical Histories with PatternFinder:
Query Support for Electronic Health Records

Jump to:
Participants
Publications
Sponsors

Project description

Pattern Finder is an integrated interface for visual query and result-set visualization for search and discovery of temporal patterns within multivariate and categorical data sets. We extend work on visual query languages for temporal data with a novel interface and address the presentation of the result sets. Temporal patterns are sequences of events with inter-event time spans. Pattern queries allow events, event sets, event attributes, and time spans to be specified so as to produce powerful queries that are difficult to express in other formalisms. Finding patterns of events over time is important in searching patient histories, web logs, news stories, or in tracking criminal activities.

Participants

Ben Shneiderman, PhD, Professor, Computer Science
Catherine Plaisant, PhD, Associate Research Scientist, HCIL
Patricia Abbott, PhD, RN, FAAN, FACMI, Post-doc fellow (visiting from Johns Hopkins School of Medicine)
Stanley Lam, Undergraduate Student, Computer Science
Early class project participants: Jerry Fails, Amy Karlson, Layla Shahamat, Hyunyoung Song, Nathaniel Ayewah, Gleneesha Johnson, John Brennan, Nima Negahban (Graduate Students, Computer Science)

Publications and reports

Fails, J., Karlson, A., Shahamat, L., Shneiderman, B.
A Visual Interface for Multivariate Temporal Data: Finding Patterns of Events over Time
in Proceedings of the IEEE Symposium on Visual Analytics Science and Technology (VAST 2006) 167-174
Short video demonstration (1Mb)