# gotz2014decisionflow

# DecisionFlow: Visual analytics for high-dimensional temporal event sequence data

Concept

DecisionFlow is a visual analysis technique designed to support the analysis of high-dimensional temporal event sequence data [1]. Traditionally, the high-dimensionality of datasets requires users to pre-filter events or collapse multiple low-level events into high-level categories, and thus unable to present a full-resolution image. DecisionFlow aims to address the issue by combining an incremental milestone-based data representation with on-demand statistical analysis and an exploratory flow-based visualization technique.

Implementation

Figure 1 shows the overview of DecisionFlow, section A allows users to define the query conditions, section B, C and D show the returned results. Each ellipse in section C depicts an event in the dataset, ordered by the temporal dimension.

A milestone can be set by selecting an event in section C, which then collapses all the directly connected events into a milestone as shown in Figure 1 E. Overlapping edges are highlighted with a black outline to illustrate the associations. Hovering over a milestone shows a tooltip with more detailed information.

Related Work

The authors review related works on visual analytics of temporal event sequence data. They conclude that traditional research focus on visualizing a single record such as LifeLines[2], Timelines[3], PlanningLines[4], Continuum[5], recent research shift the focus to the visualization of multiple records such as Visualizing Social Science Diary Data by Vrotsou, Ellegard, and Cooper[6], ActiviTree[7], Outflow[8] and LifeFlow[9].

Data Characteristics

  • Data source: an unnamed US-based care provider.
  • Size: visualized 514 to 2,899 cardiology patients with 113,189 to 1,074,435 events. However, the complete dataset contains 32,000 patients.
  • Spatial dimensionality: 2D
  • Temporal dimensionality: static
  • Type: multivariate
  • Libraries used: web-based, unknown, video demo: https://vimeo.com/103864820 (opens new window)

Visualization Techniques

  • Glyph
  • Sankey diagram (variant)

Papers Cited

34

Years Spanned

1994-2013

Application Domain

  • Electronic Health Record Visualization
  • Temporal Event Sequence
  • Medical focus: Cardiology - General

Reference

  1. Gotz, D., & Stavropoulos, H. (2014). DecisionFlow: Visual analytics for high-dimensional temporal event sequence data. IEEE Transactions on Visualization and Computer Graphics, 20(12), 1783–1792. https://doi.org/10.1109/TVCG.2014.2346682 ↩︎

  2. C. Plaisant, B. Milash, A. Rose, S. Widoff, and B. Shneiderman. LifeLines: visualizing personal histories. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pages 221–227, New York, NY, USA, 1996. ACM. ↩︎

  3. B. Harrison, R. Owen, and R. Baecker. Timelines: An interactive system for the collection and visualization of temporal data. In Grahpics Interface, 1994. ↩︎

  4. W. Aigner, S. Miksch, B. Thurnher, and S. Biffl. PlanningLines: novel glyphs for representing temporal uncertainties and their evaluation. In 2013 17th International Conference on Information Visualisation, volume 0, pages 457–463, Los Alamitos, CA, USA, 2005. IEEE Computer Society. ↩︎

  5. P. Andr, M. L. Wilson, A. Russell, D. A. Smith, A. Owens, and M. Schraefel. Continuum: Designing timelines for hierarchies, relationships and scale. In Proceedings of the 20th Annual ACM Symposium on User Interface Software and Technology, UIST ’07, page 101110, New York, NY, USA, 2007. ACM. ↩︎

  6. K. Vrotsou, K. Ellegard, and M. Cooper. Everyday life discoveries: Mining and visualizing activity patterns in social science diary data. In Information Visualization, 2007. IV ’07. 11th International Conference, pages 130–138, 2007. ↩︎

  7. K. Vrotsou, J. Johansson, and M. Cooper. ActiviTree: interactive visual exploration of sequences in event-based data using graph similarity. IEEE Transactions on Visualization and Computer Graphics, 15(6):945952, Nov. 2009. ↩︎

  8. K. Wongsuphasawat and D. Gotz. Outflow: Visualizing patient flow by symptoms and outcome. In IEEE VisWeek Workshop on Visual Analytics in Healthcare, Providence, Rhode Island, USA, 2011. ↩︎

  9. K. Wongsuphasawat, J. A. Guerra Gmez, C. Plaisant, T. D. Wang, M. Taieb-Maimon, and B. Shneiderman. LifeFlow: visualizing an overview of event sequences. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, CHI ’11, page 17471756, New York, NY, USA, 2011. ACM. ↩︎

🔄 Last Updated: 7/8/2020, 9:48:18 PM

← loorak2016timespan →