# kamaleswaran2016physio

# PhysioEx: Visual Analysis of Physiological Event Streams


Kamaleswaran et al. introduce a novel visualization technique called Temporal Intensity Map (TIM), combined with several coordinated views to form a dashboard system called PhysioEx [1]. The TIM shows data values over time to reveal the hidden patterns in the data collected by the neonatal intensive care unit.

The concept is proven to be effective in analyzing neonatal data and predicting physiological behaviors of newborns by 4 domain experts .


Figure 1 shows an overview of PhysioEx, with three TIMs showing the duration, frequency, and intensity of physiologic data over time on the left. TIM is in fact a heatmap with the y-axis representing the critical distance interval determined by a density estimation function.

On the top right in Figure 1, the authors introduce a Sequence Graph, with the x-axis represents the hours of the day and the y-axis represents is mapped to date. Below the Sequence Graph is a Linear Graph conveying the data value versus the temporal dimension. In both graphs, each ellipse's radius encodes the data value and the color represents the event being observed.

On the bottom right in Figure 1 is a Stream Graph, revealing the frequency of continuous events over time, the data is summed to frequency per hour.

The raw data is displayed in the middle, it is activated when users perform a selection in the Linear Graph, providing access to the low-level sensor data.

Related Work

The authors develop PhysioEx after reviewing prior works on temporal big data visualization techniques introduced by Gotz, Zhou and Aggarwal [2], visualizing progressive analytics by Fischer, Mansmann and Keim [3], Cloudlines[4], hierarchical clustering technique[5] and GSCope[6].

Data Characteristics

  • Data source: The Hospital for Sick Children, Canada
  • Size: 47 patients
  • Spatial dimensionality: 2D
  • Temporal dimensionality: static
  • Type: multivariate
  • Libraries used: web-based, D3.js

Visualization Techniques

  • Glyph
  • Bubble chart
  • Heatmap
  • Stream chart

Papers Cited


Years Spanned


Application Domain

  • Electronic Health Record Visualization
  • Temporal Event Sequence
  • Medical focus - Neonatology - Neonatal Intensive Care


  1. Kamaleswaran, R., Collins, C., James, A., & McGregor, C. (2016). PhysioEx: Visual Analysis of Physiological Event Streams. Computer Graphics Forum, 35(3), 331–340. https://doi.org/10.1111/cgf.12909 β†©οΈŽ

  2. Gotz, D., Zhou, M. X., & Aggarwal, V. (2006). Interactive visual synthesis of analytic knowledge. IEEE Symposium on Visual Analytics Science and Technology 2006, VAST 2006 - Proceedings. https://doi.org/10.1109/VAST.2006.261430 β†©οΈŽ

  3. Fischer, F., Mansmann, F., & Keim, D. A. (2012). Real-time visual analytics for event data streams. https://doi.org/10.1145/2245276.2245432 β†©οΈŽ

  4. KrstajiΔ‡, M., Bertini, E., & Keim, D. A. (2011). Cloudlines: Compact display of event episodes in multiple time-series. IEEE Transactions on Visualization and Computer Graphics. https://doi.org/10.1109/TVCG.2011.179 β†©οΈŽ

  5. Elmqvist, N., & Fekete, J. D. (2010). Hierarchical aggregation for information visualization: Overview, techniques, and design guidelines. IEEE Transactions on Visualization and Computer Graphics. https://doi.org/10.1109/TVCG.2009.84 β†©οΈŽ

  6. Toyoda, T., Mochizuki, Y., & Konagaya, A. (2003). GSCope: A clipped fisheye viewer effective for highly complicated biomolecular network graphs. Bioinformatics. https://doi.org/10.1093/bioinformatics/btg001 β†©οΈŽ

πŸ”„ Last Updated: 7/8/2020, 9:48:18 PM