Support for Fast Comprehension of ICU Data: Visualization using Metaphor Graphics

Summary

Objectives: The time-oriented analysis of electronic patient records on (neonatal) intensive care units is a tedious and time-consuming task. Graphic data visualization should make it easier for physicians to assess the overall situation of a patient and to recognize essential changes over time.

Methods: Metaphor graphics are used to sketch the most relevant parameters for characterizing a patient’s situation. By repetition of the graphic object in 24 frames the situation of the ICU patient is presented in one display, usually summarizing the last 24 h.

Results: VIE-VISU is a data visualization system which uses multiples to present the change in the patient’s status over time in graphic form. Each multiple is a highly structured metaphor graphic object. Each object visualizes important ICU parameters from circulation, ventilation, and fluid balance.

Conclusion: The design using multiples promotes a focus on stability and change. A stable patient is recognizable at first sight, continuous improvement or worsening condition are easy to analyze, drastic changes in the patient’s situation get the viewers attention immediately.

Keywords

Computer Graphics - Data Display - Intensive Care

• References

• 1 Tufte ER. Visual Explanations. Cheshire CT: Graphics Press; 1997
• 2 Tufte ER. The Visual Display of Quantitative Information. Cheshire CT: Graphics Press; 1983
• 3 Tufte ER. Envisioning Information. Cheshire CT: Graphics Press; 1990
• 4 Wainer H. Visual Revelations: Graphic Tales of Fate and Deception from Napoleon Bonaparte to Ross Perot. New York: Copernicus/Springer; 1997
• 5 Cole WG, Stewart JG. Metaphor graphics to support integrated decision making with respiratory data. Int J Clin Monit Comput 1993; 10: 91-100.
• 6 Cole WG, Stewart JG. Human performance evaluation of a metaphor graphic display for respiratory data. Methods Inf Med 1994; 33: 390-6.
• 7 Horn W, Popow C, Unterasinger L. Metaphor graphics to visualize ICU data over time. In: Bellazzi R, Zupan B. eds. ECAI-98 Workshop on Intelligent Data Analysis in Medicine and Pharmacology (IDAMAP-98), Brighton, UK ECAI-98 Workshop on Intelligent Data Analysis in Medicine and Pharmacology (IDAMAP-98) Brighton, UK: 1998: 76.
• 8 Green CA, Logie RH, Gilhooly KJ, Ross DG, Ronald A. Aberdeen polygons: computer displays of physiological profiles for intensive care. Ergonomics 1996; 39: 412-28.
• 9 Horn W, Miksch S, Egghart G, Popow C, Paky F. Effective data validation of high-frequency data: time-point-, time-interval-, and trend-based methods. Comp Biol Med 1997; 27: 389-409.
• 10 Shahar Y. A framework for knowledge-based temporal abstraction. Artif Intell 1997; 90: 79-133.
• 11 Combi C, Chittaro L. Abstraction on clinical data sequences: an object-oriented data model and a query language based on the event calculus. Artif Intell Med 1999; 17: 271-301.
• 12 Shahar Y, Cheng C. Model-based visualization of temporal abstractions. Fifth International Workshop on Temporal Representation and Reasoning (TIME’98) Sanibel Island, Florida: 1998: 11-20.
• 13 Combi C, Portoni L, Pinciroli F. Visualizing temporal clinical data on the WWW. In: Artificial Intelligence in Medicine. Horn W. et al., eds. Berlin: Springer; 1999: 301-10.