ABSTRACT
Current visualizations of electronic medical data in the Intensive Care Unit (ICU) consist of stacked univariate plots of variables over time and a tabular display of the current numeric values for the corresponding variables and occasionally an alarm limit. The value of information is dependent upon knowledge of historic values to determine a change in state. With the ability to acquire more historic information, providers need more sophisticated visualization tools to assist them in analyzing the data in a multivariate fashion over time. We present a multivariate time series visualization that is interactive and animated, and has proven to be as effective as current methods in the ICU for predicting an episode of acute hypotension in terms of accuracy, confidence, and efficiency with only 30-60 minutes of training.
- J. M. Chambers, W. S. Cleveland, B. Kliener, and P. A. Tukey. Graphical Methods for Data Analysis. Boston: Wadsworth International, Duxbury Press, 1983.Google Scholar
- Eclipsys. Clinical information solutions for critical care. http://www.eclipsys.com/hospitals-clinicalsolutions- critical-care.htm, September 2010.Google Scholar
- G. S. Halford, R. Baker, J. McCredden, and J. D. Bain. How many variables can humans process? Psycological Science, pages 70--76, 2005.Google ScholarCross Ref
- T. Heldt, B. Long, G. Verghese, P. Szolovits, and R. G. Mark. Integrating data, models, and reasoning in critical care. In Engineering in Medicine and Biology Society, pages 350--353, 2006.Google Scholar
- JHMCIS. EPR - electronic patient record. http://dcs.jhmi.edu/epr/index.cfm, September 2010.Google Scholar
- J. Lin, E. Keogh, and S. Lonardi. Visualizing and discovering non-trivial patterns in large time series databases. Information Visualization, 4: 61--82, 2005. Google ScholarDigital Library
- M.I.T. Laboratory of Computational Physiology. Physionet challenge. http://physionet.org/challenge/2009/, 2009.Google Scholar
- G. Moody and L. Lehman. Predicting acute hypotensive episodes: The 10th annual physionet/computers in cardiology challenge. Computers in Cardiology, 2009.Google Scholar
- M. Noirhomme-Fraiture. Visualization of large data sets: the zoom star solution. International Electronic Journal of Symbolic Data Analysis, 2002.Google Scholar
- P. Ordóñez, M. desJardins, C. Feltes, C. U. Lehmann, and J. Fackler. Visualizing multivariate time series data to detect specific medical conditions. In AMIA Annual Symposuim, pages 530--534, 2008.Google Scholar
- C. Plaisant, R. Mushlin, A. Snyder, J. Li, D. Heller, and B. Shneiderman. Lifelines: Using visualization to enhance navigation and analysis of patient records. In AMIA Annual Symposuim, pages 76--80, 1998.Google Scholar
- S. Powsner and E.R.Tufte. Graphical summary of patient status. Lancet, 344: 386--389, 1994.Google ScholarCross Ref
- Y. Shahar, D. Goren-Bar, D. Boaz, and G. Tahan. KNAVE-II: A distributed architecture for interactive visualization and intelligent exploration of time-oriented clinical data. In Proc. Artificial Intelligence in Medicine, pages 115--35, 2006.Google Scholar
- E. Tufte. Beautiful Evidence. Graphic Press, 2006. Google ScholarDigital Library
Index Terms
- An animated multivariate visualization for physiological and clinical data in the ICU
Recommendations
Multivariate Relational Visualization of Complex Clinical Datasets in a Critical Care Setting: A Data Visualization Interactive Prototype
IV '06: Proceedings of the conference on Information VisualizationOne mission of medical informatics is to provide physicians, nurses, and other health care providers with the technology and tools for interpreting large and diverse data sets, so that appropriate critical care decisions can be facilitated. Ideally, ...
Visualization Mosaics for Multivariate Visual Exploration
We present a new model for creating composite visualizations of multidimensional data sets using simple visual representations such as point charts, scatterplots and parallel coordinates as components. Each visual representation is contained in a tile, ...
Animated visualization of multiple intersecting hierarchies
The authors describe a new information structure composed of multiple intersecting hierarchies, which we call a Polyarchy. Visualizing polyarchies enables use of novel views for discovery of relationships which are very difficult using existing ...
Comments