Visualization of unstructured text sequences of nursing narratives

ABSTRACT

This paper presents a keyword-based information visualization technique for nursing record sequences. Visualizing the trend information rooted in unstructured and fragmented abstract text data is a largely unaddressed problem. In our technique, multiple hierarchical keyword based visualizations are used to explore unstructured text data from nursing records. First, each text data set is broken up into a list of keywords to enable the visualization of keyword occurrences over time and the relative distribution of keywords. A graphical user interface is provided to enable selection and classification of keywords. Users may select one or more data sets to compare, in addition to one or more groups of keywords to add to the visualization. Colors are used to distinguish quickly and easily between groups of keywords present in the visualization. At the second level of hierarchy, keywords for visualization are discovered through a predetermined automatic detection and scoring based mechanism. The aggregate frequency trend of keywords from all data sets is also provided in both hierarchies as a way to visualize overall trends and analyze various events in time.

REFERENCES

• 1: Lena Mamykina , Stuart Goose , David Hedqvist , David V. Beard, CareView: analyzing nursing narratives for temporal trends, CHI '04 extended abstracts on Human factors in computing systems, April 24-29, 2004, Vienna, Austria [doi>10.1145/985921.986010]
• 2: Catherine Plaisant , Brett Milash , Anne Rose , Seth Widoff , Ben Shneiderman, LifeLines: visualizing personal histories, Proceedings of the SIGCHI conference on Human factors in computing systems: common ground, p.221-ff., April 13-18, 1996, Vancouver, British Columbia, Canada [doi>10.1145/238386.238493]
• 3: C. Plaisant, et al., "LifeLines: Using Visualization to Enhance Navigation and Analysis of Patient Records," Proceedings of American Medical Informatics Association Conference, 1998.
• 4: Susan Havre , Elizabeth Hetzler , Paul Whitney , Lucy Nowell, ThemeRiver: Visualizing Thematic Changes in Large Document Collections, IEEE Transactions on Visualization and Computer Graphics, v.8 n.1, p.9-20, January 2002 [doi>10.1109/2945.981848 ]
• 5: P. Imrich, K. Mueller, D. Imre, A. Zelenyuk, and W. Zhu, "Interactive Poster: 3D ThemeRiver," IEEE Information Visualization Symposium '03, October 2003.
• 6: Ronen Feldman , Ido Dagan , Haym Hirsh, Mining Text Using Keyword Distributions, Journal of Intelligent Information Systems, v.10 n.3, p.281-300, June 1, 1998 [doi>10.1023/A:1008623632443 ]

INDEX TERMS

Primary Classification:
  J. Computer Applications
  J.3 LIFE AND MEDICAL SCIENCES

Additional Classification:
  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.5 Computational Geometry and Object Modeling
          Subjects: Geometric algorithms, languages, and systems

General Terms:
Human Factors

Keywords:
nursing data processing, text and document visualization