Aligning temporal data by sentinel events: discovering patterns in electronic health records

Electronic Health Records (EHRs) and other temporal databases contain hidden patterns that reveal important cause-and-effect phenomena. Finding these patterns is a challenge when using traditional query languages and tabular displays. We present an interactive visual tool that complements query formulation by providing operations to align, rank and filter the results, and to visualize estimates of the intervals of validity of the data. Display of patient histories aligned on sentinel events (such as a first heart attack) enables users to spot precursor, co-occurring, and aftereffect events. A controlled study demonstrates the benefits of providing alignment (with a 61% speed improvement for complex tasks). A qualitative study and interviews with medical professionals demonstrates that the interface can be learned quickly and seems to address their needs.

[1]  E. Tufte,et al.  Graphical summary of patient status , 1994, The Lancet.

[2]  Roland Pressat,et al.  L'analyse démographique : méthodes, résultats applications. Présentation d'une publication de l'I.N.E.D. aux P.U.F. , 1961 .

[3]  Yuval Shahar,et al.  Intelligent visualization and exploration of time-oriented clinical data , 1999, Proceedings of the 32nd Annual Hawaii International Conference on Systems Sciences. 1999. HICSS-32. Abstracts and CD-ROM of Full Papers.

[4]  Jessica Lin,et al.  Visually mining and monitoring massive time series , 2004, KDD.

[5]  W. Lexis,et al.  Einleitung in die Theorie der Bevölkerungsstatistik , 1875 .

[6]  Wolfgang Jank,et al.  Representing Unevenly-Spaced Time Series Data for Visualization and Interactive Exploration , 2005, INTERACT.

[7]  Eamonn J. Keogh,et al.  VizTree: a Tool for Visually Mining and Monitoring Massive Time Series Databases , 2004, VLDB.

[8]  Benjamin B. Bederson,et al.  Toolkit design for interactive structured graphics , 2004, IEEE Transactions on Software Engineering.

[9]  Hsinchun Chen,et al.  Evaluating event visualization: a usability study of COPLINK spatio-temporal visualizer , 2005, Int. J. Hum. Comput. Stud..

[10]  John V. Carlis,et al.  Interactive visualization of serial periodic data , 1998, UIST '98.

[11]  Andrew R. Post,et al.  Model Formulation: PROTEMPA: A Method for Specifying and Identifying Temporal Sequences in Retrospective Data for Patient Selection , 2007, J. Am. Medical Informatics Assoc..

[12]  Ben Shneiderman,et al.  LifeLines: visualizing personal histories , 1996, CHI.

[13]  Masahito Hirakawa,et al.  Interactive visualization of spatiotemporal patterns using spirals on a geographical map , 1999, Proceedings 1999 IEEE Symposium on Visual Languages.

[14]  Ben Shneiderman,et al.  Dynamic Query Tools for Time Series Data Sets: Timebox Widgets for Interactive Exploration , 2004, Inf. Vis..

[15]  Ben Shneiderman,et al.  LifeLines: using visualization to enhance navigation and analysis of patient records , 1998, AMIA.

[16]  Silvia Miksch,et al.  Connecting time-oriented data and information to a coherent interactive visualization , 2004, CHI.

[17]  Morgan Dixon,et al.  ExperiScope: an analysis tool for interaction data , 2007, CHI.

[18]  Marc Alexa,et al.  Visualizing time-series on spirals , 2001, IEEE Symposium on Information Visualization, 2001. INFOVIS 2001..

[19]  Ben Shneiderman,et al.  Hawkeye: an interactive visual analytics tool for genome assemblies , 2007, Genome Biology.

[20]  Ben Shneiderman,et al.  A Visual Interface for Multivariate Temporal Data: Finding Patterns of Events across Multiple Histories , 2006, 2006 IEEE Symposium On Visual Analytics Science And Technology.

[21]  Isaac S. Kohane,et al.  Architecture of the Open-source Clinical Research Chart from Informatics for Integrating Biology and the Bedside , 2007, AMIA.

[22]  Tamara Munzner,et al.  Session Viewer: Visual Exploratory Analysis of Web Session Logs , 2007, 2007 IEEE Symposium on Visual Analytics Science and Technology.