●About ●History ●History of the Field ●Become a Member ●Jobs and Student Funding ●Our Lighter Side ●Contact Us ●News ●Events ●BBL Speaker Series ●HCIL Annual Symposium ●Event Archive ●Research ●Sparks of Innovation (Medium Posts) ●Awards (External) ●Awards (Internal) ●Books ●Software Products ●ARCHIVE ●People ●Faculty and Leadership ●Students ●Past Members and Alumni ●Academics ●Sponsorship ●Symposium Sponsorship ●Research Sponsorship ●Industry Visits ●Active Sponsors ●ARCHIVE ●Research Histories – Early Themes ●Research Projects ●Tech Reports and Publications ●YouTube Channel ●Historical Research Videos ●Events ●Presentations ●Class Projects ●Service Projects ●Collaborating Groups and People

EventFlow: Visual Analysis of Temporal Event Sequences and Advanced Strategies for Healthcare Discovery

Jump to: Features | Participants | Presentations | Videos | Download & Licensing | User Support | Publications | Press| Related Projects

Updates

●Had fun making a short demo video with French audio for talks in Québec (November 2017) ●We presented “Coping with Volume and Variety in Temporal Event Sequences: Strategies for Sharpening Analytic Focus” at the IEEE Vis Conference. Follow the link for slides and video. ●Summer 2016: Sana Graduated! Her project CoCo for Cohort Comparison, built on our experience with Eventflow. If you want to try Coco, ask Catherine for access. ●May 2016: we held a workshop on Temporal Event Sequence Analysis + EventFlow and Coco User Group Meeting, as part of the 2016 HCIL Annual Symposium in College Park. ●A summary of analysts’ strategies using EventFlow: Coping with Volume and Variety in Temporal Event Sequences: Strategies for Sharpening Analytic Focus. ●EventFlow is available for Licensing (see below). ●Oracle produced a nice video highlighting our work.: January 2013.

Summary

EventFlow is a novel tool for event analytics. It provides a way to: ● Visualize and review the data from individual records and their event sequences ● Search for temporal patterns of interest, using a powerful graphical interface ● Summarize all the event sequences, their timing and prevalence, and find anomalies ● Perform data transformations to reveal useful patterns that answer questions you have ● Select cohorts of interest for further studies Other keywords: temporal analysis, time series, visual data mining, temporal visualization,

EventFlow Applications

Eventflow has been used for medical research, log analysis, cybersecurity, sports analytics, learning analytics, incident management, workflow analysis, pharmacovigilance, epidemiology etc. The analysis of healthcare data has been our main focus in term of number of partners. Medical researchers and hospitals have applied EventFlow to analyze treatment patterns and outcomes in Electronic Health Records or claims reports, while network security analysts have studied cyberattack patters and sports analysts have found novel approaches to studying games, overall team performance, and seasonal patterns. Education researchers and universities have used EventFlow to look at class enrollment sequences and student records. Applications for web log, sensor data, business processes, and financial transactions are also emerging markets. If you are interested in how EventFlow is being used look at some of the case study reports in the Publications section, or take a look at the workshops from 2016; 2015; and 2014 which we ran in association with the Annual HCIL Symposium,

Project History

The HCIL’s ongoing work with temporal event records has produced powerful tools for analyzing and exploring patterns of point-based events: David Wang’s Lifelines2 introduced simple operators to manipulate and visualize colections of records. Krist Wongsuphasawat’s LifeFlow introduced a method for summarizing all patterns. Megan Monroe pushed the limits further with EventFlow, which now deals with interval events, for example, the 3-month interval during which patients took a medication. Interval-based events represent a fundamental increase in complexity at every level of the application. Megan also added a powerful graphical search and (along with other HCIL students) expanded the panoply of data manipulations tools available, leading to the development of strategies for dealing with data volume and diversity.

Participants

●Fan Du, PhD Candidate, Computer Science ●Catherine Plaisant, Research Scientist, UMIACS ●Ben Shneiderman, Professor, Computer Science Major past participants ●Sana Malik, PhD, Computer Science ●Megan Monroe, PhD, Computer Science ●Krist Wongsuphasawat PhD, Computer Science Other participants and collaborators ●David Wang, PhD Candidate, Computer Science ●John Alexis Gerra Gómez, PhD Candidate, Computer Science ●Matt Mauriello, PhD Candidate, Computer Science ●Hsueh-Chien Cheng, PhD Candidate, Computer Science ●Hanseung Lee, PhD Candidate, Computer Science ●Christopher Imbriano, MS Candidate, Computer Science ●Rongjian Lan, PhD Candidate, Computer Science ●Sigfried Gold ●Jeff Millstein We also appreciate the collaboration of clinical researchers and epidemiologists at the US Army Pharmacovigilance Center, University of Maryland School of Pharmacy, National Children Hospital, University of Florida, Washington Hospital Center, and many others.

Videos

INTRODUCTION VIDEO (start here) Using sample data showing the trajectory of PATIENTS in an hospital (e.g. showing patients who “bounced back” to the emergency room) ↓	Another introduction, showing how an analyst was able to clean her data interactively with EventFlow and reveal 27 common deviations from the ATLS protocol (which is supposed to be used to evaluate trauma victims).

Another short example with DRUG prescription data ↓	An older short example focused on manipulating and searching INTERVAL DATA ↓

Other example with BASKETBALL data: Basketball Play-by-play Analysis ↓	and the analysis of the Offensive Rebounding of the Indiana Pacers basketball team ↓

Licensing

Since April 2018 EventFlow is available for licensing from the UMd STORE ●Not sure? Special cases? Contact plaisant@cs.umd.edu and describe your affiliation and project You can also request a software review agreement or more information about special licensing agreements that better suit your needs (e.g. access to source code) by contacting the Office of Technology Commercialization (OTC) Email: otc@umd.edu

User Manual

●Please see the EventFlow Manual, which covers all the major features of EventFLow and includes a large number of detailed videos. ●Quick look at the simple EventFlow data format: see EventFlow data format section in the user manual. ●To generate datasets for testing, use the Dataset Generator ●Suggestions for dealing with large datasets: Coping with Volume and Variety in Temporal Event Sequences: Strategies for Sharpening Analytic Focus. ●You can also review the workshop pages (2016; 2015; and 2014) to see how users shared their experiences using EventFlow, and ideas for potential improvements. ●Questions: eventflow.umd@gmail.com

Publications

Full Papers

[BEST REFERENCE] Simplification of temporal event sequences: Megan Monroe, Rongjian Lan, Catherine Plaisant, Ben Shneiderman Temporal Event Sequence Simplification TVCG: IEEE Transactions on Visualization and Computer Graphic, 2013. The EventFlow graphical query interface: Megan Monroe, Rongjian Lan, Juan Morales del Olmo, Catherine Plaisant, Ben Shneiderman, Jeff Millstein The Challenges of Specifying Intervals and Absences in Temporal Queries: A Graphical Language Approach. CHI: In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2013. Strategies used by analysts: Fan Du, Ben Shneiderman, Catherine Plaisant, Sana Malik, Adam Perer Coping with Volume and Variety in Temporal Event Sequences: Strategies for Sharpening Analytic Focus
IEEE Transactions on Visualization and Computer Graphic, 2016 .
Technical paper on temporal query processing algorithms Megan Monroe, Amol Deshpande An Integer Programming Approach to Temporal Pattern Matching Queries SSTDM: In Proceedings ofInternational Workshop on Spatial and Spatiotemporal Data Mining, 2013.

Examples of Use

Patterns of activities of older adults
Chung, J., Ozkaynak, M. and Demiris, G. Examining daily activity routines of older adults using workflow Journal of Biomedical Informatics, 71 (2017) pp.82-90. Innovation trajectory analysis C. Scott Dempwolf, Ben Shneiderman Event Analytics for Innovation Trajectories: Understanding Inputs and Outcomes for Entrepreneurial Success Technology and Innovation (2017) 397-413. http://dx.doi.org/10.21300/19.1.2017.397 Disease and treatment analysis (joint work with CDC) Karlyn Beer, Sarah Collier, Fan Du, Julia Gargano Giardiasis Diagnosis and Treatment Practices Among Commercially Insured Persons in the United States Clinical Infectious Diseases, 64, 9 (2017) 1244-1250. Hypothesis generation Eberechukwu Onukwugha, Margret Bjarnadottir, Shujia Zhou, David Czerwinski Visualizing Data for Hypothesis Generation Using Large-Volume Claims Data Value & Outcomes Spotlight, 3, 1, 2017. Motion capture data analysis Jürgen Bernard, Eduard Dobermann, Anna Vögele, Björn Krüger, Jörn Kohlhammer, Dieter Fellner Visual-Interactive Semi-Supervised Labeling of Human Motion Capture Data Electronic Imaging, Visualization and Data Analysis, pp 34-45(12), 2017. Prescriptions adherence analysis Bjarnadottir, M., Malik, S., Onukwugha, E., Gooden, T., Plaisant, C. Understanding Adherence and Prescription Patterns Using Large Scale Claims Data PharmacoEconomics, Volume 34, Issue 2, pp 169-179, 2016. Health service utilization among cancer patients (part of Book Chapter) Onukwugha, E., Plaisant, C., Shneiderman, B. Data Visualization Tools for Investigating Health Services Utilization Among Cancer Patients
Book chapter in Hesse, B., Ahern, D., and Beckjord, E. (Eds.) Oncology Informatics, Elsevier, 2016 (to appear). Workflow for pediatric asthma patients Mustafa Ozkaynak, Oliwier Dziadkowiec, Rakesh Mistry, Tiffany Callahan, Ze He, Sara Deakyne, Eric Tham Characterizing Workflow for Pediatric Asthma Patients in Emergency Departments Using Electronic Health RecordsJournal of Biomedical Informatics, Volume 57, pp 386-398, 2015. US Army asthma case study (detailed version, part of a Book Chapter) Catherine Plaisant, Megan Monroe, Tamra Meyer, Ben Shneiderman Interactive Visualization Book Chapter in Big Data and Health Analytics, Marconi, K. and Lehman, H. (Eds), CRC Press – Taylor and Francis, pp 243-262, 2014. Case study of our collaboration with the US Army Pharmacovigilance Center Megan Monroe, Tamra Meyer, Catherine Plaisant, Rongjian Lan, Krist Wongsuphasawat, Trinka Coster, Sigfried Gold, Jeff Millstein, Ben Shneiderman. A Pilot Study of Asthma Medications in the Military Health System. VAHC: In Proceedings of Workshop on Visual Analytics in HealthCare, 2013. Trauma resuscitation workflow Carter, E., Burd, R., Monroe, M., Plaisant, C., Shneiderman, B. Using EventFlow to Analyze Task Performance During Trauma Resuscitation In Proceedings of the Workshop on Interactive Systems in Healthcare (WISH), 2013.

Short Papers

Presented at the EventEvent workshop at VIS 2016 Ben Shneiderman The Event Quartet: How Visual Analytics Works for Temporal Data Catherine Plaisant, Ben Shneiderman The Diversity of Data and Tasks in Event Analytics (companion website with slides) Late-breaking work on temporal event sequence overview simplification
Matthew Louis Mauriello, Ben Shneiderman, Fan Du, Sana Malik, Catherine Plaisant Simplifying Overviews of Temporal Event Sequences (Best Paper Honorable Mention) Early work on temporal event sequence search and replace Rongjian Lan, Hanseung Lee, Megan Monroe, Allan Fong, Catherine Plaisant, Ben Shneiderman Temporal Search and Replace: An Interactive Tool for the Analysis of Temporal Event Sequences Early report on extending the Lifeflow overview visualization to handle interval data Megan Monroe, Krist Wongsuphasawat, Catherine Plaisant, Ben Shneiderman, Jeff Millstein and Sigfried Gold Exploring Point and Interval Event Patterns: Display Methods and Interactive Visual Query

Other publications written by our case study partners

E. Onukwugha, Y. Kwok, C. Yong, C. Mullins, B. Seal, A. Hussain Variation in the length of radiation therapy among men diagnosed with Incident Metastatic Prostate Cancer” ASTRO: Poster presented at the 2013 American Society for Radiation Oncology meeting. * See also related HCIL Workshops (2016; 2015; and 2014) , as they included presentations from EventFlow users.

General survey paper

Rind, A., Wang, T., Aigner, W., Miksch, S., Wongsuphasawat, K., Plaisant, C., Shneiderman, B. Interactive Information Visualization for Exploring and Querying Electronic Health Records: A Systematic Review Foundations and Trends in Human-Computer Interaction, Vol. 5, No. 3, 207-298, 2013.

Press

Hunter Whitney, It’s About Time, UX Magazine, September 2014.

Products and papers stimulated by this work

Our original research on LifeFlow and EventFlow stimulated new work by other labs, such as: ●OutFlow and CareFlow at IBM. ●Visualizing Uncertain Critical Paths in Schedule Management, by Robert Gove, Brandon Herzog (see VAST 2013 Industry posters).

Related projects and events

●EventAction: Visual Analytics for Temporal Event Sequence Recommendation. ●CoCo: A Visual Analytics Tool for Comparing Cohorts of Event Sequences. ●2015 HCIL Workshop on Visualization of Temporal Patterns in EHR data, in association with the Annual HCIL Symposium, May 28, 2015, College Park. ●Links of all HCIL Projects related to Temporal Visualization: LifeLines, LifeLines2, PatternFinder, LifeFlow, etc. ● (several years) Visual Analytics in Healthcare workshops at AMIA or IEEE Vis, with for example Ben Shneiderman’s keynote and 2 papers and demos in 2013. ●2014 IEEE VIS Workshop on Visualization of EHR data, Paris, France, November 9, 2014. ●2014 HCIL Workshop on Visualization of Temporal Patterns in EHR data:, in association with the Annual HCIL Symposium, May 29, 2014, College Park. ●2013 HCIL EHR Informatics Workshop ●2012 EventFlow User Group Meeting ●2012 HCIL EHR Informatics Workshop 2012 ●2011 HCIL EHR Informatics Workshop ●2008 HCIL Interactive Visual Exploration of Electronic Health Records ●2004 HCIL Personal Medical Devices Workshop: Increasing Patient Healthcare Participation ●1997 HCIL Visualizing Personal Histories Workshop

Presentations (list non updated)

The following slides provide an introduction to the motivation behind EventFlow, and a summary of its features. A full description can be found in the tech report.

Other Presentations ●Temporal Event Querying – Presented at CHI2013 ●Dataset Simplification – Presented at MedStar 2/13 ●Basketball Play-by-play Analysis – Presented at the 2013 HCIL Symposium

Human-Computer Interaction Lab (HCIL) 4130 Campus Drive, Hornbake Building, South Wing, Room 2105 College Park, MD 20742 hcil-info@umd.edu The lab is jointly supported by the College of Information Studies (INFO) and the University of Maryland Institute for Advanced Computer Studies (UMIACS). Copyright © 2024 · Human-Computer Interaction Lab · College of Information Studies · University of Maryland · Privacy Policy · Web Accessibility