Several recent projects have reached a level of maturity where we are able to release open-source software via GitHub. While a number of manuscripts for these projects remain under peer review in advance of eventual publication, we’ve released two open-source repositories corresponding to three distinct research projects.
Cadence
First, we’ve released an early version of our Cadence platform for event sequence analysis. This includes new capabilities designed to (1) combat selection bias during exploratory data analysis, and (2) support high-dimensional event visualization via dynamic hierarchical aggregation.
I’m excited to announced that I’ve been named a 2019-2020 University Scholar by RTI International. Starting in September, I’ll be spending time at RTI’s headquarters to work with the RTI Center of Data Science on collaborative research projects. Our joint goals are to advance the state of the art in data science methods, to develop new data science tools based on those advances, and to apply those tools to impactful real-world problems.
I’m excited to report that the long-running Task Force on Evaluation, organized by AMIA’s VIS Working Group, has published its findings in a JAMIA article released earlier this year. The task force, co-chaired by myself and Danny Wu, was one of the very first initiatives launched by the VIS Working Group and provides a valuable resource to health informatics researchers and developers who are looking to evaluate the use of visualization or visual analytics technologies within the healthcare domain.
Our research team has a new article out in Information Visualization related to our work on contextual visualization. The abstract of the paper is as follows:
Data visualizations typically show a representation of a data set with little to no focus on the repeatability or generalizability of the displayed trends and patterns. However, insights gleaned from these visualizations are often used as the basis for decisions about future events. Visualizations of retrospective data therefore often serve as “visual predictive models.
A new article from our group has been published in IEEE Computer Graphics and Applications (CG&A) focused on the concept of contextual visualization. The article defines the term contextual visualization, motivates the importance of contextual visualization as a research topic, and anchors the challenges in this area within a body of previous related research. This work was made possible in part by funding from the National Science Foundation (NSF) under Grant No.
The AMIA Annual Symposium is one the premier meetings in the field of biomedical and health informatics. This 2018 AMIA Annual Symposium was held in San Francisco from November 3-7, and VACLab research was well represented.
First, Wanchen Zhao presented her paper on Visual Query interfaces for cohort studies during the 2018 Visual Analytics in Healthcare Workshop.
Wanchen Zhao, David Borland, Arlene E. Chung, David Gotz. Visual Cohort Queries for High-Dimensional Data: A Design Study.
The BioVis Interest Group has organized events at IEEE VIS for several years, exploring various aspects of visualization in biology. BioVis provides a forum for researchers from a range of fields including visualization, bioinformatics, and biology communities to meet, discuss new visualization developments within the biological domain, and identify new challenges. This year, the BioVis interest Group organized the BioVis Challenges Workshop which was held in Berlin, Germany on October 22, 2018.
IEEE VIS is the premier conference for Visualization and Visual Analytics research. The 2018 IEEE VIS Conference will take place in Berlin, Germany in October, and VACLab research will be well represented.
First, David Gotz is a co-author on a VAST paper titled “Visual Progression Analysis of Event Sequence Data” which describes the latest work to come from an ongoing collaboration with Nan Can at Tongji University and several other collaborators: Shunan Guo, Zhuochen Jin, Fan Du, and Hongyuan Zha.
I’m excited to share a new article that has just been published in the Journal for Electronic Health Data and Methods (eGEMs) that highlights a critical issue that is impeding improvements in EHR usability. The article—written with co-authors Saif Khairat, Cam Coleman and Samantha Russomagno—reports the results from a survey we conducted of 126 professionals in the health informatics community regarding (1) access to EHRs, and (2) the ability to publish usability-focused findings including screenshots of existing interfaces.
I’m excited to share that our recently accepted ACM CHI 2018 paper has been honored with an Honorable Mention Award, a highly selective designation given to the very best accepted CHI papers of the year. The paper focuses on a visual analytics approach to heart arrhythmia detection within very long ECG data streams. The system combines interactive data visualization with a deep learning model for heartbeat classification to help clinicians quickly and efficiently identify clinically important heartbeat signals.