Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Uploaded on Nov 30, 2018
Authors: Behrooz Omidvar-Tehrani, Cicero A. L. Pahins, Sihem Amer-Yahia, Jean-Christian Borel, Valérie Siroux, Jean-Louis Pépin and João L. D. Comba.
We demonstrate COVIZ, an interactive system to visualize and explore patient cohorts. COVIZ seamlessly integrates cohort formation, exploration and visualization, making it a single destination to form and explore cohorts. COVIZ is easy to use by medical experts and offers many features:
(1) It provides the ability to isolate demographics (e.g., their age group and location), health markers (e.g., their body mass index), and treatments (e.g., Ventilation for respiratory problems), and hence facilitates cohort formation;
(2) It summarizes the evolution of treatments of a cohort into health trajectories, and lets medical experts explore those trajectories;
(3) It guides them in exploring different facets of a cohort and generating hypotheses for future analysis;
(4) Finally, it provides cohort comparison that is applied to multiple cohorts to compare their statistics and health trajectories.
COVIZ relies on QDS, a novel data structure that encodes and indexes various data distributions to enable their efficient retrieval. Additionally, COVIZ visualizes air quality data in the regions where patients live to provide explanations. We demonstrate two key scenarios. In the time-series scenario, COVIZ shows the temporal correlation between markers and pollutants in the region of a given cohort. In the Case Cross-Over scenario, COVIZ enables the comparison of different periods for each patient and helps unveil the impact of treatments, markers and pollution on that patient's health.