TITLE: Advanced Visual Analytics of Safety Data from Different Data Sources – Approaches and Available Tools
Dr. Melvin Munsaka , AbbVie
Dr. Kefei Zhou, Theravance Biopharma,
Dr. K.P. Singh, GSK



Safety data from various sources present many challenges with regard to curation, analysis, interpretation, and reporting. Safety outcomes have high variability in measurements and are multidimensional and interrelated in nature. Traditionally, safety data in drug research have primarily come from clinical trials using structured data sources. Newer sources of safety data within and outside clinical trials, including spontaneous reporting systems, real world, and social medial data sources have heighted the need to identify new approaches to analyze and present these data in some insightful way. The availability of high speed computing and influx of electronic medical and healthcare records (EMR/EHR) and digital sensors in premarketing and postmarketing settings have led to new sources of safety data in the direction of big data in terms of volume, veracity, velocity, and variety. For example, one such source of safety data that is attracting much interest is that of unstructured data in the form of free-text or notes which present unique challenges in programming and analysis. These data include doctors’ notes or can come from other sources such as social media or notes in electronic medical or healthcare records. The various sources of safety data coupled with readily available high speed computing resources has opened up new frontiers and opportunities for the assessment of drug safety and requires somewhat non-traditional programming and visualization approaches. Visual analytics present a useful alternative to tabular outputs for exploring safety data and present a great opportunity to enhance and facilitate evaluation of drug safety and help convey multiple pieces of information concisely and more effectively than tables. Graphical depictions of safety data also play a big role in facilitating communication of safety results with regulators, investigators, DMC, and other stakeholders. Visual analytics facilitates blending data visualization, statistical and data mining techniques to create visualization modalities that help users make sense out of safety data with some emphasis on how to complement computation and visualization to perform effective analysis.

This tutorial will present various advanced visual analytics approaches of safety data from a variety of data sources. The tutorial will also include a discussion of various enhancements of these visual forms to get maximum gain from using visual analytics taking into account some considerations that must be borne in mind for effective and informative visualization. A key consideration will be the use of advanced visual analytics to synthesize safety information and derive insight from massive, dynamic, potentially ambiguous and conflicting data, detect the unexpected, and to provide timely, defensible, and understandable assessments and to communicate assessment effectively to aid in safety decision making. Examples and code will be show-cased using different state-of the art software.

The tutorial will be broken down into the following subtopics:

  1. General considerations in information visualization, visual analytics and statistical and graphing principles underlying the production and interpretation of the graphical displays
  2. Visual analytics of safety from clinical trials data sources
  3. Visual analytics of safety from spontaneous reporting systems data sources
  4. Visual analytics of safety from EHR/EMR data sources
  5. Visual analytics of safety from internet and social medial sources
  6. Demonstration and illustrative examples of the use of a variety of state of the art tools and visual for visual analytics for safety data along with code


This entry was posted in . Bookmark the permalink.

Leave a Reply

Your email address will not be published. Required fields are marked *