Information Visualization Platform for Postmarket Surveillance Decision Support

The US FDA receives more than 2 million postmarket reports each year. Safety Evaluators (SEs) review these reports, as well as external information, to identify potential safety signals. With the increasing number of reports and the size of external information, more efficient solutions for data integration and decision making are needed.

The aim of this study was to develop an interactive decision support application for drug safety surveillance that integrates and visualizes information from postmarket reports, product labels, and biomedical literature.

We conducted multiple meetings with a group of seven SEs at the FDA to collect the requirements for the Information Visualization Platform (InfoViP). Using infographic design principles, we implemented the InfoViP prototype version as a modern web application using the integrated information collected from the FDA Adverse Event Reporting System, the DailyMed repository, and PubMed. The same group of SEs evaluated the InfoViP prototype functionalities using a simple evaluation form and provided input for potential enhancements.

The SEs described their workflows and overall expectations around the automation of time-consuming tasks, including the access to the visualization of external information. We developed a set of wireframes, shared them with the SEs, and finalized the InfoViP design. The InfoViP prototype architecture relied on a javascript and a python-based framework, as well as an existing tool for the processing of free-text information in all sources. This natural language processing tool supported multiple functionalities, especially the construction of time plots for individual postmarket reports and groups of reports. Overall, we received positive comments from the SEs during the InfoViP prototype evaluation and addressed their suggestions in the final version.

The InfoViP system uses context-driven interactive visualizations and informatics tools to assist FDA SEs in synthesizing data from multiple sources for their case series analyses.