Information Visualization Platform for Postmarket Surveillance Decision Support

Area of Science:

• Pharmacovigilance and Drug Safety
• Health Informatics
• Data Visualization

Background:

• The US Food and Drug Administration (FDA) receives over 2 million postmarket reports annually.
• Safety Evaluators (SEs) face challenges integrating and analyzing vast amounts of postmarket data alongside external information.
• Increasing data volume necessitates more efficient solutions for drug safety surveillance and signal detection.

Purpose of the Study:

• To develop an interactive decision support application for drug safety surveillance.
• To integrate and visualize information from postmarket reports, product labels, and biomedical literature.
• To enhance the efficiency of identifying potential safety signals.

Main Methods:

• Conducted requirements gathering with seven FDA SEs to design the Information Visualization Platform (InfoViP).
• Developed InfoViP as a web application using infographic design principles, integrating data from FDA Adverse Event Reporting System, DailyMed, and PubMed.
• Utilized a Python and JavaScript framework with natural language processing for free-text information analysis and time plot generation.

Main Results:

• The InfoViP prototype was developed based on SEs' workflows and requirements, focusing on automating time-consuming tasks.
• SEs provided positive feedback on the prototype's functionalities, particularly the visualization of external information and time plot construction.
• Suggestions from SEs were incorporated into the final version of the InfoViP system.

Conclusions:

• The InfoViP system provides context-driven interactive visualizations and informatics tools.
• It assists FDA SEs in synthesizing data from multiple sources for comprehensive case series analyses.
• The platform aims to improve the efficiency and effectiveness of postmarket drug safety surveillance.