Skip to main content

Mini-Sentinel: Automated Approaches to Anaphylaxis Case Classification Using Unstructured Data

Basic Details
Date Posted
Status
Complete
Health Outcome(s)
anaphylaxis
Description

The objective of this workgroup was to evaluate whether features extracted from unstructured narrative data using natural language processing (NLP) could be used to classify anaphylaxis cases. Using previously developed methods, the workgroup extracted features from unstructured narrative data using NLP and applied rule- and similarity-based algorithms to identify anaphylaxis among 62 potential cases previously classified by human experts as anaphylaxis, not anaphylaxis, and unknown. 

Information
Time Period
January 2009 - December 2010
HOI Study Type
Novel Approaches to More Efficient Outcome Validation
Data Source(s)
Mini-Sentinel Distributed Database (MSDD)
Related Links
Related Link(s)
Evaluating Automated Approaches to Anaphylaxis Case Classification Using Unstructured Data from the FDA Sentinel System
Validation of Anaphylaxis Using Machine Learning
Workgroup Leader(s)

Robert Ball, MD, MPH, ScM; Office of Surveillance and Epidemiology, Center for Drug Evaluation and Research, FDA, Silver Spring, MD

Workgroup Member(s)

Sengwee Toh, ScD; Jamie Nolan, BA; Department of Population Medicine, Harvard Medical School and Harvard Pilgrim Health Care Institute, Boston, MA

Kevin Haynes, PharmD, MSCE; Translational Research for Affordability and Quality, HealthCore, Inc., Wilmington, DE

Richard Forshee, PhD; Taxiarchis Botsis, PhD; Office of Biostatistics and Epidemiology, Center for Biologics Evaluation and Research, FDA, Silver Spring, MD