Open Tools for Data De-identification

Class Experience Level
Beginner, Intermediate

This class is no longer accepting registrations

Data de-identification often poses a challenge to researchers. With more funders supporting or requiring data sharing, data de-identification is a crucial step in the data management lifecycle. Explore openly available tools and technologies to help with data de-identification, including how machine learning and natural language processing apply to data de-identification.

Learn about the NLM Scrubber and other open NLP tools that can be used for clinical text de-identification. This session includes a demonstration of how to run NLM Scrubber and shows the types of data it can find and redact. Finally, the presenters will share ways to promote data privacy and data de-identification tools at your institution.

By registering for this class, you are agreeing to the NNLM Code of Conduct

This presentation addresses data and health information resources, as well as the NLM initiative of building a data-ready workforce by including information about de-identifying data and the NLM Scrubber resource.

Objectives:

1. Define artificial intelligence and natural language processing.

2. Compare NLM Scrubber and other clinical de-identification tools.

3. Implement open de-identification tools into library instruction and outreach programs.

Class Recording

Class Details

Date(s): November 7, 2024
Time: 3:00 PM - 4:00 PM EST
Platform: Zoom
CE Credits: 1.00
CE Categories: DSS Level 1
Class Experience Level: Beginner, Intermediate
This is a National NNLM class.
Learn more about this class and find other upcoming instances:

Class Contacts

Technical Assistance: Rebecca Brown

Can't join us live?

Register anyway and you'll receive the recording after the event.