Open Tools for Data Deidentification

For more information or to schedule this course, please contact the NNLM Training Office at nto@utah.edu. 

This webinar will provide a brief introduction to data science topics and terminologies. Topics will include AI in healthcare, explaining what natural language processing is, and discussing HIPAA privacy requirements and defining PII. This first part will be brief and focus on providing a foundational understanding. The second and bulk of the class will focus on the NLM Scrubber and CliniDeID as examples of NLP models that can be used for clinical deidentification. The class will cover how to promote these tools at the librarians’ institution.

Course URL: https://www.nnlm.gov/training/class-catalog/open-data-deidentification-tools

This course is an approved elective for the Level I Data Services Specialization.

Learning Objectives

1. Define artificial intelligence and natural language processing

2. Compare NLM Scrubber and other clinical deidentification tools

3. Implement open deidentification tools into library instruction and outreach programs

Agenda

• AI in healthcare
• What is natural language processing
• HIPAA privacy requirements and what is considering PII
• Define anonymization, deidentification, and its challenges
• What is NLM Scrubber and what does it do?
• What is CLiniDeID and what does it do?
• Ideas for promotion and outreach

MLA CE Credits: 1.0