Enabling qualitative research data sharing using a natural language processing pipeline for deidentification: moving beyond HIPAA Safe Harbor identifiers.

Aditi GuptaAlbert M LaiJessica MozerskyXiaoteng MaHeidi WalshJames M DuBois

Published in: JAMIA open (2021)

The results of this study demonstrate that NLP methods can be used to identify both HSH identifiers and non-HSH identifiers. Automated tools to assist researchers with the deidentification of qualitative data will be increasingly important given the new National Institutes of Health (NIH) data-sharing mandate.

Keyphrases

electronic health record
health information
big data
healthcare
social media
public health
systematic review
machine learning
autism spectrum disorder
high throughput
risk assessment
data analysis
climate change