Skip to content
All videos
newsDatabricks·July 19, 2022

Lessons Learned from Deidentifying 700 Million Patient Notes

Summary

Providence and Tegria deidentify over 700 million patient notes by using Spark NLP for Healthcare on Databricks to tag and obfuscate protected health information. The process requires data sampling, human annotation, and equity analysis to evaluate and improve model performance and privacy protection.

Summary generated by brickster.ai from the video transcript.

More from Databricks