Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

The HMS Scrubber builds on years of community efforts progress in de-identification and NLP. 
In 2006, Beckwith developed and validated a rule based system to de-identify pathology reports. 
This widely accessed de-id program well in the pathology environment and was approved by the four IRBs at Harvard teaching hospitals. 

Porting this software to other hospital settings and note types proved difficult and required fine-tuning the regular expressions for each installation. 
This lead to the creation of the "3.X" Scrubber, combining autocoding and de-identification tasks to maximize research utility and minimize site specific customization.

This new approach using machine learning analyzes similaraties and differences betwen physician notes, medical dictionaries, and medical journal publications.