You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 10 Next »




Introduction

For a quick introduction to PSL, see presentations by Kohane and McMurry.

For a complete technical description of PSL, see papers by McMurry and Drake.



Software Overview


PSL extracts, transforms, and loads Free Text and Coded Pathology Data into a de-identified format which can be searched across multiple hospitals.
PSL requires the following open.med modules:

  • Natural Language Processing of Free Text (SCRUBBER)
  • Distributed Database Search  (SPIN)

With the specimen data is loaded, an investigator may SEARCH THE PATHOLOGY ARCHIVES to find and request human tissue samples.


Architecture Diagram

Below is a summary "picture" that show 4 hospitals getting "loaded up" with specimen data and then searched with increasing level of access as necessary.

IRB approval is required for only the limited subset of patient specimens located.


  • No labels