Skip to content

Commit

Permalink
Update DataFlow.md
Browse files Browse the repository at this point in the history
fixed table layout
  • Loading branch information
tznind authored Apr 10, 2020
1 parent 5e7d629 commit 6f98d46
Showing 1 changed file with 1 addition and 2 deletions.
3 changes: 1 addition & 2 deletions docs/DataFlow.md
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,5 @@ Key
| NLP Algorithms | Validated production ready algorithms run on identifiable free text data (e.g. Dose Reports, Structured Reports) and output results useful for cohort building into the relational database |
| Relational Database | Only tags useful for cohort building that are easily (and reliably) anonymised (e.g. 5% of all tags) |
| Cohort building | Only tags useful for cohort building and only study/series level (e.g. 4% of all tags) |
| Researcher Zone (from CTP) | DICOM images with tags anonymised by CTP. These include technical tags (some of which are
not loaded to Relational / used in cohort building), date tags, anonymised patient ID e.g. 12% of original tags|
| Researcher Zone (from CTP) | DICOM images with tags anonymised by CTP. These include technical tags (some of which are not loaded to Relational / used in cohort building), date tags, anonymised patient ID e.g. 12% of original tags|
| Researcher Zone (from NLP) | DICOM files containing full clinical reports (e.g. Dose Reports, Structured Reports). These reports would need to be be anonymised with a dedicated NLP tool as free text report redacting is not something CTP is set up to do. A high proportion of the clinical report content would need to remain in these files for most free text research activities e.g. 98%|

0 comments on commit 6f98d46

Please sign in to comment.