One that we looked at in the past is AeroText, but that does not look like it exists as its own project anymore. I would think that it could be written in any language since we are interested in the output (the annotated entities), although it certainly would be a plus if it had a Java API that could be interfaced with. Any level from free to purchase would be appreciated.

Just a note on the use, we will be using it as a supplemental annotator. It will not be our main source of named entities generated. So, yes, I am asking for rule-based suggestions only.

2 Answers 2


You can use deid software package (mirror) provided with PhysioNet/mimic.


The question is 3 years old, but here is another answer:

What about Spacy?

  • written in Python
  • free
  • no Java API , AFAIK

Rule-based matching. Find phrases and tokens, and match entities

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.