Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Correct History behaviour #323

Open
5 tasks
aricohen93 opened this issue Sep 24, 2024 · 0 comments
Open
5 tasks

Correct History behaviour #323

aricohen93 opened this issue Sep 24, 2024 · 0 comments
Assignees

Comments

@aricohen93
Copy link
Collaborator

Description

Several issues were detected.

  • Trigger
  • Pipe name
  • Parameters
  • History of the presen illness
  • Family medical history

Trigger

The "history" tag is activated even when the trigger comes after the entity but it's included in the phrase. It should be activated when the trigger is before the entity. Although, some typical exceptions are identified, for example:

  • asthme (atcd)
  • rhume : antécédent

I recommend also to check previous annotated datasets to identified other typical forms

Pipe name

It is suggested to rename the pipe to medical_history

Parameters

Expose the patterns and the sections to consider in the parameters of the class

History of the present illness

As suggested in #219 , the section histoire de la maladie doesn't fit exactly to the common definition of medical history.

I support the idea of stop considering this section as a default history section.

Although, I think that an example in the docs showing how to add this to the parameters if the user want would be nice.

Family medical history

Stop considering this section as a default history section.
Although, I think that an example in the docs showing how to add this to the parameters if the user want would be nice.

How to reproduce the bug

text = "Il a été hospitalisé du xx/xx/xxxx au xx/xx/xxxx pour une DA avec un antécédent d'asthme il y a 25 jours."

import edsnlp
nlp = edsnlp.blank("eds")
# Sentencizer component, needed for negation detection
nlp.add_pipe("eds.sentences")
# normalize
nlp.add_pipe("eds.normalizer")
# Matcher component
nlp.add_pipe("eds.matcher", config={"terms": {"da":["da"] ,"asthme":["asthme"]}, "attr":"NORM"})
# Detect sections
nlp.add_pipe("eds.sections")
# history
nlp.add_pipe(
    "eds.history",
    config=dict(
        use_sections=True,
        use_dates=False,explain=True
    ),
)

Your Environment

  • EDS-NLP Version Used: '0.13.0'
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants