Skip to main content

Performant and production-ready NLP pipelines for clinical text written in Dutch

Project description

clinlp

test docs pypi version pypi python versions license made with spaCy ruff

clinlp

  • :hospital: clinical + :netherlands: nl + :clipboard: NLP = :sparkles: clinlp
  • :star: NLP tools and algorithms for clinical text written in Dutch
  • :triangular_ruler: Organized in a standardized but flexible framework using spaCy
  • :rocket: Production-ready, performant, well-tested and easy to use
  • :bulb: Free, open source, created and maintained by the Dutch Clinical NLP community

Contact

If you have questions, need help getting started, found a bug, or have a feature request, please don't hesitate to contact us!

Getting started

Installation

pip install clinlp

Example

import spacy
from clinlp.ie import Term

nlp = spacy.blank("clinlp")

# Normalization
nlp.add_pipe("clinlp_normalizer")

# Sentences
nlp.add_pipe("clinlp_sentencizer")

# Entities
terms = {
    "prematuriteit": [
        "preterm", "<p3", "prematuriteit", "partus praematurus"
    ],
    "hypotensie": [
        "hypotensie", Term("bd verlaagd", proximity=1)
    ],
    "veneus_infarct": [
        "veneus infarct", Term("VI", attr="TEXT")
    ]
}

entity_matcher = nlp.add_pipe("clinlp_rule_based_entity_matcher", config={"attr": "NORM", "fuzzy": 1})
entity_matcher.add_terms_from_dict(terms)

# Qualifiers
nlp.add_pipe("clinlp_context_algorithm", config={"phrase_matcher_attr": "NORM"})

text = (
    "Preterme neonaat (<p3) opgenomen, bd enigszins verlaagd, familieanamnese vermeldt eveneens hypotensie "
    "bij moeder. Thans geen aanwijzingen voor veneus infarkt wat ook geen "
    "verklaring voor de partus prematurus is. Risico op VI blijft aanwezig."
)

doc = nlp(text)

Find information in the Doc object:

from spacy import displacy

displacy.render(doc, style="span", options={'spans_key': 'ents'})

example_doc_render.png

With relevant qualifiers (defaults omitted for readability):

for ent in doc.spans["ents"]:
  print(ent, ent._.qualifiers_str)
  • Preterme set()
  • <p3 set()
  • bd enigszins verlaagd set()
  • hypotensie {'Experiencer.Family'}
  • veneus infarkt {'Presence.Absent'}
  • partus prematurus set()
  • VI {'Temporality.Future'}

Documentation

The full documentation can be found at https://clinlp.readthedocs.io.

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

clinlp-0.9.3.tar.gz (400.2 kB view details)

Uploaded Source

Built Distribution

clinlp-0.9.3-py3-none-any.whl (49.2 kB view details)

Uploaded Python 3

File details

Details for the file clinlp-0.9.3.tar.gz.

File metadata

  • Download URL: clinlp-0.9.3.tar.gz
  • Upload date:
  • Size: 400.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.5.1

File hashes

Hashes for clinlp-0.9.3.tar.gz
Algorithm Hash digest
SHA256 0223a7a01ebec1402bf7d5f9b6e6c2ef9bbccf0e093405eab73c30312f066223
MD5 31fed76c1bb0aed5f783d8de4f6c564b
BLAKE2b-256 d8261d6383685e2a87b42b36825a4bd0d29cc0dfd075a84edcfd601debd5076e

See more details on using hashes here.

File details

Details for the file clinlp-0.9.3-py3-none-any.whl.

File metadata

  • Download URL: clinlp-0.9.3-py3-none-any.whl
  • Upload date:
  • Size: 49.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.5.1

File hashes

Hashes for clinlp-0.9.3-py3-none-any.whl
Algorithm Hash digest
SHA256 e6ab05b514e984757a37c922961d513fbd970eafcc2ed353dec2853b2c863e57
MD5 b225f84389a5319878533644d406b56b
BLAKE2b-256 eb4b995bb5303bea1d19e78715f8b93dfe156ab6fa952bc6b5d2916fe51a6854

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page