medkit-lib

Toolkit for a learning health system

https://github.com/medkit-lib/medkit

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (9.8%) to scientific vocabulary

Keywords

bert digital-health electronic-health-records nlp umls

Last synced: 6 months ago · JSON representation ·

Repository

Toolkit for a learning health system

Basic Info

Host: GitHub
Owner: medkit-lib
License: mit
Language: Python
Default Branch: main
Homepage: https://medkit-lib.org/
Size: 9.26 MB

Statistics

Stars: 18
Watchers: 4
Forks: 13
Open Issues: 7
Releases: 8

Topics

bert digital-health electronic-health-records nlp umls

Created over 2 years ago · Last pushed 11 months ago

Metadata Files

Readme Changelog Contributing License Citation

medkit

| | | |---------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | CI | | | Package | | | Project | |

medkit is a toolkit for a learning health system, developed by the HeKA research team.

This python library aims at:

Facilitating the manipulation of healthcare data of various modalities (e.g., structured, text, audio data) for the extraction of relevant features.
Developing supervised models from these various modalities for decision support in healthcare.

Installation

To install medkit with basic functionalities:

console pip install medkit-lib

To install medkit with all its optional features:

console pip install 'medkit-lib[all]'

Example

A basic named-entity recognition pipeline using medkit:

```python

1. Define individual operations.

from medkit.text.preprocessing import CharReplacer, LIGATURERULES, SIGNRULES from medkit.text.segmentation import SentenceTokenizer, SyntagmaTokenizer from medkit.text.context.negationdetector import NegationDetector from medkit.text.ner.hfentity_matcher import HFEntityMatcher

Preprocessing

charreplacer = CharReplacer(rules=LIGATURERULES + SIGN_RULES)

Segmentation

senttokenizer = SentenceTokenizer(outputlabel="sentence") synttokenizer = SyntagmaTokenizer(outputlabel="syntagma")

Negation detection

negdetector = NegationDetector(outputlabel="is_negated")

Entity recognition

entitymatcher = HFEntityMatcher(model="my-BERT-model", attrstocopy=["isnegated"])

2. Combine operations into a pipeline.

from medkit.core.pipeline import Pipeline, PipelineStep

nerpipeline = Pipeline( inputkeys=["fulltext"], outputkeys=["entities"], steps=[ PipelineStep(charreplacer, inputkeys=["fulltext"], outputkeys=["cleantext"]), PipelineStep(senttokenizer, inputkeys=["cleantext"], outputkeys=["sentences"]), PipelineStep(synttokenizer, inputkeys=["sentences"], outputkeys=["syntagmas"]), PipelineStep(negdetector, inputkeys=["syntagmas"], outputkeys=[]), PipelineStep(entitymatcher, inputkeys=["syntagmas"], outputkeys=["entities"]), ], )

3. Run the NER pipeline on a BRAT document.

from medkit.io import BratInputConverter

docs = BratInputConverter().load(path="/path/to/dataset/") entities = nerpipeline.run([doc.rawsegment for doc in docs]) ```

Getting started

To get started with medkit, please checkout our documentation.

This documentation also contains tutorials and examples showcasing the use of medkit for different tasks.

Contributing

Thank you for your interest into medkit !

We'll be happy to get your inputs !

If your problem has not been reported by another user, please open an issue, whether it's for:

reporting a bug,
discussing the current state of the code,
submitting a fix,
proposing new features,
or contributing to documentation, ...

If you want to propose a pull request, you can read CONTRIBUTING.md.

Contact

Feel free to contact us by sending an email to medkit-maintainers@inria.fr.

Owner

Name: medkit-lib
Login: medkit-lib
Kind: organization

Repositories: 2
Profile: https://github.com/medkit-lib

Citation (CITATION.cff)

# Citation File Format <https://doi.org/10.5281/zenodo.1003149>
abstract: 'Phenotyping consists in applying algorithms to identify individuals associated with a specific, potentially complex, trait or condition, typically out of a collection of Electronic Health Records (EHRs). Because a lot of the clinical information of EHRs are lying in texts, phenotyping from text takes an important role in studies that rely on the secondary use of EHRs. However, the heterogeneity and highly specialized aspect of both the content and form of clinical texts makes this task particularly tedious, and is the source of time and cost constraints in observational studies. To facilitate the development, evaluation and reproductibility of phenotyping pipelines, we developed an open-source Python library named medkit. It enables composing data processing pipelines made of easy-to-reuse software bricks, named medkit operations. In addition to the core of the library, we share the operations and pipelines we already developed and invite the phenotyping community for their reuse and enrichment.'
authors:
  - family-names: Neuraz
    given-names: Antoine
    orcid: 0000-0001-7142-6728
  - family-names: Vaillant
    given-names: Ghislain
    orcid: 0000-0003-0267-3033
  - family-names: Arias
    given-names: Camila
  - family-names: Birot
    given-names: Olivier
  - family-names: Huynh
    given-names: Kim-Tam
  - family-names: Thibaut
    given-names: Fabacher
  - family-names: Alice
    given-names: Rogier
    orcid: 0000-0002-5499-3197
  - family-names: Nicolas
    given-names: Garcelon
    orcid: 0000-0002-3326-2811
  - family-names: Ivan
    given-names: Lerner
    orcid: 0000-0002-5466-1707
  - family-names: Rance
    given-names: Bastien
    orcid: 0000-0003-4417-1197
  - family-names: Coulet
    given-names: Adrien
    orcid: 0000-0002-1466-062X
cff-version: '1.2.0'
date-released: '2024-08-30'
doi: 10.48550/arXiv.2409.00164
keywords:
  - clinical texts
  - feature extraction
  - open science
  - phenotyping
  - reproducible computing
license: MIT
message: 'If you use this software, please cite it using the metadata from this file.'
repository-code: https://github.com/medkit-lib/medkit
title: 'Facilitating phenotyping from clinical texts: the medkit library'
type: software
url: https://www.medkit-lib.org/

GitHub Events

Total

Issues event: 4
Watch event: 4
Delete event: 2
Issue comment event: 4
Push event: 12
Pull request event: 6
Pull request review event: 1
Fork event: 5
Create event: 3

Last Year

Issues event: 4
Watch event: 4
Delete event: 2
Issue comment event: 4
Push event: 12
Pull request event: 6
Pull request review event: 1
Fork event: 5
Create event: 3

Issues and Pull Requests

Last synced: over 1 year ago

All Time

Total issues: 24
Total pull requests: 74
Average time to close issues: 7 days
Average time to close pull requests: 9 days
Total issue authors: 6
Total pull request authors: 5
Average comments per issue: 1.0
Average comments per pull request: 0.39
Merged pull requests: 62
Bot issues: 0
Bot pull requests: 2

Past Year

Issues: 24
Pull requests: 74
Average time to close issues: 7 days
Average time to close pull requests: 9 days
Issue authors: 6
Pull request authors: 5
Average comments per issue: 1.0
Average comments per pull request: 0.39
Merged pull requests: 62
Bot issues: 0
Bot pull requests: 2

View more stats

Top Authors

Issue Authors

ghisvail (5)
coulet (3)
DrFabach (3)
Thibeb (2)
vincentzossou (1)
valentin-marie (1)
nourG22 (1)

Pull Request Authors

ghisvail (74)
cpetresc (6)
Thibeb (5)
DrFabach (4)
dependabot[bot] (3)
val461 (1)

Top Labels

Issue Labels

bug (1)

Pull Request Labels

dependencies (3)

Packages

Total packages: 1
Total downloads:
- pypi 120 last-month

Total dependent packages: 0
Total dependent repositories: 0
Total versions: 19
Total maintainers: 2

pypi.org: medkit-lib

A Python library for a learning health system

Documentation: https://medkit.readthedocs.io
License: MIT License
Latest release: 0.17.0
published 11 months ago

Versions: 19
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 120 Last month

Rankings

Dependent packages count: 7.0%

Average: 18.7%

Dependent repos count: 30.5%

Maintainers (2)

ghisvail medkit-maintainers

Last synced: 6 months ago

Dependencies

.github/workflows/lint.yaml actions

actions/checkout v4 composite
actions/setup-python v4 composite
pre-commit/action v3.0.0 composite

.github/workflows/test.yaml actions

actions/checkout v4 composite
actions/setup-python v4 composite
snok/install-poetry v1 composite

poetry.lock pypi

317 dependencies

pyproject.toml pypi

PyRuSH ^1.0
Unidecode *
duptextfinder *
edsnlp ^0.9
feather-format ^0.4
flashtext ^2.7
iamsystem >=0.3
intervaltree *
numpy *
packaging *
pandas --- - !ruby/hash:ActiveSupport::HashWithIndifferentAccess version: "^1.4" python: ">=3.8, <4.0" optional: true
pyaml *
pyannote-audio ^3.1
pyannote-core ^5.0.0
pyannote-metrics ^3.2.0
pysrt ^1.1.2
python >=3.8, <4.0
quickumls ^1.4
requests *
resampy ^0.4
sacremoses *
scikit-learn ^1.3.2
sentencepiece *
seqeval ^1.2.2
smart-open *
soundfile *
spacy ^3.4
speechbrain ^0.5
torch ^2.1.1
torchaudio ^2.1.1
tqdm *
transformers ^4.21
typing-extensions *
unqlite ^0.9.6
webrtcvad ^2.0
wheel *

.github/workflows/release.yaml actions

actions/checkout v4 composite
actions/setup-python v4 composite
pypa/gh-action-pypi-publish release/v1 composite