Practical overview
When it fits
Use Medacy when developing or applying medical NLP models to clinical text, particularly for entity extraction and research pipelines.
Who it is for
- Researchers developing or comparing medical named-entity-recognition models.
- Developers building pipelines to extract structured information from medical text.
Documented uses
- Identify medication names and related dosage, form and duration details in clinical text.
- Train or apply medical named-entity-recognition models.
- Build customizable, reproducible medical NLP pipelines.
- Apply models through the command-line interface.
Requirements & limits
The repository is public and identifies the package as GPL-3.0 licensed.
- The clinical-notes model must be installed separately from the Medacy package for the documented prediction example.
- The repository documents a stable installation command and a distinct development-branch option.
- Pipeline development and contribution instructions are separate from the general prediction and model-training installation path.
- The package is built on spaCy and offers both Python and command-line use.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Run the clinical-notes prediction example
Use the documented clinical model to extract labeled details from a sample sentence.
Before you start
- Python environment with medaCy installed using the stable command: pip install git+https://github.com/NLPatVCU/medaCy.git
- The medaCy clinical-notes model installed separately
Steps
Install medaCy with the documented stable installation command.
Install medaCy's clinical-notes model by following its model guide.
Load the model with Model.load_external('medacy_model_clinical_notes').
Call model.predict() with clinical text and inspect the returned annotations.
Expected outcome
The README example returns labeled spans for Drug, Dosage, Form and Duration from a sentence about a prescribed medicine.
Guide limitations
- The guide demonstrates a single example sentence; it does not establish results for other texts or model performance.
- The clinical model is a separate prerequisite from the package.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 17 October 2026
- Original website title
- NLPatVCU/medaCy · Official homepage title · retained in its source language