medaCy / Git / Diff of /README.md

Models:

philipB/

medaCy

Downloads: 1

Diff of /README.md [6c353a] .. [175152]

Switch to unified view


[![spaCy](https://img.shields.io/badge/built%20with-spaCy-09a3d5.svg)](https://spacy.io)

# medaCy
:hospital: Medical Text Mining and Information Extraction with spaCy :hospital:

MedaCy is a text processing and learning framework built over [spaCy](https://spacy.io/) to support the lightning fast 
prototyping, training, and application of highly predictive medical NLP models. It is designed to streamline researcher 
workflow by providing utilities for model training, prediction and organization while insuring the replicability of systems.

![alt text](https://nlp.cs.vcu.edu/images/Edit_NanomedicineDatabase.png?raw=true "Nanoinformatics")

# :star2: Features
- Highly predictive, shared-task dominating out-of-the-box trained models for medical named entity recognition.
- Customizable pipelines with detailed development instructions and documentation.
- Allows the designing of replicable NLP systems for reproducing results and encouraging the distribution of models whilst still allowing for privacy.
- Active community development spearheaded and maintained by [NLP@VCU](https://nlp.cs.vcu.edu/).
- Detailed [API](https://medacy.readthedocs.io/en/latest/).

## :thought_balloon: Where to ask questions

MedaCy is actively maintained by a team of researchers at Virginia Commonwealth University. The best way to
receive immediate responses to any questions is to raise an issue. Make sure to first consult the 
[API](https://medacy.readthedocs.io/en/latest/).  See how to formulate a good issue or feature request in the [Contribution Guide](CONTRIBUTING.md).

## :computer: Installation Instructions
MedaCy can be installed for general use or for pipeline development / research purposes.

| Application | Run           |
| ----------- |:-------------:|
| Prediction and Model Training (stable) | `pip install git+https://github.com/NLPatVCU/medaCy.git` |
| Prediction and Model Training (latest) | `pip install git+https://github.com/NLPatVCU/medaCy.git@development` |
| Pipeline Development and Contribution  | [See Contribution Instructions](/CONTRIBUTING.md) |


# :books: Power of medaCy
After installing medaCy and [medaCy's clinical model](guide/models/clinical_notes_model.md), simply run:

```python
from medacy.model.model import Model

model = Model.load_external('medacy_model_clinical_notes')
annotation = model.predict("The patient was prescribed 1 capsule of Advil for 5 days.")
print(annotation)
```
and receive instant predictions:
```python
[
    ('Drug', 40, 45, 'Advil'),
    ('Dosage', 27, 28, '1'), 
    ('Form', 29, 36, 'capsule'),
    ('Duration', 46, 56, 'for 5 days')
]
```

MedaCy can also be used through its command line interface, documented [here](./guide/command_line_interface.md)

To explore medaCy's other models or train your own, visit the [examples section](guide).

Reference
=========
```bibtex
@ARTICLE {
    author  = "Andriy Mulyar, Natassja Lewinski and Bridget McInnes",
    title   = "TAC SRIE 2018: Extracting Systematic Review Information with MedaCy",
    journal = "National Institute of Standards and Technology (NIST) 2018 Systematic Review Information Extraction (SRIE) > Text Analysis Conference",
    year    = "2018",
    month   = "nov"
}
```

License
=======
This package is licensed under the GNU General Public License.

Authors
=======
Current contributors: Steele Farnsworth, Anna Conte, Gabby Gurdin, Aidan Kierans, Aidan Myers, and Bridget T. McInnes

Former contributors: Andriy Mulyar, Jorge Vargas, Corey Sutphin, and Bobby Best

Acknowledgments
===============
- [VCU Natural Language Processing Lab](https://nlp.cs.vcu.edu/) ![alt text](https://nlp.cs.vcu.edu/images/vcu_head_logo "VCU")
- [Nanoinformatics Vertically Integrated Projects](https://rampages.us/nanoinformatics/)

	a/README.md		b/README.md
1	[![spaCy](https://img.shields.io/badge/built%20with-spaCy-09a3d5.svg)](https://spacy.io)	1	[![spaCy](https://img.shields.io/badge/built%20with-spaCy-09a3d5.svg)](https://spacy.io)
2		2
3	# medaCy	3	# medaCy
4	:hospital: Medical Text Mining and Information Extraction with spaCy :hospital:	4	:hospital: Medical Text Mining and Information Extraction with spaCy :hospital:
5		5
6	MedaCy is a text processing and learning framework built over [spaCy](https://spacy.io/) to support the lightning fast	6	MedaCy is a text processing and learning framework built over [spaCy](https://spacy.io/) to support the lightning fast
7	prototyping, training, and application of highly predictive medical NLP models. It is designed to streamline researcher	7	prototyping, training, and application of highly predictive medical NLP models. It is designed to streamline researcher
8	workflow by providing utilities for model training, prediction and organization while insuring the replicability of systems.	8	workflow by providing utilities for model training, prediction and organization while insuring the replicability of systems.
9		9
10	![alt text](https://nlp.cs.vcu.edu/images/Edit_NanomedicineDatabase.png "Nanoinformatics")	10	![alt text](https://nlp.cs.vcu.edu/images/Edit_NanomedicineDatabase.png?raw=true "Nanoinformatics")
11		11
12	# :star2: Features	12	# :star2: Features
13	- Highly predictive, shared-task dominating out-of-the-box trained models for medical named entity recognition.	13	- Highly predictive, shared-task dominating out-of-the-box trained models for medical named entity recognition.
14	- Customizable pipelines with detailed development instructions and documentation.	14	- Customizable pipelines with detailed development instructions and documentation.
15	- Allows the designing of replicable NLP systems for reproducing results and encouraging the distribution of models whilst still allowing for privacy.	15	- Allows the designing of replicable NLP systems for reproducing results and encouraging the distribution of models whilst still allowing for privacy.
16	- Active community development spearheaded and maintained by [NLP@VCU](https://nlp.cs.vcu.edu/).	16	- Active community development spearheaded and maintained by [NLP@VCU](https://nlp.cs.vcu.edu/).
17	- Detailed [API](https://medacy.readthedocs.io/en/latest/).	17	- Detailed [API](https://medacy.readthedocs.io/en/latest/).
18		18
19	## :thought_balloon: Where to ask questions	19	## :thought_balloon: Where to ask questions
20		20
21	MedaCy is actively maintained by a team of researchers at Virginia Commonwealth University. The best way to	21	MedaCy is actively maintained by a team of researchers at Virginia Commonwealth University. The best way to
22	receive immediate responses to any questions is to raise an issue. Make sure to first consult the	22	receive immediate responses to any questions is to raise an issue. Make sure to first consult the
23	[API](https://medacy.readthedocs.io/en/latest/). See how to formulate a good issue or feature request in the [Contribution Guide](CONTRIBUTING.md).	23	[API](https://medacy.readthedocs.io/en/latest/). See how to formulate a good issue or feature request in the [Contribution Guide](CONTRIBUTING.md).
24		24
25	## :computer: Installation Instructions	25	## :computer: Installation Instructions
26	MedaCy can be installed for general use or for pipeline development / research purposes.	26	MedaCy can be installed for general use or for pipeline development / research purposes.
27		27
28	\| Application \| Run \|	28	\| Application \| Run \|
29	\| ----------- \|:-------------:\|	29	\| ----------- \|:-------------:\|
30	\| Prediction and Model Training (stable) \| `pip install git+https://github.com/NLPatVCU/medaCy.git` \|	30	\| Prediction and Model Training (stable) \| `pip install git+https://github.com/NLPatVCU/medaCy.git` \|
31	\| Prediction and Model Training (latest) \| `pip install git+https://github.com/NLPatVCU/medaCy.git@development` \|	31	\| Prediction and Model Training (latest) \| `pip install git+https://github.com/NLPatVCU/medaCy.git@development` \|
32	\| Pipeline Development and Contribution \| [See Contribution Instructions](/CONTRIBUTING.md) \|	32	\| Pipeline Development and Contribution \| [See Contribution Instructions](/CONTRIBUTING.md) \|
33		33
34		34
35	# :books: Power of medaCy	35	# :books: Power of medaCy
36	After installing medaCy and [medaCy's clinical model](guide/models/clinical_notes_model.md), simply run:	36	After installing medaCy and [medaCy's clinical model](guide/models/clinical_notes_model.md), simply run:
37		37
38	```python	38	```python
39	from medacy.model.model import Model	39	from medacy.model.model import Model
40		40
41	model = Model.load_external('medacy_model_clinical_notes')	41	model = Model.load_external('medacy_model_clinical_notes')
42	annotation = model.predict("The patient was prescribed 1 capsule of Advil for 5 days.")	42	annotation = model.predict("The patient was prescribed 1 capsule of Advil for 5 days.")
43	print(annotation)	43	print(annotation)
44	```	44	```
45	and receive instant predictions:	45	and receive instant predictions:
46	```python	46	```python
47	[	47	[
48	('Drug', 40, 45, 'Advil'),	48	('Drug', 40, 45, 'Advil'),
49	('Dosage', 27, 28, '1'),	49	('Dosage', 27, 28, '1'),
50	('Form', 29, 36, 'capsule'),	50	('Form', 29, 36, 'capsule'),
51	('Duration', 46, 56, 'for 5 days')	51	('Duration', 46, 56, 'for 5 days')
52	]	52	]
53	```	53	```
54		54
55	MedaCy can also be used through its command line interface, documented [here](./guide/command_line_interface.md)	55	MedaCy can also be used through its command line interface, documented [here](./guide/command_line_interface.md)
56		56
57	To explore medaCy's other models or train your own, visit the [examples section](guide).	57	To explore medaCy's other models or train your own, visit the [examples section](guide).
58		58
59	Reference	59	Reference
60	=========	60	=========
61	```bibtex	61	```bibtex
62	@ARTICLE {	62	@ARTICLE {
63	author = "Andriy Mulyar, Natassja Lewinski and Bridget McInnes",	63	author = "Andriy Mulyar, Natassja Lewinski and Bridget McInnes",
64	title = "TAC SRIE 2018: Extracting Systematic Review Information with MedaCy",	64	title = "TAC SRIE 2018: Extracting Systematic Review Information with MedaCy",
65	journal = "National Institute of Standards and Technology (NIST) 2018 Systematic Review Information Extraction (SRIE) > Text Analysis Conference",	65	journal = "National Institute of Standards and Technology (NIST) 2018 Systematic Review Information Extraction (SRIE) > Text Analysis Conference",
66	year = "2018",	66	year = "2018",
67	month = "nov"	67	month = "nov"
68	}	68	}
69	```	69	```
70		70
71	License	71	License
72	=======	72	=======
73	This package is licensed under the GNU General Public License.	73	This package is licensed under the GNU General Public License.
74		74
75	Authors	75	Authors
76	=======	76	=======
77	Current contributors: Steele Farnsworth, Anna Conte, Gabby Gurdin, Aidan Kierans, Aidan Myers, and Bridget T. McInnes	77	Current contributors: Steele Farnsworth, Anna Conte, Gabby Gurdin, Aidan Kierans, Aidan Myers, and Bridget T. McInnes
78		78
79	Former contributors: Andriy Mulyar, Jorge Vargas, Corey Sutphin, and Bobby Best	79	Former contributors: Andriy Mulyar, Jorge Vargas, Corey Sutphin, and Bobby Best
80		80
81	Acknowledgments	81	Acknowledgments
82	===============	82	===============
83	- [VCU Natural Language Processing Lab](https://nlp.cs.vcu.edu/) ![alt text](https://nlp.cs.vcu.edu/images/vcu_head_logo "VCU")	83	- [VCU Natural Language Processing Lab](https://nlp.cs.vcu.edu/) ![alt text](https://nlp.cs.vcu.edu/images/vcu_head_logo "VCU")
84	- [Nanoinformatics Vertically Integrated Projects](https://rampages.us/nanoinformatics/)	84	- [Nanoinformatics Vertically Integrated Projects](https://rampages.us/nanoinformatics/)