SHC.Ai Cli
Project description
SHCAi Client
Instalação
Para instalar o SHCAi client: pip install -U shcaicli
Uso
from shcaicli.api import SHCAi
import os
api_key = os.getenv('API_KEY')
shc = SHCAi(api_key=api_key, tokens_mode=True)
cn = 'Paciente diagnosticado com has, nega dm. Em 20/09 iniciou QT para tratamento CA de mama'
cn_inferred = shc.infer(cn=cn)
Estrutura de retorno
O exemplo acima retorna a seguinte estrutura:
Clique para ver
[
{
"text_tokens": [
"Paciente",
"diagnosticado",
"com",
"has",
",",
"nega",
"dm",
".",
"Em",
"20/09",
"iniciou",
"QT",
"para",
"tratamento",
"CA",
"de",
"mama"
],
"clinical_entities": [
{
"entity": "has",
"entity_tokens": [
"has"
],
"label": "DISEASE",
"start": 3,
"end": 4,
"assertion": "PRESENTE",
"adverse_event": "",
"el": {
"term_text": "I10 - hipertensão essencial (primária)",
"terminology": "ICD10",
"term_code": "I10",
"term_desc": "hipertensão essencial (primária)"
},
"relations": []
},
{
"entity": "dm",
"entity_tokens": [
"dm"
],
"label": "DISEASE",
"start": 6,
"end": 7,
"assertion": "AUSENTE",
"adverse_event": "",
"el": {
"term_text": "E14 - diabetes mellitus não especificado",
"terminology": "ICD10",
"term_code": "E14",
"term_desc": "diabetes mellitus não especificado"
},
"relations": []
},
{
"entity": "20/09",
"entity_tokens": [
"20/09"
],
"label": "TEMPORAL_CONCEPT",
"start": 9,
"end": 10,
"assertion": "",
"adverse_event": "",
"el": {
"term_text": "",
"terminology": "",
"term_code": "",
"term_desc": ""
},
"relations": [
{
"entity": "QT",
"entity_tokens": [
"QT"
],
"position": "tail",
"start": 11,
"end": 12,
"type": "is_date_of"
}
]
},
{
"entity": "QT",
"entity_tokens": [
"QT"
],
"label": "PROCEDURE",
"start": 11,
"end": 12,
"assertion": "PRESENTE",
"adverse_event": "",
"el": {
"term_text": "",
"terminology": "",
"term_code": "",
"term_desc": ""
},
"relations": [
{
"entity": "20/09",
"entity_tokens": [
"20/09"
],
"position": "head",
"start": 9,
"end": 10,
"type": "is_date_of"
}
]
},
{
"entity": "CA",
"entity_tokens": [
"CA"
],
"label": "DISEASE",
"start": 14,
"end": 15,
"assertion": "PRESENTE",
"adverse_event": "",
"el": {
"term_text": "",
"terminology": "",
"term_code": "",
"term_desc": ""
},
"relations": [
{
"entity": "mama",
"entity_tokens": [
"mama"
],
"position": "tail",
"start": 16,
"end": 17,
"type": "disease_has_primary_anatomic_site"
}
]
},
{
"entity": "mama",
"entity_tokens": [
"mama"
],
"label": "BODY_PART",
"start": 16,
"end": 17,
"assertion": "",
"adverse_event": "",
"el": {
"term_text": "",
"terminology": "",
"term_code": "",
"term_desc": ""
},
"relations": [
{
"entity": "CA",
"entity_tokens": [
"CA"
],
"position": "head",
"start": 14,
"end": 15,
"type": "disease_has_primary_anatomic_site"
}
]
}
],
"biomarkers": [],
"lab_tests": [],
"vital_signs": [],
"entities_relations": [
{
"relation_type": "is_date_of",
"head_entity": "20/09",
"tail_entity": "QT",
"head_entity_tokens": [
"20/09"
],
"tail_entity_tokens": [
"QT"
],
"head_start": 9,
"head_end": 10,
"tail_start": 11,
"tail_end": 12
},
{
"relation_type": "disease_has_primary_anatomic_site",
"head_entity": "CA",
"tail_entity": "mama",
"head_entity_tokens": [
"CA"
],
"tail_entity_tokens": [
"mama"
],
"head_start": 14,
"head_end": 15,
"tail_start": 16,
"tail_end": 17
}
]
}
]
Atenção especial para a estrutura de cada clinical_entities:
{
"entity": "20/09",
"entity_tokens": [
"20/09"
],
"label": "TEMPORAL_CONCEPT",
"start": 9,
"end": 10,
"assertion": "",
"adverse_event": "",
"el": {
"term_text": "",
"terminology": "",
"term_code": "",
"term_desc": ""
},
"relations": [
{
"entity": "QT",
"entity_tokens": [
"QT"
],
"position": "tail",
"start": 11,
"end": 12,
"type": "is_date_of"
}
]
}
O campo relations está presente e mostra a quais outras entidades ela está relacionada. No exemplo acima, a entidade
categorizada como TEMPORAL_CONCEPT 20/09 possui uma relação com a entidade QT. Ao analisar a relação vemos o campo
especial position ele mostra que QT está no tail da relação que deve ser lida assim:
20/09 is_date_of QT
Tokens do texto da nota
O texto clínico foi quebrado em tokens para facilitar a identificação de cada item entre as relações. Os campos start e
end fazem referência a posição do token na lista de tokens.
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file shcaicli-0.0.8.tar.gz.
File metadata
- Download URL: shcaicli-0.0.8.tar.gz
- Upload date:
- Size: 8.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.0.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
eeebd162ba372bb04021c64d11ef217658ee9aea11e6c88e654deaae143f3876
|
|
| MD5 |
eaa4c386260e91b96aa4eeb8ab91100d
|
|
| BLAKE2b-256 |
3d9a4ec851c0ae3b4e253f7b5099c9294650345da1219d5c89189bec03dcf8a6
|
File details
Details for the file shcaicli-0.0.8-py3-none-any.whl.
File metadata
- Download URL: shcaicli-0.0.8-py3-none-any.whl
- Upload date:
- Size: 8.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.0.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9bb89943936dc114b8d4d84fdc4945028f528bac7e4d6e89f02e8f494c4edd24
|
|
| MD5 |
a0bfc84e9675f4132dcbda174f7ed51b
|
|
| BLAKE2b-256 |
c3c086267db146eb6fd53738a594121bbdb248291f7a59b7726c1c0ac12fc8fe
|