Pipeline to Detect PHI for Deidentification purposes (Italian)

Description

This pretrained pipeline is built on the top of ner_deid_subentity model.

Predicted Entities

MEDICALRECORD, ORGANIZATION, PROFESSION, DOCTOR, USERNAME, URL, CITY, DATE, SEX, PATIENT, SSN, COUNTRY, ZIP, STREET, PHONE, HOSPITAL, EMAIL, IDNUM, AGE

Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

pipeline = PretrainedPipeline("ner_deid_subentity_pipeline", "it", "clinical/models")

text = '''Ho visto Gastone Montanariello (49 anni) riferito all' Ospedale San Camillo per diabete mal controllato con sintomi risalenti a marzo 2015.'''

result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

val pipeline = new PretrainedPipeline("ner_deid_subentity_pipeline", "it", "clinical/models")

val text = "Ho visto Gastone Montanariello (49 anni) riferito all' Ospedale San Camillo per diabete mal controllato con sintomi risalenti a marzo 2015."

val result = pipeline.fullAnnotate(text)
from sparknlp.pretrained import PretrainedPipeline

pipeline = PretrainedPipeline("ner_deid_subentity_pipeline", "it", "clinical/models")

text = '''Ho visto Gastone Montanariello (49 anni) riferito all' Ospedale San Camillo per diabete mal controllato con sintomi risalenti a marzo 2015.'''

result = pipeline.fullAnnotate(text)

Results

|    | ner_chunks            |   begin |   end | ner_label   | confidence   |
|---:|:----------------------|--------:|------:|:------------|:-------------|
|  0 | Gastone Montanariello |       9 |    29 | PATIENT     |              |
|  1 | 49                    |      32 |    33 | AGE         |              |
|  2 | Ospedale San Camillo  |      55 |    74 | HOSPITAL    |              |
|  3 | marzo 2015            |     128 |   137 | DATE        |              |

Model Information

Model Name: ner_deid_subentity_pipeline
Type: pipeline
Compatibility: Healthcare NLP 4.4.4+
License: Licensed
Edition: Official
Language: it
Size: 1.3 GB

Included Models

  • DocumentAssembler
  • SentenceDetectorDLModel
  • TokenizerModel
  • WordEmbeddingsModel
  • MedicalNerModel
  • NerConverterInternalModel