NER Pipeline for Demographic Information - Voice of the Patient

Description

This pipeline extracts mentions of demographic information from health-related text in colloquial language.

Predicted Entities

Live Demo Open in Colab Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

pipeline = PretrainedPipeline("ner_vop_demographic_pipeline", "en", "clinical/models")

pipeline.annotate("
My grandma, who's 85 and Black, just had a pacemaker implanted in the cardiology department. The doctors say it'll help regulate her heartbeat and prevent future complications.
")

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

val pipeline = new PretrainedPipeline("ner_vop_demographic_pipeline", "en", "clinical/models")

val result = pipeline.annotate("
My grandma, who's 85 and Black, just had a pacemaker implanted in the cardiology department. The doctors say it'll help regulate her heartbeat and prevent future complications.
")

Results

| chunk   | ner_label     |
|:--------|:--------------|
| grandma | Gender        |
| 85      | Age           |
| Black   | RaceEthnicity |
| doctors | Employment    |
| her     | Gender        |

Model Information

Model Name: ner_vop_demographic_pipeline
Type: pipeline
Compatibility: Healthcare NLP 4.4.4+
License: Licensed
Edition: Official
Language: en
Size: 791.6 MB

Included Models

  • DocumentAssembler
  • SentenceDetectorDLModel
  • TokenizerModel
  • WordEmbeddingsModel
  • MedicalNerModel
  • NerConverter