Pipeline for Adverse Drug Events

Description

A pipeline for Adverse Drug Events (ADE) with ner_ade_biobert, assertiondl_biobert and classifierdl_ade_conversational_biobert. It will extract ADE and DRUG clinical entities, assign assertion status to ADE entities, and then assign ADE status to a text (True means ADE, False means not related to ADE).

Live Demo Open in Colab Download

How to use

pipeline = PretrainedPipeline('explain_clinical_doc_ade', 'en', 'clinical/models')

res = pipeline.fullAnnotate('The clinical course suggests that the interstitial pneumonitis was induced by hydroxyurea.')


val era_pipeline = new PretrainedPipeline("explain_clinical_doc_era", "en", "clinical/models")

val result = era_pipeline.fullAnnotate("""The clinical course suggests that the interstitial pneumonitis was induced by hydroxyurea.""")(0)

Results

| #  | chunks                        | entities   | assertion  |
|----|-------------------------------|------------|------------|
| 0  | interstitial pneumonitis      | ADE        | Present    |

Model Information

Model Name: explain_clinical_doc_ade
Type: pipeline
Compatibility: Spark NLP for Healthcare 3.0.0+
License: Licensed
Edition: Official
Language: en

Included Models

  • DocumentAssembler
  • TokenizerModel
  • BertEmbeddings
  • MedicalNerModel
  • NerConverter
  • NerConverter
  • AssertionDLModel
  • SentenceEmbeddings
  • ClassifierDLModel