Pipeline for Adverse Drug Events

Description

A pipeline for Adverse Drug Events (ADE) with ner_ade_biobert, assertion_dl_biobert, classifierdl_ade_conversational_biobert, and re_ade_biobert . It will classify the document, extract ADE and DRUG clinical entities, assign assertion status to ADE entities, and relate Drugs with their ADEs.

Predicted Entities

ADE, DRUG

Live Demo Open in Colab Copy S3 URI

How to use

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

res = pipeline.fullAnnotate("""Been taking Lipitor for 3 months, have experienced severe fatigue a lot!!!, have only experienced cramps so far, after Doctor moved me to voltaren 2 months ago.""")


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

val result = era_pipeline.fullAnnotate("""Been taking Lipitor for 3 months, have experienced severe fatigue a lot!!!, I have only experienced cramps so far, after Doctor moved me to voltaren 2 months ago.""")(0)

import nlu
nlu.load("en.explain_doc.clinical_ade").predict("""Been taking Lipitor for 3 months, have experienced severe fatigue a lot!!! , I have only experienced cramps so far, after Doctor moved me to voltaren 2 months ago.""")

Results

Assertion:

|   |         chunks | entities | assertion |
|--:|---------------:|---------:|----------:|
| 0 |        Lipitor |     DRUG |      Past |
| 1 | severe fatigue |      ADE |      Past |
| 2 |         cramps |      ADE |   Present |
| 3 |       voltaren |     DRUG |      Past |

Relations:

|   | relation | entity1 |  chunk1 | entity2 |         chunk2 |
|--:|---------:|--------:|--------:|--------:|---------------:|
| 0 |        1 |    DRUG | Lipitor |     ADE | severe fatigue |
| 1 |        0 |     ADE |  cramps |    DRUG |       voltaren |

Model Information

Model Name: explain_clinical_doc_ade
Type: pipeline
Compatibility: Healthcare NLP 3.1.2+
License: Licensed
Edition: Official
Language: en

Included Models

  • DocumentAssembler
  • TokenizerModel
  • BertEmbeddings
  • SentenceEmbeddings
  • ClassifierDLModel
  • MedicalNerModel
  • NerConverterInternal
  • PerceptronModel
  • DependencyParserModel
  • RelationExtractionModel
  • NerConverterInternal
  • AssertionDLModel