Pipeline to Detect Adverse Drug Events (MedicalBertForTokenClassification)

Description

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

Predicted Entities

Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

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

text = '''I used to be on paxil but that made me more depressed and prozac made me angry. Maybe cos of the insulin blocking effect of seroquel but i do feel sugar crashes when eat fast carbs.'''

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

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

val text = "I used to be on paxil but that made me more depressed and prozac made me angry. Maybe cos of the insulin blocking effect of seroquel but i do feel sugar crashes when eat fast carbs."

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

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

text = '''I used to be on paxil but that made me more depressed and prozac made me angry. Maybe cos of the insulin blocking effect of seroquel but i do feel sugar crashes when eat fast carbs.'''

result = pipeline.fullAnnotate(text)

Results

|    | ner_chunk        |   begin |   end | ner_label   |   confidence |
|---:|:-----------------|--------:|------:|:------------|-------------:|
|  0 | depressed        |      44 |    52 | ADE         |     0.999755 |
|  1 | angry            |      73 |    77 | ADE         |     0.999608 |
|  2 | insulin blocking |      97 |   112 | ADE         |     0.738712 |
|  3 | sugar crashes    |     147 |   159 | ADE         |     0.993742 |

Model Information

Model Name: bert_token_classifier_ade_tweet_binary_pipeline
Type: pipeline
Compatibility: Healthcare NLP 4.4.4+
License: Licensed
Edition: Official
Language: en
Size: 404.8 MB

Included Models

  • DocumentAssembler
  • SentenceDetectorDLModel
  • TokenizerModel
  • MedicalBertForTokenClassifier
  • NerConverterInternalModel