Description
This pretrained pipeline includes the Medical Bert for Sequence Classification model to classify health-related text in colloquial language according to the presence or absence of mentions of side effects related to drugs. The pipeline is built on the top of bert_sequence_classifier_vop_drug_side_effect model.
Predicted Entities
Live Demo Open in Colab Copy S3 URI
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("bert_sequence_classifier_vop_drug_side_effect_pipeline", "en", "clinical/models")
pipeline.annotate("I felt kind of dizzy after taking that medication for a month.")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("bert_sequence_classifier_vop_drug_side_effect_pipeline", "en", "clinical/models")
val result = pipeline.annotate(I felt kind of dizzy after taking that medication for a month.)
Results
| text | prediction |
|:---------------------------------------------------------------|:-------------|
| I felt kind of dizzy after taking that medication for a month. | Drug_AE |
Model Information
| Model Name: | bert_sequence_classifier_vop_drug_side_effect_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.4.3+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 406.4 MB |
Included Models
- DocumentAssembler
- TokenizerModel
- MedicalBertForSequenceClassification