Pipeline to Detect clinical events (biobert)

Description

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

Predicted Entities

SPECIES, HUMAN

Live Demo Open in Colab Download Copy S3 URI

How to use

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

pipeline.annotate("The patient presented to the emergency room last evening")

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

pipeline.annotate("The patient presented to the emergency room last evening")

import nlu
nlu.load("en.med_ner.biobert_events.pipeline").predict("""The patient presented to the emergency room last evening""")

Results

+------------------+-------------+
|chunks            |entities     |
+------------------+-------------+
|presented         |OCCURRENCE   |
|the emergency room|CLINICAL_DEPT|
+------------------+-------------+

Model Information

Included Models

• DocumentAssembler
• SentenceDetectorDLModel
• TokenizerModel
• BertEmbeddings
• MedicalNerModel
• NerConverter