Pipeline to Detect Clinical Events

Description

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

Predicted Entities

OCCURRENCE, DATE,PROBLEM,DURATION,EVIDENTIAL,TREATMENT,TEST,CLINICAL_DEPT,FREQUENCY,TIME

Live Demo Open in Colab Download Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

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


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

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

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


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

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

Results

+------------------+-------------+
|chunks            |entities     |
+------------------+-------------+
|presented         |EVIDENTIAL   |
|the emergency room|CLINICAL_DEPT|
|last evening      |DATE         |
+------------------+-------------+

Model Information

Included Models

• DocumentAssembler
• SentenceDetectorDLModel
• TokenizerModel
• WordEmbeddingsModel
• MedicalNerModel
• NerConverter