Pipeline to Detect Drugs - Generalized Single Entity

Description

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

Copy S3 URI

How to use

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

pipeline.annotate("DOSAGE AND ADMINISTRATION The initial dosage of hydrocortisone tablets may vary from 20 mg to 240 mg of hydrocortisone per day depending on the specific disease entity being treated.")
val pipeline = new PretrainedPipeline("ner_drugs_greedy_pipeline", "en", "clinical/models")

pipeline.annotate("DOSAGE AND ADMINISTRATION The initial dosage of hydrocortisone tablets may vary from 20 mg to 240 mg of hydrocortisone per day depending on the specific disease entity being treated.")
import nlu
nlu.load("en.med_ner.drugs_greedy.pipeline").predict("""DOSAGE AND ADMINISTRATION The initial dosage of hydrocortisone tablets may vary from 20 mg to 240 mg of hydrocortisone per day depending on the specific disease entity being treated.""")

Results

+-----------------------------------+------------+
| chunk                             | ner_label  |
+-----------------------------------+------------+
| hydrocortisone tablets            | DRUG       |
| 20 mg to 240 mg of hydrocortisone | DRUG       |
+-----------------------------------+------------+

Model Information

Model Name: ner_drugs_greedy_pipeline
Type: pipeline
Compatibility: Healthcare NLP 3.4.1+
License: Licensed
Edition: Official
Language: en
Size: 1.7 GB

Included Models

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