Edit on GitHub
  • John Snow Labs
  • Jun 26, 2022

Mapping Drug Brand Names with Corresponding National Drug Codes

  • chunk_mapper
  • ndc
  • clinical
  • licensed
  • en

Description

This pretrained model maps drug brand names to corresponding National Drug Codes (NDC). Product NDCs for each strength are returned in result and metadata.

Predicted Entities

Strength_NDC

Open in Colab Copy S3 URI

How to use

document_assembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("chunk")

chunkerMapper = ChunkMapperModel.pretrained("drug_brandname_ndc_mapper", "en", "clinical/models")\
.setInputCols(["chunk"])\
.setOutputCol("ndc")\
.setRels(["Strength_NDC"])\
.setLowerCase(True)


pipeline = Pipeline().setStages([
			document_assembler,
			chunkerMapper])  


model = pipeline.fit(spark.createDataFrame([[""]]).toDF("text")) 

light_pipeline = LightPipeline(model)

result = light_pipeline.fullAnnotate(["zytiga", "zyvana", "ZYVOX"])

val document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("chunk")

val chunkerMapper = ChunkMapperModel.pretrained("drug_brandname_ndc_mapper", "en", "clinical/models")
.setInputCols(Array("chunk"))
.setOutputCol("ndc")
.setRels(Array("Strength_NDC"))
.setLowerCase(True)


val pipeline = new Pipeline().setStages(Array(
				  document_assembler,
				  chunkerMapper))

val sample_data = Seq("zytiga", "zyvana", "ZYVOX").toDS.toDF("text")

val result = pipeline.fit(sample_data).transform(sample_data)

import nlu
nlu.load("en.map_entity.drug_brand_to_ndc").predict("""Put your text here.""")

Results

|    | Brandname   | Strength_NDC             |
|---:|:------------|:-------------------------|
|  0 | zytiga      | 500 mg/1 | 57894-195     |
|  1 | zyvana      | 527 mg/1 | 69336-405     |
|  2 | ZYVOX       | 600 mg/300mL | 0009-4992 |

Model Information

Model Name: drug_brandname_ndc_mapper
Compatibility: Healthcare NLP 3.5.3+
License: Licensed
Edition: Official
Input Labels: [chunk]
Output Labels: [mappings]
Language: en
Size: 3.0 MB