Mapping National Drug Codes (NDC) Codes with Corresponding Drug Brand Names

Description

This pretrained model maps National Drug Codes (NDC) codes with their corresponding drug brand names.

Important Note: Mappers extract additional information such as extended descriptions and categories related to Concept codes (such as RxNorm, ICD10, CPT, MESH, NDC, UMLS, etc.). They generally take Concept Codes, which are the outputs of EntityResolvers, as input. When creating a pipeline that contains ‘Mapper’, it is necessary to use the ChunkMapperModel after an EntityResolverModel.

Predicted Entities

drug_brand_name

Live Demo Open in Colab Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")

mapper = DocMapperModel.pretrained("ndc_drug_brandname_mapper", "en", "clinical/models")\
    .setInputCols("document")\
    .setOutputCol("mappings")\
    .setRels(["drug_brand_name"])\

pipeline = Pipeline(
    stages = [
        documentAssembler,
        mapper
        ])

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

lp = LightPipeline(model)

result = lp.fullAnnotate(["0009-4992", "57894-150"])

val documentAssembler = new DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")

val mapper = DocMapperModel.pretrained("ndc_drug_brandname_mapper", "en", "clinical/models")\
    .setInputCols("document")\
    .setOutputCol("mappings")\
    .setRels(Array("drug_brand_name")\

val pipeline = new Pipeline(stages = Array(
        documentAssembler,
        mapper
))

val data = Seq(Array("0009-4992", "57894-150")).toDS.toDF("text")

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

Results

|    | ndc_code   | drug_brand_name   |
|---:|:-----------|:------------------|
|  0 | 0009-4992  | ZYVOX             |
|  1 | 57894-150  | ZYTIGA            |

Model Information