Edit on GitHub
  • John Snow Labs
  • Jul 26, 2026

Mapping Drug Brand Names with Corresponding National Drug Codes

  • en
  • chunk_mapper
  • licensed
  • clinical
  • ndc
  • drug_brandname

Description

This pretrained clinical model performs the task of mapping pharmaceutical brand names to their corresponding National Drug Codes (NDC). The model returns product NDCs for each dosage strength in both the result and metadata fields. Trained on the openFDA NDC Directory (release 2026-07-22).

Open in Colab Copy S3 URI

How to use


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

doc2chunk = Doc2Chunk()\
    .setInputCols(["document"])\
    .setOutputCol("chunk")

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

pipeline = Pipeline(stages=[
    document_assembler,
    doc2chunk,
    chunkerMapper
])

data = spark.createDataFrame([["zytiga"], ["lipitor"], ["crestor"]]).toDF("text")
result = pipeline.fit(data).transform(data)



document_assembler = nlp.DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")

doc2chunk = nlp.Doc2Chunk()\
    .setInputCols(["document"])\
    .setOutputCol("chunk")

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

pipeline = nlp.Pipeline(stages=[
    document_assembler,
    doc2chunk,
    chunkerMapper
])

data = spark.createDataFrame([["zytiga"], ["lipitor"], ["crestor"]]).toDF("text")
result = pipeline.fit(data).transform(data)



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

val doc2chunk = new Doc2Chunk()
    .setInputCols("document")
    .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(
    documentAssembler,
    doc2chunk,
    chunkerMapper
))

val data = Seq("zytiga", "lipitor", "crestor").toDF("text")
val result = pipeline.fit(data).transform(data)

Results

| Brandname   | Strength_NDC         | All_K_Resolutions                                                                     |
|:------------|:---------------------|:--------------------------------------------------------------------------------------|
| zytiga      | 250 mg/1 | 57894-150 | 250 mg/1 | 57894-150:::500 mg/1 | 57894-195                                           |
| lipitor     | 20 mg/1 | 58151-156  | 20 mg/1 | 58151-156:::80 mg/1 | 58151-158:::10 mg/1 | 58151-155:::40 mg/1 | 58151-157 |
| crestor     | 10 mg/1 | 0310-7570  | 10 mg/1 | 0310-7570:::20 mg/1 | 0310-7580:::40 mg/1 | 0310-7590:::5 mg/1 | 0310-7560  |

Model Information

Model Name: drug_brandname_ndc_mapper
Compatibility: Healthcare NLP 6.4.0+
License: Licensed
Edition: Official
Input Labels: [chunk]
Output Labels: [ndc]
Language: en
Size: 1.7 MB