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

Mapping National Drug Codes (NDC) with Corresponding HCPCS Codes and Descriptions

  • en
  • chunk_mapper
  • licensed
  • clinical
  • ndc
  • hcpcs

Description

This pretrained model establishes mappings between National Drug Codes and their corresponding HCPCS codes along with descriptions. Trained on the PDAC NDC/HCPCS Crosswalk (release pdac-2026-07-05).

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("ndc_hcpcs_mapper", "en", "clinical/models")\
    .setInputCols(["chunk"])\
    .setOutputCol("hcpcs")\
    .setRels(["hcpcs_code", "hcpcs_description"])

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

data = spark.createDataFrame([["16714-0892-01"], ["00990-6138-03"], ["43598-0650-11"]]).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("ndc_hcpcs_mapper", "en", "clinical/models")\
    .setInputCols(["chunk"])\
    .setOutputCol("hcpcs")\
    .setRels(["hcpcs_code", "hcpcs_description"])

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

data = spark.createDataFrame([["16714-0892-01"], ["00990-6138-03"], ["43598-0650-11"]]).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("ndc_hcpcs_mapper", "en", "clinical/models")
    .setInputCols(Array("chunk"))
    .setOutputCol("hcpcs")
    .setRels(Array("hcpcs_code", "hcpcs_description"))

val pipeline = new Pipeline().setStages(Array(
    documentAssembler,
    doc2chunk,
    chunkerMapper
))

val data = Seq("16714-0892-01", "00990-6138-03", "43598-0650-11").toDF("text")
val result = pipeline.fit(data).transform(data)

Results

| NDC Code      | HCPCS Code   | HCPCS Description                                  |
|:--------------|:-------------|:---------------------------------------------------|
| 16714-0892-01 | J0878        | INJECTION, DAPTOMYCIN, 1 MG                        |
| 00990-6138-03 | A4217        | STERILE WATER/SALINE, 500 ML                       |
| 43598-0650-11 | J9342        | INJECTION, THIOTEPA, NOT OTHERWISE SPECIFIED, 1 MG |

Model Information

Model Name: ndc_hcpcs_mapper
Compatibility: Healthcare NLP 6.4.0+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 179.2 KB