Edit on GitHub
  • John Snow Labs
  • Jun 13, 2026

Mapping MedDRA Codes with Their Corresponding UMLS Codes

  • en
  • chunk_mapper
  • licensed
  • clinical
  • umls
  • meddra

Description

This model maps MedDRA codes to UMLS codes. It is trained on the 2026AA release of the Unified Medical Language System (UMLS) dataset. MedDRA mapper models are removed from the Models Hub due to license restrictions and can only be shared with the users who already have a valid MedDRA license. Please contact support@johnsnowlabs.com for access.

Live Demo Open in Colab

How to use


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

doc2chunk = Doc2Chunk()\
    .setInputCols(["doc"])\
    .setOutputCol("ner_chunk")

mapper = ChunkMapperModel.pretrained("meddra_umls_mapper","en","clinical/models")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")

pipeline = Pipeline(stages=[document_assembler, doc2chunk, mapper])
data = spark.createDataFrame([["10012594"],["10003268"],["10047699"]]).toDF("text")
result = pipeline.fit(data).transform(data)



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

doc2chunk = nlp.Doc2Chunk()\
    .setInputCols(["doc"])\
    .setOutputCol("ner_chunk")

mapper = medical.ChunkMapperModel.pretrained("meddra_umls_mapper","en","clinical/models")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")

pipeline = nlp.Pipeline(stages=[document_assembler, doc2chunk, mapper])
data = spark.createDataFrame([["10012594"],["10003268"],["10047699"]]).toDF("text")
result = pipeline.fit(data).transform(data)



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

val doc2chunk = new Doc2Chunk()
  .setInputCols(Array("doc"))
  .setOutputCol("ner_chunk")

val mapper = ChunkMapperModel.pretrained("meddra_umls_mapper","en","clinical/models")
  .setInputCols(Array("ner_chunk"))
  .setOutputCol("mappings")

val pipeline = new Pipeline().setStages(Array(documentAssembler, doc2chunk, mapper))
val data = Seq("10012594","10003268","10047699").toDF("text")
val result = pipeline.fit(data).transform(data)

Results

|   meddra_code | umls_code   |
|--------------:|:------------|
|      10012594 | C0011849    |
|      10003268 | C0003873    |
|      10047699 | C0042963    |

Model Information

Model Name: meddra_umls_mapper
Compatibility: Healthcare NLP 6.4.0+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 739.9 KB