Edit on GitHub
  • John Snow Labs
  • Jun 12, 2026

Mapping Entities (Clinical Drug) with Corresponding UMLS CUI Codes

  • en
  • chunk_mapper
  • licensed
  • clinical
  • umls
  • clinical_drug

Description

This model maps clinical drug formulation entities extracted by NER to UMLS CUI codes covering the Clinical Drug semantic type (T200), comprising approximately 345,000 name–CUI pairs. It is trained on the 2026AA release of the Unified Medical Language System (UMLS) dataset.

Live Demo Open in Colab Copy S3 URI

How to use


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

sentence_detector = SentenceDetector()\
    .setInputCols(["document"])\
    .setOutputCol("sentence")

tokenizer = Tokenizer()\
    .setInputCols(["sentence"])\
    .setOutputCol("token")

word_embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")\
    .setInputCols(["sentence", "token"])\
    .setOutputCol("embeddings")

ner_model = MedicalNerModel.pretrained("ner_posology_greedy", "en", "clinical/models")\
    .setInputCols(["sentence", "token", "embeddings"])\
    .setOutputCol("clinical_ner")

ner_model_converter = NerConverterInternal()\
    .setInputCols(["sentence", "token", "clinical_ner"])\
    .setOutputCol("ner_chunk")

chunkerMapper = ChunkMapperModel.pretrained("umls_clinical_drugs_mapper", "en", "clinical/models")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")\
    .setRels(["umls_code"])\
    .setLowerCase(True)

mapper_pipeline = Pipeline(stages=[
    document_assembler,
    sentence_detector,
    tokenizer,
    word_embeddings,
    ner_model,
    ner_model_converter,
    chunkerMapper,
])
data = spark.createDataFrame([["The patient was prescribed Neosporin Cream to be applied externally to the infected area, metformin hydrochloride 1000 MG for diabetes management, and acetaminophen 500 mg oral capsule for pain relief. "]]).toDF("text")
result = mapper_pipeline.fit(data).transform(data)



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

sentence_detector = nlp.SentenceDetector()\
    .setInputCols(["document"])\
    .setOutputCol("sentence")

tokenizer = nlp.Tokenizer()\
    .setInputCols(["sentence"])\
    .setOutputCol("token")

word_embeddings = nlp.WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")\
    .setInputCols(["sentence", "token"])\
    .setOutputCol("embeddings")

ner_model = medical.NerModel.pretrained("ner_posology_greedy", "en", "clinical/models")\
    .setInputCols(["sentence", "token", "embeddings"])\
    .setOutputCol("clinical_ner")

ner_model_converter = medical.NerConverterInternal()\
    .setInputCols(["sentence", "token", "clinical_ner"])\
    .setOutputCol("ner_chunk")

chunkerMapper = medical.ChunkMapperModel.pretrained("umls_clinical_drugs_mapper", "en", "clinical/models")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")\
    .setRels(["umls_code"])\
    .setLowerCase(True)

mapper_pipeline = nlp.Pipeline(stages=[
    document_assembler,
    sentence_detector,
    tokenizer,
    word_embeddings,
    ner_model,
    ner_model_converter,
    chunkerMapper,
])
data = spark.createDataFrame([["The patient was prescribed Neosporin Cream to be applied externally to the infected area, metformin hydrochloride 1000 MG for diabetes management, and acetaminophen 500 mg oral capsule for pain relief. "]]).toDF("text")
result = mapper_pipeline.fit(data).transform(data)



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

val sentenceDetector = new SentenceDetector()
    .setInputCols(Array("document"))
    .setOutputCol("sentence")

val tokenizer = new Tokenizer()
    .setInputCols(Array("sentence"))
    .setOutputCol("token")

val wordEmbeddings = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")
    .setInputCols(Array("sentence", "token"))
    .setOutputCol("embeddings")

val nerModel = MedicalNerModel.pretrained("ner_posology_greedy", "en", "clinical/models")
    .setInputCols(Array("sentence", "token", "embeddings"))
    .setOutputCol("clinical_ner")

val nerModelConverter = new NerConverterInternal()
    .setInputCols(Array("sentence", "token", "clinical_ner"))
    .setOutputCol("ner_chunk")

val chunkerMapper = ChunkMapperModel.pretrained("umls_clinical_drugs_mapper", "en", "clinical/models")
    .setInputCols(Array("ner_chunk"))
    .setOutputCol("mappings")
    .setRels(Array("umls_code"))
    .setLowerCase(true)

val mapperPipeline = new Pipeline().setStages(Array(
    documentAssembler,
    sentenceDetector,
    tokenizer,
    wordEmbeddings,
    nerModel,
    nerModelConverter,
    chunkerMapper,
))

val data = Seq("The patient was prescribed Neosporin Cream to be applied externally to the infected area, metformin hydrochloride 1000 MG for diabetes management, and acetaminophen 500 mg oral capsule for pain relief. ").toDF("text")
val result = mapperPipeline.fit(data).transform(data)

Results

| ner_chunk                         | umls_code   |
|:----------------------------------|:------------|
| Neosporin Cream                   | C0132149    |
| metformin hydrochloride 1000 MG   | C2719784    |
| acetaminophen 500 mg oral capsule | C0691088    |

Model Information

Model Name: umls_clinical_drugs_mapper
Compatibility: Healthcare NLP 6.4.0+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 16.5 MB