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

Mapping Entities (Major Clinical Concepts) with Corresponding UMLS CUI Codes

  • en
  • chunk_mapper
  • licensed
  • clinical
  • umls
  • major_concepts

Description

This model maps major biomedical concept entities extracted by NER to UMLS CUI codes covering Body Part, Finding, Injury, and Device semantic types (T023, T033, T037, T074), comprising approximately 1,270,000 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_medmentions_coarse", "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_major_concepts_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 complains of pustules after falling from stairs. Also, she has a history of quadriceps tendon rupture. She also had a fracture of the tibia and bruising of the knee."]]).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_medmentions_coarse", "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_major_concepts_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 complains of pustules after falling from stairs. Also, she has a history of quadriceps tendon rupture. She also had a fracture of the tibia and bruising of the knee."]]).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_medmentions_coarse", "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_major_concepts_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 complains of pustules after falling from stairs. Also, she has a history of quadriceps tendon rupture. She also had a fracture of the tibia and bruising of the knee.").toDF("text")
val result = mapperPipeline.fit(data).transform(data)

Results

| ner_chunk                 | umls_code   |
|:--------------------------|:------------|
| pustules                  | C0241157    |
| stairs                    | C4300351    |
| quadriceps tendon rupture | C0263968    |
| fracture                  | C0016658    |
| tibia                     | C0040184    |
| knee                      | C0022742    |

Model Information

Model Name: umls_major_concepts_mapper
Compatibility: Healthcare NLP 6.4.0+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 45.1 MB