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

Mapping Entities (Clinical Findings) with Corresponding UMLS CUI Codes

  • en
  • chunk_mapper
  • licensed
  • clinical
  • umls
  • findings

Description

This model maps clinical finding entities extracted by NER to UMLS CUI codes covering the Finding semantic type (T033), comprising 736,075 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_clinical_large", "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_findings_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([["A 28-year-old female with a history of obesity with BMI of 33.5 kg/m2, presented with a one-week history of reduced fatigue. The patient shows tachycardia, cardiomegaly and proteinuria on admission."]]).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_clinical_large", "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_findings_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([["A 28-year-old female with a history of obesity with BMI of 33.5 kg/m2, presented with a one-week history of reduced fatigue. The patient shows tachycardia, cardiomegaly and proteinuria on admission."]]).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_clinical_large", "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_findings_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("A 28-year-old female with a history of obesity with BMI of 33.5 kg/m2, presented with a one-week history of reduced fatigue. The patient shows tachycardia, cardiomegaly and proteinuria on admission.").toDF("text")
val result = mapperPipeline.fit(data).transform(data)

Results

| ner_chunk       | umls_code   |
|:----------------|:------------|
| obesity         | C4759928    |
| BMI             | C0578022    |
| reduced fatigue | C5547024    |
| tachycardia     | C0039231    |
| cardiomegaly    | C0018800    |
| proteinuria     | C0033687    |

Model Information

Model Name: umls_clinical_findings_mapper
Compatibility: Healthcare NLP 6.4.0+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 25.1 MB