Edit on GitHub
  • John Snow Labs
  • Jun 22, 2025

Mapping Entities (Disease or Syndrome) with Corresponding UMLS CUI Codes

  • umls
  • chunk_mapper
  • clinical
  • licensed
  • en

Description

This pretrained model maps entities (Disease or Syndrome) with corresponding UMLS CUI codes.

Predicted Entities

umls_code

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_disease_syndrome_mapper", "en", "clinical/models")\
      .setInputCols(["ner_chunk"])\
      .setOutputCol("mappings")\
      .setRels(["umls_code"])\
      .setLowerCase(True)

mapper_pipeline = Pipeline().setStages([
        document_assembler,
        sentence_detector,
        tokenizer, 
        word_embeddings,
        ner_model, 
        ner_model_converter, 
        chunkerMapper])

data = spark.createDataFrame([["""A 35-year-old male with a history of obesity and gestational diabetes mellitus and acyclovir allergy."""]]).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_disease_syndrome_mapper", "en", "clinical/models")\
      .setInputCols(["ner_chunk"])\
      .setOutputCol("mappings")\
      .setRels(["umls_code"])\
      .setLowerCase(True)

mapper_pipeline = nlp.Pipeline().setStages([
        document_assembler,
        sentence_detector,
        tokenizer, 
        word_embeddings,
        ner_model, 
        ner_model_converter, 
        chunkerMapper])

data = spark.createDataFrame([["""A 35-year-old male with a history of obesity and gestational diabetes mellitus and acyclovir allergy."""]]).toDF("text")

result = mapper_pipeline.fit(data).transform(data)

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

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

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

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

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

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

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

val mapper_pipeline = new Pipeline().setStages(Array(
                                                   document_assembler,
                                                   sentence_detector,
                                                   tokenizer, 
                                                   word_embeddings,
                                                   ner_model, 
                                                   ner_model_converter, 
                                                   chunkerMapper))

val data = Seq("""A 35-year-old male with a history of obesity and gestational diabetes mellitus and acyclovir allergy.""").toDF("text")

val result = mapper_pipeline.fit(data).transform(data)

Results

+-----------------------------+---------+
|ner_chunk                    |umls_code|
+-----------------------------+---------+
|obesity                      |C0028754 |
|gestational diabetes mellitus|C0085207 |
|acyclovir allergy            |C0571297 |
+-----------------------------+---------+

Model Information

Model Name: umls_disease_syndrome_mapper
Compatibility: Healthcare NLP 6.0.2+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 14.8 MB

References

Trained on concepts from disease syndrome for the 2025AA release of the Unified Medical Language System® (UMLS) Knowledge Sources: https://www.nlm.nih.gov/research/umls/index.html