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

Mapping Entities (Drug Substances) with Corresponding UMLS CUI Codes

  • umls
  • chunk_mapper
  • clinical
  • en
  • licensed

Description

This pretrained model maps entities (Drug Substances) with their 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_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_drug_substance_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([["""The patient was given  metformin, lenvatinib and gallopamil 50 MG Oral Tablet."""]]).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_drug_substance_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([["""The patient was given  metformin, lenvatinib and gallopamil 50 MG Oral Tablet."""]]).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_posology_greedy", "en", "clinical/models")
      .setInputCols(Array("sentence", "token", "embeddings"))
      .setOutputCol("clinical_ner")

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

val chunkerMapper = ChunkMapperModel
      .pretrained("umls_drug_substance_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("""The patient was given  metformin, lenvatinib and gallopamil 50 MG Oral Tablet.""").toDF("text")

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

Results

+----------------------------+---------+
|ner_chunk                   |umls_code|
+----------------------------+---------+
|metformin                   |C0025598 |
|lenvatinib                  |C2986924 |
|gallopamil 50 MG Oral Tablet|C0787234 |
+----------------------------+---------+

Model Information

Model Name: umls_drug_substance_mapper
Compatibility: Healthcare NLP 6.0.2+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 44.1 MB

References

2025AA UMLS dataset’s Clinical Drug, Pharmacologic Substance, Antibiotic, Hazardous or Poisonous Substance categories. https://www.nlm.nih.gov/research/umls/index.html