Mapping Entities (Clinical Drugs) with Corresponding UMLS CUI Codes

Description

This pretrained model maps entities (Clinical Drugs) with their corresponding UMLS CUI codes.

Predicted Entities

umls_code

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", "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().setStages([
        document_assembler,
        sentence_detector,
        tokenizer, 
        word_embeddings,
        ner_model, 
        ner_model_converter, 
        chunkerMapper])


sample_text="""She was immediately given hydrogen peroxide 30 mg, and has been advised Neosporin Cream for 5 days. 
               She has a history of taking magnesium hydroxide 100mg/1ml and metformin 1000 mg."""

test_data = spark.createDataFrame([[sample_text]]).toDF("text")
result = mapper_pipeline.fit(test_data).transform(test_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", "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_clinical_drugs_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 test_data = Seq("She was immediately given hydrogen peroxide 30 mg, and has been advised Neosporin Cream for 5 days. She has a history of taking magnesium hydroxide 100mg/1ml and metformin 1000 mg.").toDF("text")

val result = pipeline.fit(test_data).transform(test_data) 

Results

+-------------------+---------+
|ner_chunk          |umls_code|
+-------------------+---------+
|hydrogen peroxide  |C0020281 |
|Neosporin Cream    |C0132149 |
|magnesium hydroxide|C0024476 |
|metformin          |C0025598 |
+-------------------+---------+

Model Information

Model Name: umls_clinical_drugs_mapper
Compatibility: Healthcare NLP 4.0.0+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 23.3 MB

References

2022AA UMLS dataset’s Clinical Drug category. https://www.nlm.nih.gov/research/umls/index.html