Edit on GitHub
  • John Snow Labs
  • Jun 20, 2024

Mapping Entities with Corresponding RxNorm Codes

  • rxnorm
  • chunk_mapper
  • en
  • licensed
  • clinical

Description

This pretrained model maps entities with their corresponding RxNorm codes.

Predicted Entities

RxNorm Codes

Open in Colab Copy S3 URI

How to use

document_assembler = DocumentAssembler()\
.setInputCol('text')\
.setOutputCol('document')

sentence_detector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare", "en", "clinical/models")\
    .setInputCols(["document"])\
    .setOutputCol("sentence")

tokenizer = Tokenizer()\
    .setInputCols("sentence")\
    .setOutputCol("token")

word_embeddings = WordEmbeddingsModel\
    .pretrained("embeddings_clinical", "en", "clinical/models")\
    .setInputCols(["sentence", "token"])\
    .setOutputCol("embeddings")

posology_ner_model = MedicalNerModel\
    .pretrained("ner_posology_greedy", "en", "clinical/models")\
    .setInputCols(["sentence", "token", "embeddings"])\
    .setOutputCol("posology_ner")

posology_ner_converter = NerConverterInternal()\
    .setInputCols("sentence", "token", "posology_ner")\
    .setOutputCol("ner_chunk")

chunkerMapper = ChunkMapperModel\
    .pretrained("rxnorm_mapper", "en", "clinical/models")\
    .setInputCols(["ner_chunk"])\
    .setOutputCol("mappings")\
    .setRels(["rxnorm_code"])

mapper_pipeline = Pipeline().setStages([
document_assembler,
sentence_detector,
tokenizer, 
word_embeddings,
posology_ner_model, 
posology_ner_converter, 
chunkerMapper])


test_data = spark.createDataFrame([["The patient was given Zyrtec 10 MG, Adapin 10 MG Oral Capsule, Septi-Soothe 0.5 Topical Spray"]]).toDF("text")

mapper_model = mapper_pipeline.fit(test_data)

result= mapper_model.transform(test_data)

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

val sentence_detector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")
    .setInputCols("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 posology_ner_model = MedicalNerModel
    .pretrained("ner_posology_greedy", "en", "clinical/models")
    .setInputCols(Array("sentence", "token", "embeddings"))
    .setOutputCol("posology_ner")

val posology_ner_converter = new NerConverterInternal()
    .setInputCols("sentence", "token", "posology_ner")
    .setOutputCol("ner_chunk")

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

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


val data = Seq("The patient was given Zyrtec 10 MG, Adapin 10 MG Oral Capsule, Septi-Soothe 0.5 Topical Spray").toDS.toDF("text")

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

import nlu
nlu.load("en.map_entity.rxnorm_resolver").predict("""The patient was given Zyrtec 10 MG, Adapin 10 MG Oral Capsule, Septi-Soothe 0.5 Topical Spray""")

Results

+------------------------------+-----------+
|ner_chunk                     |rxnorm_code|
+------------------------------+-----------+
|Zyrtec 10 MG                  |1011483    |
|Adapin 10 MG Oral Capsule     |1000050    |
|Septi-Soothe 0.5 Topical Spray|1000046    |
+------------------------------+-----------+

Model Information

Model Name: rxnorm_mapper
Compatibility: Healthcare NLP 5.3.3+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 10.5 MB