Edit on GitHub
  • John Snow Labs
  • Jun 28, 2022

Mapping Drugs With Their Corresponding Actions And Treatments

  • drug
  • action
  • treatment
  • chunk_mapper
  • clinical
  • licensed
  • en

Description

This pretrained model maps drugs with their corresponding action and treatment. action refers to the function of the drug in various body systems, treatment refers to which disease the drug is used to treat.

Predicted Entities

action, treatment

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")

clinical_ner = MedicalNerModel.pretrained("ner_posology_small", "en", "clinical/models")\
.setInputCols(["sentence","token","embeddings"])\
.setOutputCol("ner")\
.setLabelCasing("upper")

ner_converter = NerConverter()\
.setInputCols(["sentence", "token", "ner"])\
.setOutputCol("ner_chunk")\
.setWhiteList(["DRUG"])

chunkerMapper_action = ChunkMapperModel.pretrained("drug_action_treatment_mapper", "en", "clinical/models")\
.setInputCols(["ner_chunk"])\
.setOutputCol("action_mappings")\
.setRels(["action"])\
.setLowerCase(True)

chunkerMapper_treatment = ChunkMapperModel.pretrained("drug_action_treatment_mapper", "en", "clinical/models")\
.setInputCols(["ner_chunk"])\
.setOutputCol("treatment_mappings")\
.setRels(["treatment"])\
.setLowerCase(True)


pipeline = Pipeline().setStages([document_assembler,
sentence_detector,
tokenizer, 
word_embeddings,
clinical_ner, 
ner_converter,
chunkerMapper_action,
chunkerMapper_treatment])


model = pipeline.fit(spark.createDataFrame([[""]]).toDF("text"))

text = """The patient is a 71-year-old female patient of Dr. X. and she was given Aklis, Dermovate, Aacidexam and Paracetamol."""

pipeline = LightPipeline(model)

result = pipeline.fullAnnotate(text)

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

val sentence_detector = new SentenceDetector()
.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 clinical_ner = MedicalNerModel.pretrained("ner_posology_small","en","clinical/models")
.setInputCols(Array("sentence","token","embeddings"))
.setOutputCol("ner")
.setLabelCasing("upper")

val ner_converter = new NerConverter()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
.setWhiteList(Array("DRUG"))

val chunkerMapper_action = ChunkMapperModel.pretrained("drug_action_treatment_mapper", "en", "clinical/models")
.setInputCols(Array("ner_chunk"))
.setOutputCol("action_mappings")
.setRels(Array("action"))
.setLowerCase(True)

val chunkerMapper_treatment = ChunkMapperModel.pretrained("drug_action_treatment_mapper", "en", "clinical/models")
.setInputCols(Array("ner_chunk"))
.setOutputCol("treatment_mappings")
.setRels(Array("treatment"))
.setLowerCase(True)


val pipeline = new Pipeline().setStages(Array(
document_assembler,
sentence_detector,
tokenizer, 
word_embeddings,
clinical_ner, 
ner_converter,
chunkerMapper_action,
chunkerMapper_treatment))




val data = Seq("""The patient is a 71-year-old female patient of Dr. X. and she was given Aklis, Dermovate, Aacidexam and Paracetamol.""").toDS.toDF("text")

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

import nlu
nlu.load("en.map_entity.drug_to_action_treatment").predict("""The patient is a 71-year-old female patient of Dr. X. and she was given Aklis, Dermovate, Aacidexam and Paracetamol.""")

Results

+-----------+--------------------+-------------------+------------------------------------------------------------+-----------------------------------------------------------------------------+
|Drug       |action_mappings     |treatment_mappings |action_meta                                                 |treatment_meta                                                               |
+-----------+--------------------+-------------------+------------------------------------------------------------+-----------------------------------------------------------------------------+
|Aklis      |cardioprotective    |hyperlipidemia     |hypotensive:::natriuretic                                   |hypertension:::diabetic kidney disease:::cerebrovascular accident:::smoking  |
|Dermovate  |anti-inflammatory   |lupus              |corticosteroids::: dermatological preparations:::very strong|discoid lupus erythematosus:::empeines:::psoriasis:::eczema                  |
|Aacidexam  |antiallergic        |abscess            |antiexudative:::anti-inflammatory:::anti-shock              |brain abscess:::agranulocytosis:::adrenogenital syndrome                     |
|Paracetamol|analgesic           |arthralgia         |anti-inflammatory:::antipyretic:::pain reliever             |period pain:::pain:::sore throat:::headache:::influenza:::toothache          |   
+-----------+--------------------+-------------------+------------------------------------------------------------+-----------------------------------------------------------------------------+

Model Information

Model Name: drug_action_treatment_mapper
Compatibility: Healthcare NLP 3.5.3+
License: Licensed
Edition: Official
Input Labels: [ner_chunk]
Output Labels: [mappings]
Language: en
Size: 8.4 MB