Detect posology entities (large-biobert)

Description

Detect Drug, Dosage and administration instructions in text using pretraiend NER model.

Predicted Entities

DOSAGE, DRUG, STRENGTH, FORM, DURATION, FREQUENCY, ROUTE

Live Demo Open in Colab Copy S3 URI

How to use

document_assembler = DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")
         
sentence_detector = SentenceDetector()\
    .setInputCols(["document"])\
    .setOutputCol("sentence")

embeddings_clinical = BertEmbeddings.pretrained("biobert_pubmed_base_cased")\
    .setInputCols(["sentence", "token"])\
    .setOutputCol("embeddings")

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

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

nlpPipeline = Pipeline(stages=[document_assembler, sentence_detector, tokenizer, embeddings_clinical, clinical_ner, ner_converter])

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

results = model.transform(spark.createDataFrame([["EXAMPLE_TEXT"]]).toDF("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 embeddings_clinical = BertEmbeddings.pretrained("biobert_pubmed_base_cased")
    .setInputCols(Array("sentence", "token"))
    .setOutputCol("embeddings")

val ner = MedicalNerModel.pretrained("ner_posology_large_biobert", "en", "clinical/models")
    .setInputCols(Array("sentence", "token", "embeddings"))
    .setOutputCol("ner")

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

val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, tokenizer, embeddings_clinical, ner, ner_converter))

val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.med_ner.posology.large_biobert").predict("""Put your text here.""")

Model Information

Model Name: ner_posology_large_biobert
Compatibility: Healthcare NLP 3.0.0+
License: Licensed
Edition: Official
Input Labels: [sentence, token, embeddings]
Output Labels: [ner]
Language: en