Detect radiology concepts (ner_radiology_wip_clinical)

Description

Detect clincal concepts from radiology reports and text using pretrained NER model.

Predicted Entities

ImagingFindings, Direction, OtherFindings, Measurements, Score, BodyPart, Medical_Device, Test, ManualFix, Procedure, Disease_Syndrome_Disorder, Test_Result, Imaging_Technique, ImagingTest, Symptom, Units

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")

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

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

clinical_ner = MedicalNerModel.pretrained("ner_radiology_wip_clinical", "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 = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")
    .setInputCols(Array("sentence", "token"))
    .setOutputCol("embeddings")

val ner = MedicalNerModel.pretrained("ner_radiology_wip_clinical", "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.radiology.wip_clinical").predict("""Put your text here.""")

Model Information

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