Edit on GitHub
  • John Snow Labs
  • Apr 01, 2021

Detect clinical entities (ner_healthcare_slim)

  • ner
  • clinical
  • licensed
  • de

Description

Detect clinical entities in German text using pretrained NER model

Predicted Entities

TREATMENT, PERSON, BODY_PART, TIME_INFORMATION, MEDICAL_CONDITION

Live Demo 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")
  
embeddings_clinical = WordEmbeddingsModel.pretrained("w2v_cc_300d", "de", "clinical/models")\
    .setInputCols(["sentence", "token"])\
    .setOutputCol("embeddings")

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

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

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

val tokenizer = new Tokenizer()
	.setInputCols("sentence")
	.setOutputCol("token")

val embeddings_clinical = WordEmbeddingsModel.pretrained("w2v_cc_300d", "de", "clinical/models")
    .setInputCols(Array("sentence", "token"))
    .setOutputCol("embeddings")

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

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

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

val result = pipeline.fit(Seq.empty[String]).transform(data)

import nlu
nlu.load("de.med_ner").predict("""Put your text here.""")

Model Information

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