NerDLModel Clinical Large

Description

Pretrained named entity recognition deep learning model for clinical terms. The SparkNLP deep learning model (NerDL) is inspired by a former state of the art model for NER: Chiu & Nicols, Named Entity Recognition with Bidirectional LSTM-CNN.

Predicted Entities

Problem, Test, Treatment

Live Demo Open in Colab Download

How to use

Use as part of an nlp pipeline with the following stages: DocumentAssembler, SentenceDetector, Tokenizer, WordEmbeddingsModel, NerDLModel. Add the NerConverter to the end of the pipeline to convert entity tokens into full entity chunks.

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

nlpPipeline = Pipeline(stages=[clinical_ner])

empty_data = spark.createDataFrame([[""]]).toDF("text")

model = nlpPipeline.fit(empty_data)

results = model.transform(data)

val ner = NerDLModel.pretrained("ner_clinical_large", "en", "clinical/models") \
  .setInputCols(["sentence", "token", "embeddings"]) \
  .setOutputCol("ner")

val pipeline = new Pipeline().setStages(Array(ner))

val result = pipeline.fit(Seq.empty[String].toDS.toDF("text")).transform(data)

Results

The output is a dataframe with a sentence per row and a “ner” column containing all of the entity labels in the sentence, entity character indices, and other metadata. To get only the tokens and entity labels, without the metadata, select “token.result” and “ner.result” from your output dataframe:

Model Information

Data Source

Trained on augmented 2010 i2b2 challenge data with ‘embeddings_clinical’. https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/