Description
Named Entity recognition annotator allows for a generic model to be trained by utilizing a deep learning algorithm (Char CNNs - BiLSTM - CRF - word embeddings) inspired on a former state of the art model for NER: Chiu & Nicols, Named Entity Recognition with Bidirectional LSTM,CNN. Deidentification NER (Absolute) is a Named Entity Recognition model that annotates text to find protected health information that may need to be deidentified. It detects 7 entities. This ner model is trained with combination of i2b2 train set and augmented version of i2b2 train set using Glove-100d embeddings.
We sticked to official annotation guideline (AG) for 2014 i2b2 Deid challenge while annotating new datasets for this model. All the details regarding the nuances and explanations for AG can be found here https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4978170/
Predicted Entities
DATE, NAME, LOCATION, PROFESSION, CONTACT, AGE, ID
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")
glove_embeddings = WordEmbeddingsModel.pretrained('glove_100d') \
.setInputCols(['sentence', 'token']) \
.setOutputCol('embeddings')
deid_ner = MedicalNerModel.pretrained("ner_deid_generic_glove", "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,
glove_embeddings,
deid_ner,
ner_converter])
model = nlpPipeline.fit(spark.createDataFrame([[""]]).toDF("text"))
results = model.transform(spark.createDataFrame(pd.DataFrame({"text": ["""A. Record date : 2093-01-13, David Hale, M.D., Name : Hendrickson, Ora MR. # 7194334 Date : 01/13/93 PCP : Oliveira, 25 -year-old, Record date : 1-11-2000. Cocke County Baptist Hospital. 0295 Keats Street. Phone +1 (302) 786-5227."""]})))
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 glove_embeddings = WordEmbeddingsModel.pretrained("glove_100d")
.setInputCols(Array("sentence', 'token"))
.setOutputCol("embeddings")
val deid_ner = MedicalNerModel.pretrained("ner_deid_generic_glove", "en", "clinical/models")
.setInputCols(Array("sentence", "token", "embeddings"))
.setOutputCol("ner")
val ner_converter = NerConverter()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
val nlpPipeline = new Pipeline().setStages(Array(
document_assembler,
sentence_detector,
tokenizer,
glove_embeddings,
deid_ner, ner_converter))
val result = nlpPipeline.fit(Seq.empty["A. Record date : 2093-01-13, David Hale, M.D., Name : Hendrickson, Ora MR. # 7194334 Date : 01/13/93 PCP : Oliveira, 25 -year-old, Record date : 1-11-2000. Cocke County Baptist Hospital. 0295 Keats Street. Phone +1 (302) 786-5227."].toDS.toDF("text")).transform(data)
Results
+-----------------------------+---------+
|chunk |ner_label|
+-----------------------------+---------+
|2093-01-13 |DATE |
|David Hale |NAME |
|Hendrickson, Ora |NAME |
|7194334 |ID |
|01/13/93 |DATE |
|Oliveira |NAME |
|25 |AGE |
|1-11-2000 |DATE |
|Cocke County Baptist Hospital|LOCATION |
|0295 Keats Street |LOCATION |
|(302) 786-5227 |CONTACT |
+-----------------------------+---------+
Model Information
| Model Name: | ner_deid_generic_glove |
| Compatibility: | Healthcare NLP 3.0.4+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sentence, token, embeddings] |
| Output Labels: | [ner] |
| Language: | en |
Data Source
A custom data set which is created from the i2b2-PHI train and the augmented version of the i2b2-PHI train set is used.