Description
Assign assertion status to clinical entities.
How to use
# Test classifier in Spark NLP pipeline
document_assembler = DocumentAssembler()\
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer()\
.setInputCols(["document"]) \
.setOutputCol("token")
# Load newly trained classifier
assertion_classifier = MedicalBertForSequenceClassification\
.pretrained("AssertionBertForSequence_i2b2_3label", "en", "clinical/models")\
.setInputCols(["document", "token"])\
.setOutputCol("prediction")
pipeline = Pipeline(stages=[
document_assembler,
tokenizer,
assertion_classifier
])
# Generating example
data = spark.createDataFrame(["he was begun on physical therapy but remained agitated .",
"there were no meatal blood ."], StringType()).toDF("text")
result = pipeline.fit(data).transform(data)
# Checking results
result.select("text", "prediction.result").show(truncate=False)
# Test classifier in Spark NLP pipeline
document_assembler = nlp.DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = nlp.Tokenizer() \
.setInputCols(["document"]) \
.setOutputCol("token")
# Load newly trained classifier
assertion_classifier = medical.BertForSequenceClassification\
.pretrained("AssertionBertForSequence_i2b2_3label", "en", "clinical/models")\
.setInputCols(["document", "token"])\
.setOutputCol("prediction")
pipeline = nlp.Pipeline(stages=[
document_assembler,
tokenizer,
assertion_classifier
])
# Generating example
data = spark.createDataFrame(["he was begun on physical therapy but remained agitated .",
"there were no meatal blood ."], StringType()).toDF("text")
result = pipeline.fit(data).transform(data)
val documenter = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols("sentences")
.setOutputCol("token")
val assertion_classifier = MedicalBertForSequenceClassification
.pretrained("AssertionBertForSequence_i2b2_3label", "en", "clinical/models")
.setInputCols(Array("document", "token"))
.setOutputCol("prediction")
val pipeline = new Pipeline().setStages(Array(documenter, tokenizer, assertion_classifier))
val data = Seq(Array("he was begun on physical therapy but remained agitated .",
"there were no meatal blood .")).toDF("text")
val result = pipeline.fit(data).transform(data)
Results
+----------------------------------------------------------------+-------+
|text |result |
+----------------------------------------------------------------+-------+
|he was begun on physical therapy but remained agitated . |present|
|there were no meatal blood . |absent |
+----------------------------------------------------------------+-------+
Model Information
| Model Name: | AssertionBertForSequence_i2b2_3label |
| Compatibility: | Healthcare NLP 5.5.2+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [assertion_class] |
| Language: | en |
| Size: | 406.3 MB |
| Case sensitive: | false |
| Max sentence length: | 512 |