Description
This model is a BioBERT based classifier that can identify texts that mention a HCP consult.
Predicted Entities
Consulted_By_HCP, Other
How to use
document_assembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols(["document"]) \
.setOutputCol("token")
sequence_classifier = MedicalBertForSequenceClassification.pretrained("bert_sequence_classifier_vop_hcp_consult_onnx", "en", "clinical/models")\
.setInputCols(["document", "token"])\
.setOutputCol("class")
pipeline = Pipeline(stages=[
document_assembler,
tokenizer,
sequence_classifier
])
data = spark.createDataFrame(["hi does anybody have feet aches with anxiety, i do suffer from anxiety but never had anything wrong with my feet before",
"My son has been to two doctors who gave him antibiotic drops but they also say the problem might related to allergies."], StringType()).toDF("text")
model = pipeline.fit(data)
result = model.transform(data)
document_assembler = nlp.DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = nlp.Tokenizer() \
.setInputCols(["document"]) \
.setOutputCol("token")
sequenceClassifier = medical.BertForSequenceClassification.pretrained("bert_sequence_classifier_vop_hcp_consult_onnx", "en", "clinical/models")\
.setInputCols(["document","token"])\
.setOutputCol("classes")
pipeline = nlp.Pipeline(stages=[
document_assembler,
tokenizer,
sequenceClassifier
])
data = spark.createDataFrame(["hi does anybody have feet aches with anxiety, i do suffer from anxiety but never had anything wrong with my feet before",
"My son has been to two doctors who gave him antibiotic drops but they also say the problem might related to allergies."], StringType()).toDF("text")
model = pipeline.fit(data)
result = model.transform(data)
val document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols(Array("document"))
.setOutputCol("token")
val sequenceClassifier = MedicalBertForSequenceClassification.pretrained("bert_sequence_classifier_vop_hcp_consult_onnx", "en", "clinical/models")
.setInputCols(Array("document","token"))
.setOutputCol("class")
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, sequenceClassifier))
val data = Seq(Array("hi does anybody have feet aches with anxiety, i do suffer from anxiety but never had anything wrong with my feet before",
"My son has been to two doctors who gave him antibiotic drops but they also say the problem might related to allergies.")).toDF("text")
val model = pipeline.fit(data)
val result = model.transform(data)
Results
+-----------------------------------------------------------------------------------------------------------------------+------------------+
|text |result |
+-----------------------------------------------------------------------------------------------------------------------+------------------+
|hi does anybody have feet aches with anxiety, i do suffer from anxiety but never had anything wrong with my feet before|[Other] |
|My son has been to two doctors who gave him antibiotic drops but they also say the problem might related to allergies. |[Consulted_By_HCP]|
+-----------------------------------------------------------------------------------------------------------------------+------------------+
Model Information
| Model Name: | bert_sequence_classifier_vop_hcp_consult_onnx |
| Compatibility: | Healthcare NLP 6.1.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [label] |
| Language: | en |
| Size: | 437.7 MB |
| Case sensitive: | true |