Description
This model is a BioBERT based classifier that can classify patients non-adherent to their treatments and their reasons on Twitter.
Predicted Entities
negative, positive
Live Demo Open in Colab Copy S3 URI
How to use
document_assembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')
tokenizer = Tokenizer() \
.setInputCols(['document']) \
.setOutputCol('token')
sequenceClassifier = MedicalBertForSequenceClassification.pretrained("bert_sequence_classifier_treatment_changes_sentiment_tweet", "en", "clinical/models")\
.setInputCols(["document",'token'])\
.setOutputCol("class")
pipeline = Pipeline(stages=[
document_assembler,
tokenizer,
sequenceClassifier
])
data = spark.createDataFrame(["I love when they say things like this. I took that ambien instead of my thyroid pill.",
"I am a 30 year old man who is not overweight but is still on the verge of needing a Lipitor prescription."], StringType()).toDF("text")
result = pipeline.fit(data).transform(data)
result.select("text", "class.result").show(truncate=False)
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_treatment_changes_sentiment_tweet", "en", "clinical/models")
.setInputCols(Array("document","token"))
.setOutputCol("class")
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, sequenceClassifier))
val data = Seq(Array("I love when they say things like this. I took that ambien instead of my thyroid pill.",
"I am a 30 year old man who is not overweight but is still on the verge of needing a Lipitor prescription.")).toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.classify.bert_sequence.treatment_sentiment_tweets").predict("""I am a 30 year old man who is not overweight but is still on the verge of needing a Lipitor prescription.""")
Results
+---------------------------------------------------------------------------------------------------------+----------+
|text |result |
+---------------------------------------------------------------------------------------------------------+----------+
|I love when they say things like this. I took that ambien instead of my thyroid pill. |[positive]|
|I am a 30 year old man who is not overweight but is still on the verge of needing a Lipitor prescription.|[negative]|
+---------------------------------------------------------------------------------------------------------+----------+
Model Information
| Model Name: | bert_sequence_classifier_treatment_changes_sentiment_tweet |
| Compatibility: | Healthcare NLP 4.0.2+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [class] |
| Language: | en |
| Size: | 406.5 MB |
| Case sensitive: | true |
| Max sentence length: | 128 |
Benchmarking
label precision recall f1-score support
negative 0.9515 0.9751 0.9632 1368
positive 0.6304 0.4603 0.5321 126
accuracy - - 0.9317 1494
macro-avg 0.7910 0.7177 0.7476 1494
weighted-avg 0.9244 0.9317 0.9268 1494