Description
Identifies medical conditions that belong to family members rather than the patient.
Predicted Entities
family
How to use
document_assembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentence_detector = SentenceDetector()\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
word_embeddings = WordEmbeddingsModel\
.pretrained("embeddings_clinical", "en", "clinical/models")\
.setInputCols(["sentence", "token"])\
.setOutputCol("embeddings")
clinical_ner = MedicalNerModel\
.pretrained("ner_clinical", "en", "clinical/models")\
.setInputCols(["sentence", "token", "embeddings"])\
.setOutputCol("ner")
ner_converter = NerConverterInternal()\
.setInputCols(["sentence", "token", "ner"])\
.setOutputCol("ner_chunk")
contextual_assertion = ContextualAssertion\
.pretrained("contextual_assertion_family", "en", "clinical/models")\
.setInputCols("sentence", "token", "ner_chunk")\
.setOutputCol("assertion_family")
flattener = Flattener()\
.setInputCols("assertion_family")\
.setExplodeSelectedFields({"assertion_family": ["metadata.ner_chunk as ner_chunk",
"begin as begin",
"end as end",
"metadata.ner_label as ner_label",
"result"]})
pipeline = Pipeline(stages=[
document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
clinical_ner,
ner_converter,
contextual_assertion,
flattener
])
empty_data = spark.createDataFrame([[""]]).toDF("text")
model = pipeline.fit(empty_data)
text = """Father has diabetes and mother had breast cancer. Sister suffers from migraines."""
data = spark.createDataFrame([[text]]).toDF('text')
result = model.transform(data)
document_assembler = nlp.DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentence_detector = nlp.SentenceDetector()\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = nlp.Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
word_embeddings = nlp.WordEmbeddingsModel\
.pretrained("embeddings_clinical", "en", "clinical/models")\
.setInputCols(["sentence", "token"])\
.setOutputCol("embeddings")
clinical_ner = medical.MedicalNerModel\
.pretrained("ner_clinical", "en", "clinical/models")\
.setInputCols(["sentence", "token", "embeddings"])\
.setOutputCol("ner")
ner_converter = medical.NerConverterInternal()\
.setInputCols(["sentence", "token", "ner"])\
.setOutputCol("ner_chunk")
contextual_assertion = medical.ContextualAssertion\
.pretrained("contextual_assertion_family", "en", "clinical/models")\
.setInputCols("sentence", "token", "ner_chunk")\
.setOutputCol("assertion_family")
flattener = medical.Flattener()\
.setInputCols("assertion_family")\
.setExplodeSelectedFields({"assertion_family": ["metadata.ner_chunk as ner_chunk",
"begin as begin",
"end as end",
"metadata.ner_label as ner_label",
"result"]})
pipeline = nlp.Pipeline(stages=[
document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
clinical_ner,
ner_converter,
contextual_assertion,
flattener
])
empty_data = spark.createDataFrame([[""]]).toDF("text")
model = pipeline.fit(empty_data)
text = """Father has diabetes and mother had breast cancer. Sister suffers from migraines."""
data = spark.createDataFrame([[text]]).toDF('text')
result = model.transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentenceDetector = new SentenceDetector()
.setInputCols(Array("document"))
.setOutputCol("sentences")
val tokenizer = new Tokenizer()
.setInputCols(Array("sentences"))
.setOutputCol("tokens")
val embedder = WordEmbeddingsModel
.pretrained("embeddings_clinical", "en", "clinical/models")
.setInputCols(Array("sentences", "tokens"))
.setOutputCol("embeddings")
val nerTagger = MedicalNerModel
.pretrained("ner_clinical", "en", "clinical/models")
.setInputCols(Array("sentences", "tokens", "embeddings"))
.setOutputCol("nerTags")
val nerConverter = new NerConverterInternal()
.setInputCols(Array("sentences", "tokens", "nerTags"))
.setOutputCol("nerChunks")
val contextualAssertion = ContextualAssertion
.pretrained("contextual_assertion_family", "en", "clinical/models")
.setInputCols("sentences", "tokens", "nerChunks")
.setOutputCol("assertion_family")
val flattener = new Flattener()
.setInputCols("assertion_family")
.setExplodeSelectedFields(Map("assertion_family" -> Array(
"metadata.ner_chunk as ner_chunk",
"begin as begin",
"end as end",
"metadata.ner_label as ner_label",
"result as result"
)))
val emptyDataSet = Seq("").toDS().toDF("text")
val pipeline = new Pipeline()
.setStages(Array(
documentAssembler,
sentenceDetector,
tokenizer,
embedder,
nerTagger,
nerConverter,
contextualAssertion,
flattener
)).fit(emptyDataSet)
val text = Seq("""Father has diabetes and mother had breast cancer. Sister suffers from migraines.""").toDS.toDF("text")
val dataSetResult = pipeline.transform(text)
Results
+---------------+-------+-----+-----------+-----------+
|ner_chunk |begin |end |ner_label |result |
+---------------+-------+-----+-----------+-----------+
|diabetes |11 |18 |PROBLEM |family |
|breast cancer |35 |47 |PROBLEM |family |
|migraines |70 |78 |PROBLEM |family |
+---------------+-------+-----+-----------+-----------+
Model Information
| Model Name: | contextual_assertion_family |
| Compatibility: | Healthcare NLP 6.2.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sentence, token, ner_chunk] |
| Output Labels: | [custom_family] |
| Language: | en |
| Size: | 2.3 KB |
| Case sensitive: | false |