Description
Assertion status model used to predict if an NER chunk refers to a positive finding from the patient (Present_Or_Past), or if it refers to a family member or another person (SomeoneElse) or if it is mentioned but not as something present (Hypothetical_Or_Absent).
Predicted Entities
Hypothetical_Or_Absent, Present_Or_Past, SomeoneElse
How to use
document_assembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentence_detector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare", "en", "clinical/models")\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer() \
.setInputCols(["sentence"]) \
.setOutputCol("token")
word_embeddings = WordEmbeddingsModel().pretrained("embeddings_clinical", "en", "clinical/models")\
.setInputCols(["sentence", "token"]) \
.setOutputCol("embeddings")
ner = MedicalNerModel.pretrained("ner_vop_emb_clinical", "en", "clinical/models") \
.setInputCols(["sentence", "token", "embeddings"]) \
.setOutputCol("ner")
ner_converter = NerConverterInternal() \
.setInputCols(["sentence", "token", "ner"]) \
.setOutputCol("ner_chunk")
assertion = AssertionDLModel.pretrained("assertion_vop_clinical", "en", "clinical/models") \
.setInputCols(["sentence", "ner_chunk", "embeddings"]) \
.setOutputCol("assertion")
pipeline = Pipeline(stages=[document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner,
ner_converter,
assertion])
data = spark.createDataFrame([["I was feeling anxiety honestly. Can it bring on tremors? It was right after my friend was diagnosed with diabetes."]]).toDF("text")
result = pipeline.fit(data).transform(data)
val document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentence_detector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare", "en", "clinical/models")
.setInputCols("document")
.setOutputCol("sentence")
val tokenizer = new Tokenizer()
.setInputCols("sentence")
.setOutputCol("token")
val word_embeddings = WordEmbeddingsModel().pretrained("embeddings_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "token"))
.setOutputCol("embeddings")
val ner = MedicalNerModel.pretrained("ner_vop_emb_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "token", "embeddings"))
.setOutputCol("ner")
val ner_converter = new NerConverterInternal()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
val assertion = AssertionDLModel.pretrained("assertion_vop_clinical", "en", "clinical/models")
.setInputCols("sentence","ner_chunk","embeddings")
.setOutputCol("assertion")
val pipeline = new Pipeline().setStages(Array(document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner,
ner_converter,
assertion))
val data = Seq("I was feeling anxiety honestly. Can it bring on tremors? It was right after my friend was diagnosed with diabetes.").toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
Results
+--------+-----+---+----------------------+-------+----------------------+----------+
|chunk |begin|end|ner_label |sent_id|assertion |confidence|
+--------+-----+---+----------------------+-------+----------------------+----------+
|anxiety |14 |20 |PsychologicalCondition|0 |Present_Or_Past |0.9853 |
|tremors |48 |54 |Symptom |1 |Hypothetical_Or_Absent|0.9998 |
|diabetes|105 |112|Disease |2 |SomeoneElse |0.9916 |
+--------+-----+---+----------------------+-------+----------------------+----------+
Model Information
| Model Name: | assertion_vop_clinical |
| Compatibility: | Healthcare NLP 5.0.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document, chunk, embeddings] |
| Output Labels: | [assertion] |
| Language: | en |
| Size: | 942.0 KB |
References
In-house annotated health-related text in colloquial language.
Benchmarking
label precision recall f1-score support
Hypothetical_Or_Absent 0.75 0.78 0.76 1265
Present_Or_Past 0.88 0.88 0.88 2873
SomeoneElse 0.92 0.88 0.90 1084
accuracy - - 0.85 5222
macro_avg 0.85 0.85 0.85 5222
weighted_avg 0.86 0.85 0.86 5222