Description
This model detects the assertion status of entities related to response to treatment. The model identifies positive mentions (Present_Or_Past status), and hypothetical or absent mentions (Hypothetical_Or_Absent status).
Predicted Entities
Hypothetical_Or_Absent, Present_Or_Past
Live Demo Open in Colab Copy S3 URI
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_oncology_wip", "en", "clinical/models") \
.setInputCols(["sentence", "token", "embeddings"]) \
.setOutputCol("ner")
ner_converter = NerConverter() \
.setInputCols(["sentence", "token", "ner"]) \
.setOutputCol("ner_chunk")\
.setWhiteList(["Response_To_Treatment"])
assertion = AssertionDLModel.pretrained("assertion_oncology_response_to_treatment_wip", "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([["The patient presented no evidence of recurrence."]]).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(Array("document"))
.setOutputCol("sentence")
val tokenizer = new Tokenizer()
.setInputCols(Array("sentence"))
.setOutputCol("token")
val word_embeddings = WordEmbeddingsModel().pretrained("embeddings_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "token"))
.setOutputCol("embeddings")
val ner = MedicalNerModel.pretrained("ner_oncology_wip", "en", "clinical/models")
.setInputCols(Array("sentence", "token", "embeddings"))
.setOutputCol("ner")
val ner_converter = new NerConverter()
.setInputCols(Array("sentence", "token", "ner"))
.setOutputCol("ner_chunk")
.setWhiteList(Array("Response_To_Treatment"))
val clinical_assertion = AssertionDLModel.pretrained("assertion_oncology_response_to_treatment_wip","en","clinical/models")
.setInputCols(Array("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("""The patient presented no evidence of recurrence.""").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.assert.oncology_response_to_treatment_wip").predict("""The patient presented no evidence of recurrence.""")
Results
| chunk | ner_label | assertion |
|:-----------|:----------------------|:-----------------------|
| recurrence | Response_To_Treatment | Hypothetical_Or_Absent |
Model Information
| Model Name: | assertion_oncology_response_to_treatment_wip |
| Compatibility: | Healthcare NLP 4.1.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document, chunk, embeddings] |
| Output Labels: | [assertion_pred] |
| Language: | en |
| Size: | 1.4 MB |
References
In-house annotated oncology case reports.
Benchmarking
label precision recall f1-score support
Hypothetical_Or_Absent 0.83 0.96 0.89 46.0
Present_Or_Past 0.94 0.79 0.86 43.0
macro-avg 0.89 0.87 0.87 89.0
weighted-avg 0.89 0.88 0.88 89.0