Description
This relation extraction model links test extractions to their corresponding results.
Predicted Entities
is_finding_of
, O
Live Demo Open in Colab Copy S3 URI
How to use
Each relevant relation pair in the pipeline should include one test entity (such as Biomarker, Imaging_Test, Pathology_Test or Oncogene) and one result entity (such as Biomarker_Result, Pathology_Result or Tumor_Finding).
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")
pos_tagger = PerceptronModel.pretrained("pos_clinical", "en", "clinical/models") \
.setInputCols(["sentence", "token"]) \
.setOutputCol("pos_tags")
dependency_parser = DependencyParserModel.pretrained("dependency_conllu", "en") \
.setInputCols(["sentence", "pos_tags", "token"]) \
.setOutputCol("dependencies")
re_model = RelationExtractionModel.pretrained("re_oncology_test_result_wip", "en", "clinical/models") \
.setInputCols(["embeddings", "pos_tags", "ner_chunk", "dependencies"]) \
.setOutputCol("relation_extraction") \
.setRelationPairs(["Biomarker-Biomarker_Result", "Biomarker_Result-Biomarker", "Oncogene-Biomarker_Result", "Biomarker_Result-Oncogene", "Pathology_Test-Pathology_Result", "Pathology_Result-Pathology_Test"]) \
.setMaxSyntacticDistance(10)
pipeline = Pipeline(stages=[document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner,
ner_converter,
pos_tagger,
dependency_parser,
re_model])
data = spark.createDataFrame([["Pathology showed tumor cells, which were positive for estrogen and progesterone receptors."]]).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")
val pos_tagger = PerceptronModel.pretrained("pos_clinical", "en", "clinical/models")
.setInputCols(Array("sentence", "token"))
.setOutputCol("pos_tags")
val dependency_parser = DependencyParserModel.pretrained("dependency_conllu", "en")
.setInputCols(Array("sentence", "pos_tags", "token"))
.setOutputCol("dependencies")
val re_model = RelationExtractionModel.pretrained("re_oncology_test_result_wip", "en", "clinical/models")
.setInputCols(Array("embeddings", "pos_tags", "ner_chunk", "dependencies"))
.setOutputCol("relation_extraction")
.setRelationPairs(Array("Biomarker-Biomarker_Result", "Biomarker_Result-Biomarker", "Oncogene-Biomarker_Result", "Biomarker_Result-Oncogene", "Pathology_Test-Pathology_Result", "Pathology_Result-Pathology_Test"))
.setMaxSyntacticDistance(10)
val pipeline = new Pipeline().setStages(Array(document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner,
ner_converter,
pos_tagger,
dependency_parser,
re_model))
val data = Seq("Pathology showed tumor cells, which were positive for estrogen and progesterone receptors.").toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.relation.oncology.test_result").predict("""Pathology showed tumor cells, which were positive for estrogen and progesterone receptors.""")
Results
chunk1 entity1 chunk2 entity2 relation confidence
Pathology Pathology_Test tumor cells Pathology_Result is_finding_of 0.53310496
positive Biomarker_Result estrogen Biomarker is_finding_of 0.9453165
positive Biomarker_Result progesterone receptors Biomarker is_finding_of 0.8816877
Model Information
Model Name: | re_oncology_test_result_wip |
Type: | re |
Compatibility: | Healthcare NLP 4.0.0+ |
License: | Licensed |
Edition: | Official |
Input Labels: | [embeddings, pos_tags, train_ner_chunks, dependencies] |
Output Labels: | [relations] |
Language: | en |
Size: | 266.9 KB |
References
In-house annotated oncology case reports.
Benchmarking
label recall precision f1
O 0.84 0.88 0.86
is_finding_of 0.89 0.85 0.87
macro-avg 0.86 0.86 0.86