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_ner_chunk_filter = RENerChunksFilter()\
.setInputCols(["ner_chunk", "dependencies"])\
.setOutputCol("re_ner_chunk")\
.setMaxSyntacticDistance(10)\
.setRelationPairs(["Biomarker-Biomarker_Result", "Biomarker_Result-Biomarker", "Oncogene-Biomarker_Result", "Biomarker_Result-Oncogene", "Pathology_Test-Pathology_Result", "Pathology_Result-Pathology_Test"])
re_model = RelationExtractionDLModel.pretrained("redl_oncology_test_result_biobert_wip", "en", "clinical/models")\
.setInputCols(["re_ner_chunk", "sentence"])\
.setOutputCol("relation_extraction")
pipeline = Pipeline(stages=[document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner,
ner_converter,
pos_tagger,
dependency_parser,
re_ner_chunk_filter,
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_ner_chunk_filter = new RENerChunksFilter()
.setInputCols("ner_chunk", "dependencies")
.setOutputCol("re_ner_chunk")
.setMaxSyntacticDistance(10)
.setRelationPairs(Array("Biomarker-Biomarker_Result", "Biomarker_Result-Biomarker", "Oncogene-Biomarker_Result", "Biomarker_Result-Oncogene", "Pathology_Test-Pathology_Result", "Pathology_Result-Pathology_Test"))
val re_model = RelationExtractionDLModel.pretrained("redl_oncology_test_result_biobert_wip", "en", "clinical/models")
.setPredictionThreshold(0.5f)
.setInputCols("re_ner_chunk", "sentence")
.setOutputCol("relation_extraction")
val pipeline = new Pipeline().setStages(Array(document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner,
ner_converter,
pos_tagger,
dependency_parser,
re_ner_chunk_filter,
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_biobert").predict("""Pathology showed tumor cells, which were positive for estrogen and progesterone receptors.""")
Results
| chunk1 | entity1 | chunk2 | entity2 | relation | confidence |
|-------- |----------------- |----------------------- |---------- |-------------- |----------- |
|positive | Biomarker_Result | estrogen | Biomarker | is_finding_of | 0.99451536 |
|positive | Biomarker_Result | progesterone receptors | Biomarker | is_finding_of | 0.99218905 |
Model Information
| Model Name: | redl_oncology_test_result_biobert_wip |
| Compatibility: | Healthcare NLP 4.1.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 405.4 MB |
References
In-house annotated oncology case reports.
Benchmarking
label recall precision f1
O 0.87 0.92 0.9
is_finding_of 0.93 0.88 0.9
macro-avg 0.90 0.90 0.9