Description
Using this relation extraction model, four relation types can be identified: is_date_of (between date entities and other clinical entities), is_size_of (between Tumor_Finding and Tumor_Size), is_location_of (between anatomical entities and other entities) and is_finding_of (between test entities and their results).
Predicted Entities
is_size_of, is_finding_of, is_date_of, is_location_of, O
Live Demo Open in Colab Copy S3 URI
How to use
Use realation pairs to include only the combinations of entities that are relevant in your case.
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_granular_wip", "en", "clinical/models") \
.setInputCols(["embeddings", "pos_tags", "ner_chunk", "dependencies"]) \
.setOutputCol("relation_extraction") \
.setRelationPairs(["Tumor_Finding-Tumor_Size", "Tumor_Size-Tumor_Finding", "Cancer_Surgery-Relative_Date", "Relative_Date-Cancer_Surgery"]) \
.setMaxSyntacticDistance(10)
pipeline = Pipeline(stages=[document_assembler,
sentence_detector,
tokenizer,
word_embeddings,
ner,
ner_converter,
pos_tagger,
dependency_parser,
re_model])
data = spark.createDataFrame([["A mastectomy was performed two months ago, and a 3 cm mass was extracted."]]).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_granular_wip", "en", "clinical/models")
.setInputCols(Array("embeddings", "pos_tags", "ner_chunk", "dependencies"))
.setOutputCol("relation_extraction")
.setRelationPairs(Array("Tumor_Finding-Tumor_Size", "Tumor_Size-Tumor_Finding", "Cancer_Surgery-Relative_Date", "Relative_Date-Cancer_Surgery"))
.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("A mastectomy was performed two months ago, and a 3 cm mass was extracted.").toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.relation.oncology_granular_wip").predict("""A mastectomy was performed two months ago, and a 3 cm mass was extracted.""")
Results
chunk1 entity1 chunk2 entity2 relation confidence
mastectomy Cancer_Surgery two months ago Relative_Date is_date_of 0.91336143
3 cm Tumor_Size mass Tumor_Finding is_size_of 0.96745735
Model Information
| Model Name: | re_oncology_granular_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: | 267.2 KB |
References
In-house annotated oncology case reports.
Benchmarking
relation recall precision f1
is_size_of 0.96 0.73 0.83
O 0.67 0.93 0.78
is_finding_of 0.94 0.75 0.83
is_date_of 0.94 0.54 0.69
is_location_of 0.94 0.81 0.87
macro-avg 0.89 0.75 0.80