Temporal relations for clinical events - enriched

Description

This model can be used to identify temporal relationships among clinical events.

Included Relations

BEFORE, AFTER, SIMULTANEOUS, BEGUN_BY, ENDED_BY, DURING, BEFORE_OVERLAP

Open in ColabDownload

How to use

Use as part of an nlp pipeline with the following stages: DocumentAssembler, SentenceDetector, Tokenizer, PerceptronModel, DependencyParserModel, WordEmbeddingsModel, NerDLModel, NerConverter, RelationExtractionModel.


clinical_re_Model = RelationExtractionModel()\
    .pretrained("re_temporal_events_enriched_clinical", "en", 'clinical/models')\
    .setInputCols(["embeddings", "pos_tags", "ner_chunks", "dependencies"])\
    .setOutputCol("relations")\
    .setMaxSyntacticDistance(4)\ #default: 0
    
nlp_pipeline = Pipeline(stages=[document_assembler, sentence_detector, tokenizer, pos_tagger, dependecy_parser, word_embeddings, clinical_ner, ner_converter, clinical_re_Model])

light_pipeline = LightPipeline(nlp_pipeline.fit(spark.createDataFrame([['']]).toDF("text")))

annotations = light_pipeline.fullAnnotate("""The patient is a 56-year-old right-handed female with longstanding intermittent right low back pain, who was involved in a motor vehicle accident in September of 2005. At that time, she did not notice any specific injury, but five days later, she started getting abnormal right low back pain.""")

Results

+----+------------+-----------+-----------------+---------------+-----------------------------------------------+------------+-----------------+---------------+--------------------------+--------------+
|    | relation   | entity1   |   entity1_begin |   entity1_end | chunk1                                        | entity2    |   entity2_begin |   entity2_end | chunk2                   |   confidence |
+====+============+===========+=================+===============+===============================================+============+=================+===============+==========================+==============+
|  0 | OVERLAP    | PROBLEM   |              54 |            98 | longstanding intermittent right low back pain | OCCURRENCE |             121 |           144 | a motor vehicle accident |     0.532308 |
+----+------------+-----------+-----------------+---------------+-----------------------------------------------+------------+-----------------+---------------+--------------------------+--------------+
|  1 | AFTER      | DATE      |             171 |           179 | that time                                     | PROBLEM    |             201 |           219 | any specific injury      |     0.577288 |
+----+------------+-----------+-----------------+---------------+-----------------------------------------------+------------+-----------------+---------------+--------------------------+--------------+

Model Information

Model Name: re_temporal_events_enriched_clinical
Type: re
Compatibility: Spark NLP for Healthcare 2.6.0 +
Edition: Official
License: Licensed
Input Labels: [embeddings, pos_tags, ner_chunks, dependencies]
Output Labels: [relations]
Language: [en]
Case sensitive: false