Relation Extraction Between Dates and Clinical Entities (ReDL)

Description

Identify if tests were conducted on a particular date or any diagnosis was made on a specific date by checking relations between clinical entities and dates. 1 : Shows date and the clinical entity are related, 0 : Shows date and the clinical entity are not related.

Predicted Entities

0, 1

Live Demo Open in Colab Download

How to use

...
documenter = DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")

sentencer = SentenceDetector()\
    .setInputCols(["document"])\
    .setOutputCol("sentences")

tokenizer = sparknlp.annotators.Tokenizer()\
    .setInputCols(["sentences"])\
    .setOutputCol("tokens")

words_embedder = WordEmbeddingsModel()\
    .pretrained("embeddings_clinical", "en", "clinical/models")\
    .setInputCols(["sentences", "tokens"])\
    .setOutputCol("embeddings")

pos_tagger = PerceptronModel()\
    .pretrained("pos_clinical", "en", "clinical/models") \
    .setInputCols(["sentences", "tokens"])\
    .setOutputCol("pos_tags")

events_ner_tagger = MedicalNerModel.pretrained("ner_events_clinical", "en", "clinical/models")\
    .setInputCols("sentences", "tokens", "embeddings")\
    .setOutputCol("ner_tags") 

ner_chunker = NerConverterInternal()\
    .setInputCols(["sentences", "tokens", "ner_tags"])\
    .setOutputCol("ner_chunks")

dependency_parser = DependencyParserModel() \
    .pretrained("dependency_conllu", "en") \
    .setInputCols(["sentences", "pos_tags", "tokens"]) \
    .setOutputCol("dependencies")

events_re_ner_chunk_filter = RENerChunksFilter() \
    .setInputCols(["ner_chunks", "dependencies"])\
    .setOutputCol("re_ner_chunks")

events_re_Model = RelationExtractionDLModel() \
    .pretrained('redl_date_clinical_biobert', "en", "clinical/models")\
    .setPredictionThreshold(0.5)\
    .setInputCols(["re_ner_chunks", "sentences"]) \
    .setOutputCol("relations")

pipeline = Pipeline(stages=[
    documenter,
    sentencer,
    tokenizer, 
    words_embedder, 
    pos_tagger, 
    events_ner_tagger,
    ner_chunker,
    dependency_parser,
    events_re_ner_chunk_filter,
    events_re_Model])

text ="This 73 y/o patient had CT on 1/12/95, with progressive memory and cognitive decline since 8/11/94."

data = spark.createDataFrame([[text]]).toDF("text")

p_model = pipeline.fit(data)

result = p_model.transform(data)
...
val documenter = new DocumentAssembler() 
    .setInputCol("text") 
    .setOutputCol("document")

val sentencer = new SentenceDetector()
    .setInputCols("document")
    .setOutputCol("sentences")

val tokenizer = new Tokenizer()
    .setInputCols("sentences")
    .setOutputCol("tokens")
    
val words_embedder = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")
    .setInputCols(Array("sentence", "token"))
    .setOutputCol("embeddings")

val pos_tagger = PerceptronModel()
    .pretrained("pos_clinical", "en", "clinical/models") 
    .setInputCols(Array("sentences", "tokens"))
    .setOutputCol("pos_tags")

val events_ner_tagger = MedicalNerModel.pretrained("ner_events_clinical", "en", "clinical/models")
    .setInputCols(Array("sentences", "tokens", "embeddings"))
    .setOutputCol("ner_tags")  

val ner_chunker = new NerConverterInternal()
    .setInputCols(Array("sentences", "tokens", "ner_tags"))
    .setOutputCol("ner_chunks")

val dependency_parser = DependencyParserModel()
    .pretrained("dependency_conllu", "en")
    .setInputCols(Array("sentences", "pos_tags", "tokens"))
    .setOutputCol("dependencies")

val events_re_ner_chunk_filter = RENerChunksFilter() 
    .setInputCols(Array("ner_chunks", "dependencies"))
    .setOutputCol("re_ner_chunks")
    
val events_re_Model = RelationExtractionDLModel() 
    .pretrained('redl_date_clinical_biobert', "en", "clinical/models")
    .setPredictionThreshold(0.5)
    .setInputCols(Array("re_ner_chunks", "sentences")) 
    .setOutputCol("relations")

val pipeline = new Pipeline().setStages(Array(documenter,sentencer,tokenizer,words_embedder,pos_tagger,events_ner_tagger,ner_chunker,dependency_parser,events_re_ner_chunk_filter,events_re_Model))

val data = Seq("This 73 y/o patient had CT on 1/12/95, with progressive memory and cognitive decline since 8/11/94.").toDS.toDF("text")

val result = pipeline.fit(data).transform(data)

Results

|   | relations | entity1 | entity1_begin | entity1_end | chunk1                                   | entity2 | entity2_end | entity2_end | chunk2  | confidence |
|---|-----------|---------|---------------|-------------|------------------------------------------|---------|-------------|-------------|---------|------------|
| 0 | 1         | Test    | 24            | 25          | CT                                       | Date    | 31          | 37          | 1/12/95 | 1.0        |
| 1 | 1         | Symptom | 45            | 84          | progressive memory and cognitive decline | Date    | 92          | 98          | 8/11/94 | 1.0        |

Model Information

Model Name: redl_date_clinical_biobert
Compatibility: Spark NLP for Healthcare 3.0.3+
License: Licensed
Edition: Official
Language: en
Case sensitive: true

Data Source

Trained on an internal dataset.

Benchmarking

Relation           Recall Precision        F1   Support
0                   0.738     0.729     0.734        84
1                   0.945     0.947     0.946       416
Avg.                0.841     0.838     0.840        -