Pipeline for Extracting Clinical Entities Related to 4 major categories of UMLS CUI Codes

Description

This pipeline is designed to extract all entities mappable to 4 major categories of UMLS CUI codes.

Copy S3 URI

How to use


from sparknlp.pretrained import PretrainedPipeline

ner_pipeline = PretrainedPipeline("ner_umls_major_concepts_pipeline", "en", "clinical/models")

result = ner_pipeline.annotate("""A female patient got influenza vaccine and one day after she has complains of ankle pain. 
She has only history of gestational diabetes mellitus diagnosed prior to presentation and subsequent type two diabetes mellitus (T2DM).""")


import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

val ner_pipeline = PretrainedPipeline("ner_umls_major_concepts_pipeline", "en", "clinical/models")

val result = ner_pipeline.annotate("""A female patient got influenza vaccine and one day after she has complains of ankle pain. 
She has only history of gestational diabetes mellitus diagnosed prior to presentation and subsequent type two diabetes mellitus (T2DM).""")

Results

|    | chunks                        |   begin |   end | entities     |
|---:|:------------------------------|--------:|------:|:-------------|
|  0 | influenza vaccine             |      21 |    37 | Vaccine_Name |
|  1 | one day after                 |      43 |    55 | RelativeDate |
|  2 | ankle pain                    |      78 |    87 | Symptom      |
|  3 | gestational diabetes mellitus |     115 |   143 | Diabetes     |
|  4 | type two diabetes mellitus    |     192 |   217 | Diabetes     |
|  5 | T2DM                          |     220 |   223 | Diabetes     |

Model Information

Model Name: ner_umls_major_concepts_pipeline
Type: pipeline
Compatibility: Healthcare NLP 6.0.2+
License: Licensed
Edition: Official
Language: en
Size: 1.7 GB

Included Models

  • DocumentAssembler
  • SentenceDetectorDLModel
  • TokenizerModel
  • WordEmbeddingsModel
  • MedicalNerModel
  • NerConverterInternalModel