Pipeline to Mapping Entities (Disease or Syndrome) with Corresponding UMLS CUI Codes

Description

This pretrained pipeline is built on the top of umls_disease_syndrome_mapper model and maps entities (Disease or Syndrome) with corresponding UMLS CUI codes.

Live Demo Open in Colab Download Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline

pipeline = PretrainedPipeline("umls_disease_syndrome_mapping", "en", "clinical/models")

sample_text = """ A 35-year-old male with a history of obesity and gestational diabetes mellitus and acyclovir allergy."""

result = pipeline.transform(spark.createDataFrame([[sample_text]]).toDF("text"))

from johnsnowlabs import nlp, medical

pipeline = nlp.PretrainedPipeline("umls_disease_syndrome_mapping", "en", "clinical/models")

sample_text = """ A 35-year-old male with a history of obesity and gestational diabetes mellitus and acyclovir allergy."""

result = pipeline.transform(spark.createDataFrame([[sample_text]]).toDF("text"))

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

val pipeline = PretrainedPipeline("umls_disease_syndrome_mapping", "en", "clinical/models")

val sample_text = """ A 35-year-old male with a history of obesity and gestational diabetes mellitus and acyclovir allergy."""

val result = pipeline.transform(spark.createDataFrame([[sample_text]]).toDF("text"))

Results

| chunk                         | umls_code |
| :---------------------------- | :-------- |
| obesity                       | C0028754  |
| gestational diabetes mellitus | C0085207  |
| acyclovir allergy             | C0571297  |

Model Information

Included Models

• DocumentAssembler
• SentenceDetector
• TokenizerModel
• WordEmbeddingsModel
• MedicalNerModel
• NerConverterInternalModel
• ChunkMapperModel