Pipeline to Mapping Entities (Major Clinical Concepts) with Corresponding UMLS CUI Codes

Description

This pretrained pipeline is built on the top of umls_major_concepts_mapper model and maps entities (Major Clinical Concepts) 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_major_concepts_mapping", "en", "clinical/models")

sample_text = """ The patient complains of pustules after falling from stairs. Also,  she has a history of quadriceps tendon rupture."""

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

from johnsnowlabs import nlp, medical

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

sample_text = """ The patient complains of pustules after falling from stairs. Also,  she has a history of quadriceps tendon rupture."""

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

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

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

val sample_text = """ The patient complains of pustules after falling from stairs. Also,  she has a history of quadriceps tendon rupture."""

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

Results

| chunk                     | umls_code |
| :------------------------ | :-------- |
| pustules                  | C0241157  |
| stairs                    | C4300351  |
| quadriceps tendon rupture | C0263968  |

Model Information

Included Models

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