Pipeline to Mapping LOINC Codes with Their Corresponding UMLS Codes

Description

This pretrained pipeline is built on the top of loinc_umls_mapper model and maps LOINC codes to corresponding UMLS codes.

Copy S3 URI

How to use


from sparknlp.pretrained import PretrainedPipeline

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

sample_text = """ [['LA26702-3'], ['LP99998-4']]"""

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


from johnsnowlabs import nlp, medical

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

sample_text = """ [['LA26702-3'], ['LP99998-4']]"""

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


import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

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

val sample_text = """ [['LA26702-3'], ['LP99998-4']]"""

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

Results


| loinc_code | umls_code |
| :--------- | :-------- |
| LA26702-3  | C0004057  |
| LP99998-4  | C0050078  |

Model Information

Model Name: loinc_umls_mapping
Type: pipeline
Compatibility: Healthcare NLP 6.3.0+
License: Licensed
Edition: Official
Language: en
Size: 3.4 MB

Included Models

  • DocumentAssembler
  • Doc2Chunk
  • ChunkMapperModel