MeSH to UMLS Code Mapping

Description

This pretrained pipeline maps MeSH codes to UMLS codes without using any text data. You’ll just feed white space-delimited MeSH codes and it will return the corresponding UMLS codes as a list. If there is no mapping, the original code is returned with no mapping.

Live Demo Open in Colab Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline 
pipeline = PretrainedPipeline("mesh_umls_mapping","en","clinical/models")
pipeline.annotate("C028491 D019326 C579867")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("mesh_umls_mapping","en","clinical/models")
val result = pipeline.annotate("C028491 D019326 C579867")
import nlu
nlu.load("en.resolve.mesh.umls").predict("""C028491 D019326 C579867""")

Results

{'mesh': ['C028491', 'D019326', 'C579867'],
'umls': ['C0970275', 'C0886627', 'C3696376']}

Note:

| MeSH       | Details                      | 
| ---------- | ----------------------------:|
| C028491    |  1,3-butylene glycol         |
| D019326    | 17-alpha-Hydroxyprogesterone |
| C579867    | 3-Methylglutaconic Aciduria  |

| UMLS       | Details                     |
| ---------- | ---------------------------:|
| C0970275   | 1,3-butylene glycol         |
| C0886627   | 17-hydroxyprogesterone      |
| C3696376   | 3-methylglutaconic aciduria |

Model Information

Model Name: mesh_umls_mapping
Type: pipeline
Compatibility: Healthcare NLP 3.1.0+
License: Licensed
Edition: Official
Language: en

Included Models

  • DocumentAssembler
  • TokenizerModel
  • LemmatizerModel
  • Finisher