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.
Predicted Entities
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 3.0.2+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
Included Models
- DocumentAssembler
- TokenizerModel
- LemmatizerModel
- Finisher