Description
This pretrained pipeline maps entities (Clinical Drugs) with their corresponding UMLS CUI codes. You’ll just feed your text and it will return the corresponding UMLS codes.
Available as Private API Endpoint
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline= PretrainedPipeline("umls_drug_resolver_pipeline", "en", "clinical/models")
pipeline.annotate("The patient was given Adapin 10 MG, coumadn 5 mg")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline= PretrainedPipeline("umls_drug_resolver_pipeline", "en", "clinical/models")
val pipeline.annotate("The patient was given Adapin 10 MG, coumadn 5 mg")
import nlu
nlu.load("en.map_entity.umls_drug_resolver").predict("""The patient was given Adapin 10 MG, coumadn 5 mg""")
Results
+------------+---------+---------+
|chunk |ner_label|umls_code|
+------------+---------+---------+
|Adapin 10 MG|DRUG |C2930083 |
|coumadn 5 mg|DRUG |C2723075 |
+------------+---------+---------+
Model Information
| Model Name: | umls_drug_resolver_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.0.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 4.6 GB |
Included Models
- DocumentAssembler
- SentenceDetector
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverter
- ChunkMapperModel
- ChunkMapperModel
- ChunkMapperFilterer
- Chunk2Doc
- BertSentenceEmbeddings
- SentenceEntityResolverModel
- ResolverMerger