Description
This pipeline is designed to extract all entities mappable to UMLS CUI (Clinical Drug) codes.
How to use
from sparknlp.pretrained import PretrainedPipeline
ner_pipeline = PretrainedPipeline("ner_umls_clinical_drugs_pipeline", "en", "clinical/models")
result = ner_pipeline.annotate("""The patient was given Adapin 10 MG, coumadn 5 mg, Avandia 4 mg, Tegretol, zitiga.""")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val ner_pipeline = PretrainedPipeline("ner_umls_clinical_drugs_pipeline", "en", "clinical/models")
val result = ner_pipeline.annotate("""The patient was given Adapin 10 MG, coumadn 5 mg, Avandia 4 mg, Tegretol, zitiga.""")
Results
| | chunks | begin | end | entities |
|---:|:-------------|--------:|------:|:-----------|
| 0 | Adapin 10 MG | 23 | 34 | DRUG |
| 1 | coumadn 5 mg | 37 | 48 | DRUG |
| 2 | Avandia 4 mg | 51 | 62 | DRUG |
| 3 | Tegretol | 65 | 72 | DRUG |
| 4 | zitiga | 75 | 80 | DRUG |
Model Information
| Model Name: | ner_umls_clinical_drugs_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 6.0.2+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.7 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverter
- TextMatcherInternalModel
- ChunkMergeModel