Description
This pipeline is designed to extract all entities mappable to UMLS CUI codes.
How to use
from sparknlp.pretrained import PretrainedPipeline
ner_pipeline = PretrainedPipeline("ner_umls_clinical_findings_pipeline", "en", "clinical/models")
result = ner_pipeline.annotate("""HTG-induced pancreatitis associated with an acute hepatitis, and obesity.""")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val ner_pipeline = PretrainedPipeline("ner_umls_clinical_findings_pipeline", "en", "clinical/models")
val result = ner_pipeline.annotate("""HTG-induced pancreatitis associated with an acute hepatitis, and obesity.""")
Results
| | chunks | begin | end | entities |
|---:|:-------------------------|--------:|------:|:-----------|
| 0 | HTG-induced pancreatitis | 1 | 24 | PROBLEM |
| 1 | an acute hepatitis | 42 | 59 | PROBLEM |
| 2 | obesity | 66 | 72 | PROBLEM |
Model Information
| Model Name: | ner_umls_clinical_findings_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
- NerConverterInternalModel