Description
This pretrained pipeline is built on the top of ner_oncology_test model.
Predicted Entities
Biomarker, Biomarker_Result, Imaging_Test, Oncogene, Pathology_Test
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("ner_oncology_test_pipeline", "en", "clinical/models")
text = ''' biopsy was conducted using an ultrasound guided thick-needle. His chest computed tomography (CT) scan was negative.'''
result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("ner_oncology_test_pipeline", "en", "clinical/models")
val text = " biopsy was conducted using an ultrasound guided thick-needle. His chest computed tomography (CT) scan was negative."
val result = pipeline.fullAnnotate(text)
Results
| | ner_chunks | begin | end | ner_label | confidence |
|---:|:--------------------------|--------:|------:|:---------------|-------------:|
| 0 | biopsy | 1 | 6 | Pathology_Test | 0.9987 |
| 1 | ultrasound guided | 31 | 47 | Imaging_Test | 0.87635 |
| 2 | chest computed tomography | 67 | 91 | Imaging_Test | 0.9176 |
| 3 | CT | 94 | 95 | Imaging_Test | 0.8294 |
Model Information
| Model Name: | ner_oncology_test_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.7 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverterInternalModel