Description
This pretrained pipeline is built on the top of bert_token_classifier_ner_jsl_slim model.
Predicted Entities
Admission_Discharge, Age, Alergen, Birth_Entity, Body_Part, Clinical_Dept, Date_Time, Death_Entity, Demographics, Disease_Syndrome_Disorder, Drug, Header, Lifestyle, Medical_Device, Oncological, Physical_Measurement, Pregnancy_Newborn, Procedure, Substance_Quantity, Symptom, Test, Test_Result, Treatment, Vital_Sign
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("bert_token_classifier_ner_jsl_slim_pipeline", "en", "clinical/models")
text = '''HISTORY: 30-year-old female presents for digital bilateral mammography secondary to a soft tissue lump palpated by the patient in the upper right shoulder. The patient has a family history of breast cancer within her mother at age 58. Patient denies personal history of breast cancer.'''
result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("bert_token_classifier_ner_jsl_slim_pipeline", "en", "clinical/models")
val text = "HISTORY: 30-year-old female presents for digital bilateral mammography secondary to a soft tissue lump palpated by the patient in the upper right shoulder. The patient has a family history of breast cancer within her mother at age 58. Patient denies personal history of breast cancer."
val result = pipeline.fullAnnotate(text)
import nlu
nlu.load("en.classify.token_bert.jsl_slim.pipeline").predict("""HISTORY: 30-year-old female presents for digital bilateral mammography secondary to a soft tissue lump palpated by the patient in the upper right shoulder. The patient has a family history of breast cancer within her mother at age 58. Patient denies personal history of breast cancer.""")
Results
| | ner_chunk | begin | end | ner_label | confidence |
|---:|:-----------------|--------:|------:|:-------------|-------------:|
| 0 | HISTORY: | 0 | 7 | Header | 0.994786 |
| 1 | 30-year-old | 9 | 19 | Age | 0.982408 |
| 2 | female | 21 | 26 | Demographics | 0.99981 |
| 3 | mammography | 59 | 69 | Test | 0.993892 |
| 4 | soft tissue lump | 86 | 101 | Symptom | 0.999448 |
| 5 | shoulder | 146 | 153 | Body_Part | 0.99978 |
| 6 | breast cancer | 192 | 204 | Oncological | 0.999466 |
| 7 | her mother | 213 | 222 | Demographics | 0.997765 |
| 8 | age 58 | 227 | 232 | Age | 0.997636 |
| 9 | breast cancer | 270 | 282 | Oncological | 0.999452 |
Model Information
| Model Name: | bert_token_classifier_ner_jsl_slim_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 405.0 MB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- MedicalBertForTokenClassifier
- NerConverterInternalModel