Description
This pretrained pipeline is built on the top of ner_chexpert model.
Predicted Entities
ANAT, OBS
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("ner_chexpert_pipeline", "en", "clinical/models")
text = '''FINAL REPORT HISTORY : Chest tube leak , to assess for pneumothorax. FINDINGS : In comparison with study of ___ , the endotracheal tube and Swan - Ganz catheter have been removed . The left chest tube remains in place and there is no evidence of pneumothorax. Mild atelectatic changes are seen at the left base.'''
result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("ner_chexpert_pipeline", "en", "clinical/models")
val text = "FINAL REPORT HISTORY : Chest tube leak , to assess for pneumothorax. FINDINGS : In comparison with study of ___ , the endotracheal tube and Swan - Ganz catheter have been removed . The left chest tube remains in place and there is no evidence of pneumothorax. Mild atelectatic changes are seen at the left base."
val result = pipeline.fullAnnotate(text)
import nlu
nlu.load("en.med_ner.chexpert.pipeline").predict("""FINAL REPORT HISTORY : Chest tube leak , to assess for pneumothorax. FINDINGS : In comparison with study of ___ , the endotracheal tube and Swan - Ganz catheter have been removed . The left chest tube remains in place and there is no evidence of pneumothorax. Mild atelectatic changes are seen at the left base.""")
Results
| | ner_chunks | begin | end | ner_label | confidence |
|---:|:-------------|--------:|------:|:------------|-------------:|
| 0 | endotracheal | 118 | 129 | OBS | 0.9881 |
| 1 | tube | 131 | 134 | OBS | 0.9996 |
| 2 | Swan - Ganz | 140 | 150 | OBS | 0.9625 |
| 3 | catheter | 152 | 159 | OBS | 0.9919 |
| 4 | left | 185 | 188 | ANAT | 0.9983 |
| 5 | chest | 190 | 194 | ANAT | 0.9749 |
| 6 | tube | 196 | 199 | OBS | 0.9999 |
| 7 | in place | 209 | 216 | OBS | 0.9894 |
| 8 | pneumothorax | 246 | 257 | OBS | 0.9997 |
| 9 | Mild | 260 | 263 | OBS | 0.9988 |
| 10 | atelectatic | 265 | 275 | OBS | 0.9986 |
| 11 | changes | 277 | 283 | OBS | 0.9984 |
| 12 | left | 301 | 304 | ANAT | 0.9999 |
| 13 | base | 306 | 309 | ANAT | 0.9999 |
Model Information
| Model Name: | ner_chexpert_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.4.4+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.7 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverter