Description
This pretrained pipeline is built on the top of bert_token_classifier_ner_clinical_trials_abstracts model.
Predicted Entities
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("bert_token_classifier_ner_clinical_trials_abstracts_pipeline", "en", "clinical/models")
text = '''This open-label, parallel-group, two-arm, pilot study compared the beta-cell protective effect of adding insulin glargine (GLA) vs. NPH insulin to ongoing metformin. Overall, 28 insulin-naive type 2 diabetes subjects (mean +/- SD age, 61.5 +/- 6.7 years; BMI, 30.7 +/- 4.3 kg/m(2)) treated with metformin and sulfonylurea were randomized to add once-daily GLA or NPH at bedtime.'''
result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("bert_token_classifier_ner_clinical_trials_abstracts_pipeline", "en", "clinical/models")
val text = "This open-label, parallel-group, two-arm, pilot study compared the beta-cell protective effect of adding insulin glargine (GLA) vs. NPH insulin to ongoing metformin. Overall, 28 insulin-naive type 2 diabetes subjects (mean +/- SD age, 61.5 +/- 6.7 years; BMI, 30.7 +/- 4.3 kg/m(2)) treated with metformin and sulfonylurea were randomized to add once-daily GLA or NPH at bedtime."
val result = pipeline.fullAnnotate(text)
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("bert_token_classifier_ner_clinical_trials_abstracts_pipeline", "en", "clinical/models")
text = '''This open-label, parallel-group, two-arm, pilot study compared the beta-cell protective effect of adding insulin glargine (GLA) vs. NPH insulin to ongoing metformin. Overall, 28 insulin-naive type 2 diabetes subjects (mean +/- SD age, 61.5 +/- 6.7 years; BMI, 30.7 +/- 4.3 kg/m(2)) treated with metformin and sulfonylurea were randomized to add once-daily GLA or NPH at bedtime.'''
result = pipeline.fullAnnotate(text)
Results
| | ner_chunk | begin | end | ner_label | confidence |
|---:|:-----------------|--------:|------:|:-------------------|-------------:|
| 0 | open-label | 5 | 14 | CTDesign | 0.742075 |
| 1 | parallel-group | 17 | 30 | CTDesign | 0.725741 |
| 2 | two-arm | 33 | 39 | CTDesign | 0.427547 |
| 3 | insulin glargine | 105 | 120 | Drug | 0.985063 |
| 4 | GLA | 123 | 125 | Drug | 0.96917 |
| 5 | NPH insulin | 132 | 142 | Drug | 0.762519 |
| 6 | metformin | 155 | 163 | Drug | 0.996344 |
| 7 | 28 | 175 | 176 | NumberPatients | 0.968501 |
| 8 | type 2 diabetes | 192 | 206 | DisorderOrSyndrome | 0.979685 |
| 9 | 61.5 | 235 | 238 | Age | 0.610416 |
| 10 | kg/m(2 | 273 | 278 | BioAndMedicalUnit | 0.974807 |
| 11 | metformin | 295 | 303 | Drug | 0.99696 |
| 12 | sulfonylurea | 309 | 320 | Drug | 0.996722 |
| 13 | randomized | 327 | 336 | CTDesign | 0.990632 |
| 14 | once-daily | 345 | 354 | DrugTime | 0.472084 |
| 15 | GLA | 356 | 358 | Drug | 0.972978 |
| 16 | NPH | 363 | 365 | Drug | 0.989424 |
| 17 | bedtime | 370 | 376 | DrugTime | 0.936016 |
Model Information
| Model Name: | bert_token_classifier_ner_clinical_trials_abstracts_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.4.4+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 404.9 MB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- MedicalBertForTokenClassifier
- NerConverterInternalModel