Description
This pretrained pipeline is built on the top of ner_clinical_trials_abstracts model.
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("ner_clinical_trials_abstracts_pipeline", "en", "clinical/models")
result = pipeline.fullAnnotate("""A one-year, randomised, multicentre trial comparing insulin glargine with NPH insulin in combination with oral agents in patients with type 2 diabetes. In a multicentre, open, randomised study, 570 patients with Type 2 diabetes, aged 34 - 80 years, were treated for 52 weeks with insulin glargine or NPH insulin given once daily at bedtime.""")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("ner_clinical_trials_abstracts_pipeline", "en", "clinical/models")
val result = pipeline.fullAnnotate("""A one-year, randomised, multicentre trial comparing insulin glargine with NPH insulin in combination with oral agents in patients with type 2 diabetes. In a multicentre, open, randomised study, 570 patients with Type 2 diabetes, aged 34 - 80 years, were treated for 52 weeks with insulin glargine or NPH insulin given once daily at bedtime.""")
import nlu
nlu.load("en.med_ner.clinical_trials_abstracts.pipe").predict("""A one-year, randomised, multicentre trial comparing insulin glargine with NPH insulin in combination with oral agents in patients with type 2 diabetes. In a multicentre, open, randomised study, 570 patients with Type 2 diabetes, aged 34 - 80 years, were treated for 52 weeks with insulin glargine or NPH insulin given once daily at bedtime.""")
Results
+----------------+------------------+
| chunk| label|
+----------------+------------------+
| randomised| CTDesign|
| multicentre| CTDesign|
|insulin glargine| Drug|
| NPH insulin| Drug|
| type 2 diabetes|DisorderOrSyndrome|
| multicentre| CTDesign|
| open| CTDesign|
| randomised| CTDesign|
| 570| NumberPatients|
| Type 2 diabetes|DisorderOrSyndrome|
| 34| Age|
| 80| Age|
| 52 weeks| Duration|
|insulin glargine| Drug|
| NPH insulin| Drug|
| once daily| DrugTime|
| bedtime| DrugTime|
+----------------+------------------+
Model Information
| Model Name: | ner_clinical_trials_abstracts_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 3.5.3+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.7 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverter