Description
This pretrained pipeline maps entities with their corresponding CVX codes. You’ll just feed your text and it will return the corresponding CVX codes.
Predicted Entities
Vaccine
How to use
from sparknlp.pretrained import PretrainedPipeline
resolver_pipeline = PretrainedPipeline("cvx_resolver_pipeline", "en", "clinical/models")
text= "The patient has a history of influenza vaccine, tetanus and DTaP"
result = resolver_pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val resolver_pipeline = new PretrainedPipeline("cvx_resolver_pipeline", "en", "clinical/models")
val result = resolver_pipeline.fullAnnotate("The patient has a history of influenza vaccine, tetanus and DTaP")
import nlu
nlu.load("en.resolve.cvx_pipeline").predict("""The patient has a history of influenza vaccine, tetanus and DTaP""")
Results
+-----------------+---------+--------+
|chunk |ner_chunk|cvx_code|
+-----------------+---------+--------+
|influenza vaccine|Vaccine |160 |
|tetanus |Vaccine |35 |
|DTaP |Vaccine |20 |
+-----------------+---------+--------+
Model Information
Model Name: | cvx_resolver_pipeline |
Type: | pipeline |
Compatibility: | Healthcare NLP 4.2.1+ |
License: | Licensed |
Edition: | Official |
Language: | en |
Size: | 2.1 GB |
Included Models
- DocumentAssembler
- SentenceDetector
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverterInternalModel
- ChunkMapperModel
- ChunkMapperFilterer
- Chunk2Doc
- BertSentenceEmbeddings
- SentenceEntityResolverModel
- ResolverMerger